{"content": "1 thing in the record have evidence against them \u2014 fact:34 names settings.json, which is gone \u2014 journal fact 34 strike \"\"", "meta": {"from": "journal"}} {"content": "fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply \"\" instead of the tag.; rule 66 \u2014 The journal never slows the agent down \u2014 The user, message 18990, after hooks timed out and waited on locks under load: the journal must never, ever decrease the performance of an agent. A hook answers at once with what decides the tool call; everything else runs after, in the background, and reaches the agent as a message. No hook waits on a lock it does not need.", "meta": {"from": "journal"}} {"content": "rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.; your answer to a journal line was kept out of the chat \u2014 a journal line is an instruction, not a message: act on it and write nothing, unless the user needs to know something such as a failure, finished work or a decision that waits on them", "meta": {"from": "journal"}} {"content": "fact 13 \u2014 This live session runs the installed copy in .journal/journal.pyz \u2014 The running journal (server, hooks, CLI) runs from .journal/journal.pyz with its viewer and skills in .journal/src, never from the repo. A change in the repo reaches it only through python3 src/journal.py --root .journal upgrade, which packs the zip again. A commit alone changes nothing that is running.; fact 20 \u2014 A slim supervisor holds the agent and a worker reloads on every build \u2014 Since 2.118.0 (2026-09-23). src/supervisor.py is standard library only and never reloads: journal claude hands its process over to it (os.execv), and it owns the pty and the agent process, relays the terminal, writes the printed and screen captures, listens on the typist socket, restarts the agent in the same session from a relaunch command written to its runtime folder while a restart is pending, and stops it with escalation while draining the pty (an agent cannot finish exiting on macOS while its output is unread). It starts the worker (src/worker.py, which runs runner/worker.py; engine/worker.py stays as an alias for supervisors started before 2.201) and starts it again whenever it exits: RELOAD on a new build, RELAUNCH to restart the agent, STOP to end, HEAL or a quick crash to roll back a build through journal heal. The worker holds everything else: seating the session, the start-up confirm typed through the typist, services, viewer, update check, check-in, and the one-time relaunch of sessions launched before agents/terminal.py LAUNCH. agents/terminal.py holds only journal-side helpers. The server (serve.py) still runs the engines and re-execs itself on a .py change. When the agent exits, the supervisor runs journal ended, which puts set-aside hooks back and stops the server when no session is left.; fact 25 \u2014 A designer's install packs the whole tree, half-done server edits\u2026 \u2014 2026-09-25: Eames and Saul run python3 src/journal.py --root .journal upgrade after their viewer builds; it packs every file in src, so a server handler I was halfway through writing went live and raised on every PostToolUse hook. While designers work in parallel, keep server edits whole between tool calls (write and test in the scratchpad first), and reinstall after reverting anything.", "meta": {"from": "journal"}} {"content": "rule 40 \u2014 A feature is named for what it is, never for its machinery \u2014 Messages 599, 600 and 703. A feature is a capability the user would name and would think of switching off. File tracking, a write gate, a phrase bank, a tree diff are services used inside a feature, not features of their own: they live in the feature they serve. Before adding a directory under features/, say what the user would call it; if the answer names a mechanism, it belongs inside something else. Report 16 holds the grouping this implies.", "meta": {"from": "journal"}} {"content": "law L3 \u2014 Read narrowly - grep for the line, sed a range, head the file; never\u2026 \u2014 Everything a tool returns stays in the context for good and is paid for on every turn after it. Search before you read, read the range you need, and cap output with grep, head or tail. Read a whole file only when you need all of it.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 3 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 3 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; the end tag does this in one step \u2014 [!end:N] makes the turn itself what landed; it runs only when it opens the last text of your turn; fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal . A helper added to the base class therefore becomes a command on every type \u2014 which is how journal handled and journal refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.; fact 34 \u2014 A hooks list in a checkout's .claude/settings.json stops every\u2026 \u2014 Seen 2026-10-08: since commit 707a82915 the committed .claude/settings.json held {\"hooks\": []}; current Claude Code answers a hooks value that is not an object with a SettingsWarning dialog, which a headless helper cannot answer, so helpers 183 and 184 exited before doing anything (their launch logs in .journal/runtime/launches/ show it). This repository's journal hooks live in settings.local.json; the committed settings.json stays {}.; rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done --how, or by a commit whose message carries Journal: todos done at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.; rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 3 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 3 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "rule 51 \u2014 Every finished feature is committed, pushed and released with a new\u2026 \u2014 Message 9207 (2026-09-24): when a new feature is ready, commit, push and publish a new tag. This is the user's standing word for releasing, so rule 44's only-when-the-user-says is met by it for finished features; fixes in between wait for the next feature or a patch the user asks for.", "meta": {"from": "journal"}} {"content": "rule 27 \u2014 Name a declaration with the word a reader already knows \u2014 An attribute, a variable or a field gets the ordinary programming word for what it holds, not an evocative one. was, heard and alone were poetry; aliases, notify_actions and urgent_actions are what they are. The test: could a reader who has never seen this codebase guess what it holds from the name alone? Prose belongs in the help text and the abstract, where it is read as prose. This does not license abbreviations \u2014 a plain word in full, not a short one.", "meta": {"from": "journal"}} {"content": "rule 61 \u2014 Features wait as pull requests until approved; only hotfixes merge\u2026 \u2014 Message 17118 (2026-10-06), after the overnight refactor merged as 2.252.0: start new work in a new branch, do not merge, write the pull request. Every pull request or new feature is parked until the user approves it. Hotfixes can be merged into main immediately (by a dispatched agent in a worktree of main, rule 60).", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 4 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "rule 38 \u2014 Never change the git branch until the user says so, by name \u2014 The work happens on the branch the user named. That was main until message 5929 and question 80 (2026-09-23), which moved the sins work to the branch sins. Do not create, switch to or merge any other branch unless the user names it in their own words.; rule 64 \u2014 A finished feature is merged into main without waiting for approval \u2014 The user, message 17815 (2026-10-07): 'make sure that no pull requests are lingering on the repository. You may merge them into main... You are allowed to merge everything into main once the feature is completed.' This replaces rule 61's wait for approval: a feature still goes on its own branch, and once it is complete, tested and its whole suite passes, it is merged into main and released, and no pull request is left open.", "meta": {"from": "journal"}} {"content": "rule 65 \u2014 Run only new and affected tests while working; the whole suite only\u2026 \u2014 The user, messages 17914 to 17917 (2026-10-07): 'stop running the whole test suite and wasting my time... please only run the new or affected tests, and then, whenever you are merging to main or publishing to main, you can run the full test suite.' Replaces rule 41's whole suite before every commit: on a feature branch, run the tests beside what changed (journal check touched, or the feature's test.py and the browser scenarios it touches); the whole suite runs once, before a merge into main and its release.", "meta": {"from": "journal"}} {"content": "your command ran 33s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 33s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 3", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 3", "meta": {"from": "journal"}} {"content": "the viewer test run came back\u2026", "meta": {"from": "journal"}} {"content": "the end tag does this in one step \u2014 [!end:N] makes the turn itself what landed; it runs only when it opens the last text of your turn; rule 54 \u2014 Settings and feature switches are read at boot and on change, never\u2026 \u2014 The user, message 13349: the application boots, determines every feature and setting once, and re-evaluates only when something changes, such as a setting or a plugin. Never lazy-load settings.; rule 57 \u2014 Never merge the overnight refactor into main before its pull request\u2026 \u2014 Messages 15005, 15006, 15109, 15110 (2026-10-04): all refactor work goes on branch overnight-refactor and reaches the user as one pull request, which they read in the morning; nothing of it is merged into main until they say so. Hotfixes the user explicitly asks for go to main at once and are merged into the branch.", "meta": {"from": "journal"}} {"content": "todo 3 next", "meta": {"from": "journal"}} {"content": "rule 48 \u2014 The viewer is built from its component library, and pages only\u2026 \u2014 Message 4258. Every visual piece the viewer shows more than once, or that a user would recognise as the same kind of thing (a dialog, a side panel or inspector, a dropdown, a list row, a switch, a button), is one component in web/src/kit, extracted aggressively, and every page composes those components instead of building its own copy. Before writing markup or styles in a page, look for the kit component that already does it and extend it with a prop; a second hand-built version is a bug. The side panel that animated in but not out, while a separate skill panel did both, is the example.", "meta": {"from": "journal"}} {"content": "your command ran 30s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 30s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "auto mode is on and work 7 stands still while todo 3 is ready \u2014 if work 7 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 3. Stop only when nothing ready is left.; work 7 is still open, with nothing logged \u2014 journal work log 7 \"\" \u2014 then journal work end 7 --how \"\", or journal work park 7 \"\"", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "your command ran 30s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "work 7 is still open \u2014 end it or park it before you stop: journal work end 7 --how \"\", or journal work park 7 \"\"", "meta": {"from": "journal"}} {"content": "work 7 is still open \u2014 end it or park it before you stop: journal work end 7 --how \"\", or journal work park 7 \"\"", "meta": {"from": "journal"}} {"content": "work 7 is still open \u2014 end it or park it before you stop: journal work end 7 --how \"\", or journal work park 7 \"\"", "meta": {"from": "journal"}} {"content": "work 7 is still open \u2014 end it or park it before you stop: journal work end 7 --how \"\", or journal work park 7 \"\"", "meta": {"from": "journal"}} {"content": "work 7 is still open \u2014 end it or park it before you stop: journal work end 7 --how \"\", or journal work park 7 \"\"", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "waiting: 3 unread todos 5, 6, 7", "meta": {"from": "journal"}} {"content": "the agent cell and waiting scenarios came back - cd\u2026", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "fact 18 \u2014 cProfile inflates the slow-request profiles about tenfold \u2014 The faults feature writes a profile when a request passes its budget, and the profile is taken with cProfile, which adds per-call overhead. On 2026-09-22 /api/summary profiled at 58ms with 48ms inside Resource.fork's deep copy; with the profiler off the same call ran in 2 to 7ms. Read the profile for where the time goes in relative terms, then time the call with curl before changing anything.; rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.", "meta": {"from": "journal"}} {"content": "rule 43 \u2014 A request or hook over its budget is fixed before the next release \u2014 Comment 1151 on this rule. When the faults feature reports a request, a hook or a command slower than its budget, file it as a to-do at once. It does not jump ahead of the work in hand, but no version is published while one is still open: profile it, fix it, and verify the new time before the release goes out. The budget is 50ms, because everything runs locally against files.", "meta": {"from": "journal"}} {"content": "law L3 \u2014 Read narrowly - grep for the line, sed a range, head the file; never\u2026 \u2014 Everything a tool returns stays in the context for good and is paid for on every turn after it. Search before you read, read the range you need, and cap output with grep, head or tail. Read a whole file only when you need all of it.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 11 stands still while todo 5 is ready \u2014 if work 11 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 5. Stop only when nothing ready is left.; work 11 is still open, with nothing logged \u2014 journal work log 11 \"\" \u2014 then journal work end 11 --how \"\", or journal work park 11 \"\"", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"I'm still waiting\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "the post-expiry dashboard timing came back\u2026", "meta": {"from": "journal"}} {"content": "fact 20 \u2014 A slim supervisor holds the agent and a worker reloads on every build \u2014 Since 2.118.0 (2026-09-23). src/supervisor.py is standard library only and never reloads: journal claude hands its process over to it (os.execv), and it owns the pty and the agent process, relays the terminal, writes the printed and screen captures, listens on the typist socket, restarts the agent in the same session from a relaunch command written to its runtime folder while a restart is pending, and stops it with escalation while draining the pty (an agent cannot finish exiting on macOS while its output is unread). It starts the worker (src/worker.py, which runs runner/worker.py; engine/worker.py stays as an alias for supervisors started before 2.201) and starts it again whenever it exits: RELOAD on a new build, RELAUNCH to restart the agent, STOP to end, HEAL or a quick crash to roll back a build through journal heal. The worker holds everything else: seating the session, the start-up confirm typed through the typist, services, viewer, update check, check-in, and the one-time relaunch of sessions launched before agents/terminal.py LAUNCH. agents/terminal.py holds only journal-side helpers. The server (serve.py) still runs the engines and re-execs itself on a .py change. When the agent exits, the supervisor runs journal ended, which puts set-aside hooks back and stops the server when no session is left.; fact 28 \u2014 The designer agent type exists, so design work goes to a subagent \u2014 Since 2026-10-01 .claude/agents/designer.md (Dieter, Opus, Claude Design tools, read-only on the repository) is an agent type; rule 56 says design is a subagent's job, never a helper's.; rule 58 \u2014 A design runs three critique rounds, then is built on a branch \u2014 Messages 17276 and 17281 (2026-10-06): the norm is a three-round cycle. Round by round, the designer designs (or revises), separate critic agents review the design through their lenses (the critic agent type, .claude/agents/critic.md: read-only, with a browser; one per lens, such as first-time, native, words and parity), and the designer adjusts it to their findings; three rounds in all. The three rounds stand in for the user's approval of the design: the user does not approve it. After the third round the design is built on a branch of its own, which ends in a pull request that waits for the user's approval (rule 61). Replaces message 15725's prototype approval.; work 11 is still open \u2014 end it or park it before you stop: journal work end 11 --how \"\", or journal work park 11 \"\"", "meta": {"from": "journal"}} {"content": "law L5 \u2014 Every subagent dispatch names the agent, in the naming style of the\u2026 \u2014 A name is how the user and the chat tell subagents apart and how they are messaged later; an id or a task line is not a name. Start the dispatch's description with the name, a colon, then the task. The profile in use says how its agents are named.; rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal . A helper added to the base class therefore becomes a command on every type \u2014 which is how journal handled and journal refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 3 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 3 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 11 is still open \u2014 end it or park it before you stop: journal work end 11 --how \"\", or journal work park 11 \"\"", "meta": {"from": "journal"}} {"content": "fact 34 \u2014 A hooks list in a checkout's .claude/settings.json stops every\u2026 \u2014 Seen 2026-10-08: since commit 707a82915 the committed .claude/settings.json held {\"hooks\": []}; current Claude Code answers a hooks value that is not an object with a SettingsWarning dialog, which a headless helper cannot answer, so helpers 183 and 184 exited before doing anything (their launch logs in .journal/runtime/launches/ show it). This repository's journal hooks live in settings.local.json; the committed settings.json stays {}.; rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done --how, or by a commit whose message carries Journal: todos done at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.", "meta": {"from": "journal"}} {"content": "rule 61 \u2014 Features wait as pull requests until approved; only hotfixes merge\u2026 \u2014 Message 17118 (2026-10-06), after the overnight refactor merged as 2.252.0: start new work in a new branch, do not merge, write the pull request. Every pull request or new feature is parked until the user approves it. Hotfixes can be merged into main immediately (by a dispatched agent in a worktree of main, rule 60).; rule 64 \u2014 A finished feature is merged into main without waiting for approval \u2014 The user, message 17815 (2026-10-07): 'make sure that no pull requests are lingering on the repository. You may merge them into main... You are allowed to merge everything into main once the feature is completed.' This replaces rule 61's wait for approval: a feature still goes on its own branch, and once it is complete, tested and its whole suite passes, it is merged into main and released, and no pull request is left open.", "meta": {"from": "journal"}} {"content": "fact 23 \u2014 Every upgrade brings system sequences and their triggers in line\u2026 \u2014 install.py runs ship_sequences after the migrations on each upgrade, so features/sequences/shipped.py is the whole source: change its wording and the next upgrade updates every journal, no migration needed. Shipped rows carry system=True and are read-only for everyone but SYSTEM (controllers/base.py _shipped).; rule 27 \u2014 Name a declaration with the word a reader already knows \u2014 An attribute, a variable or a field gets the ordinary programming word for what it holds, not an evocative one. was, heard and alone were poetry; aliases, notify_actions and urgent_actions are what they are. The test: could a reader who has never seen this codebase guess what it holds from the name alone? Prose belongs in the help text and the abstract, where it is read as prose. This does not license abbreviations \u2014 a plain word in full, not a short one.", "meta": {"from": "journal"}} {"content": "rule 40 \u2014 A feature is named for what it is, never for its machinery \u2014 Messages 599, 600 and 703. A feature is a capability the user would name and would think of switching off. File tracking, a write gate, a phrase bank, a tree diff are services used inside a feature, not features of their own: they live in the feature they serve. Before adding a directory under features/, say what the user would call it; if the answer names a mechanism, it belongs inside something else. Report 16 holds the grouping this implies.", "meta": {"from": "journal"}} {"content": "rule 48 \u2014 The viewer is built from its component library, and pages only\u2026 \u2014 Message 4258. Every visual piece the viewer shows more than once, or that a user would recognise as the same kind of thing (a dialog, a side panel or inspector, a dropdown, a list row, a switch, a button), is one component in web/src/kit, extracted aggressively, and every page composes those components instead of building its own copy. Before writing markup or styles in a page, look for the kit component that already does it and extend it with a prop; a second hand-built version is a bug. The side panel that animated in but not out, while a separate skill panel did both, is the example.; rule 54 \u2014 Settings and feature switches are read at boot and on change, never\u2026 \u2014 The user, message 13349: the application boots, determines every feature and setting once, and re-evaluates only when something changes, such as a setting or a plugin. Never lazy-load settings.; rule 65 \u2014 Run only new and affected tests while working; the whole suite only\u2026 \u2014 The user, messages 17914 to 17917 (2026-10-07): 'stop running the whole test suite and wasting my time... please only run the new or affected tests, and then, whenever you are merging to main or publishing to main, you can run the full test suite.' Replaces rule 41's whole suite before every commit: on a feature branch, run the tests beside what changed (journal check touched, or the feature's test.py and the browser scenarios it touches); the whole suite runs once, before a merge into main and its release.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 6 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 6 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "the integrations test came back - sed -i 's/^ from controllers.types import\u2026", "meta": {"from": "journal"}} {"content": "law L6 \u2014 A journal line is an instruction, never a message - act on it and\u2026 \u2014 A line that starts with [journal], a reminder, a notice or an old helper report is the journal telling the agent what to do, not the user speaking. Answering it fills the user's chat with noise. Act on it, or note it and carry on; write in the chat only what the user needs to know, such as a failure, a finished piece of work or a decision that waits on them.", "meta": {"from": "journal"}} {"content": "todo 9 next", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 9", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 9", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 9", "meta": {"from": "journal"}} {"content": "todo 9 next", "meta": {"from": "journal"}} {"content": "13 facts standing, read them \u2014 9. Every public method on a controller becomes a journal command; 13. This live session runs the installed copy in .journal/journal.pyz; 18. cProfile inflates the slow-request profiles about tenfold; 20. A slim supervisor holds the agent and a worker reloads on every build; 23. Every upgrade brings system sequences and their triggers in line with the code; 24. An answer followed by tool calls can be missing from Claude's transcript; 25. A designer's install packs the whole tree, half-done server edits included; 26. Claude Code reads agent profiles when a session starts; 27. Running src/journal.py against the live .journal root starts a second server; 28. The designer agent type exists, so design work goes to a subagent; 29. Codex's transcript records the end of every exec session, polled or not; 30. The tunler server refuses TLS for any subdomain without a tunnel; 34. A hooks list in a checkout's .claude/settings.json stops every helper at start; 43 rules in force, read them \u2014 7. journal disable must only ever be run because the user explicitly asked for it,; 9. Research dispatched to a subagent ends in a REPORT for the user, compiled by the; 13. A title names the thing in at most 80 characters and never explains it with a co; 14. A small journal capability is a feature under features, with at most one test; 17. Do not restart the viewer for frontend-only changes; 18. Provider-specific code belongs in providers, never features; 19. Providers report facts; features decide behavior; 22. File distinct user work requests immediately; 27. Name a declaration with the word a reader already knows; 30. The viewer has one API client, and every piece of it does one job; 31. Every finding a reviewing agent reports becomes its own to-do; 35. Write clean code - one funnel per kind of operation, never the same method twice; 36. Clean, DRY, idiomatic before it is committed, never after it is complained about; 37. Close every to-do explicitly with todo done or a Journal commit trailer; 38. Never change the git branch until the user says so, by name; 39. Use only registered exclamation response tags; 40. A feature is named for what it is, never for its machinery; 41. Keep moving, run the whole suite before every commit, never wait; 42. Every user-facing text passes the formatters before it leaves the server; 43. A request or hook over its budget is fixed before the next release; 45. No prose words as names in code - said, says, heard, spoke, told, shown, became; 46. Only commit and push once the whole journal is proven to boot; 47. The journal sets itself up once, when the server starts, never per command; 48. The viewer is built from its component library, and pages only compose it; 49. A dialog whose content grows keeps one fixed height, and its content scrolls; 50. Everything the user does is doable in the viewer; 51. Every finished feature is committed, pushed and released with a new version tag; 52. A chat mark for something the user did sits on the user's side; 54. Settings and feature switches are read at boot and on change, never per call; 55. Always dispatch Codex helpers on gpt-6-sol; 56. Helpers are for work that writes; subagents read, research and design; 57. Never merge the overnight refactor into main before its pull request is approved; 58. A design runs three critique rounds, then is built on a branch; 59. Every viewer heading and label says plainly what it is about; 60. A hotfix is done by a dispatched agent in a worktree of main; 61. Features wait as pull requests until approved; only hotfixes merge at once; 62. The voice profile shapes only the agent's chat speech, never code or text; 63. A small design is drawn once and the user approves it, with no critique rounds; 64. A finished feature is merged into main without waiting for approval; 65. Run only new and affected tests while working; the whole suite only before main; 66. The journal never slows the agent down; 67. Never answer a journal line in the chat; act on it silently; 68. The orchestrator approves the designer's designs itself", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 10", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 10", "meta": {"from": "journal"}} {"content": "rule 66 \u2014 The journal never slows the agent down \u2014 The user, message 18990, after hooks timed out and waited on locks under load: the journal must never, ever decrease the performance of an agent. A hook answers at once with what decides the tool call; everything else runs after, in the background, and reaches the agent as a message. No hook waits on a lock it does not need.", "meta": {"from": "journal"}} {"content": "rule 49 \u2014 A dialog whose content grows keeps one fixed height, and its content\u2026 \u2014 Message 5361, after asking more than once: a dialog that shows output as it arrives (install, update, logs) opens at its final height and never jumps; only its content scrolls.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply \"\" instead of the tag.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 2 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.", "meta": {"from": "journal"}} {"content": "work 15 in hand \u2014 Handled messages colour their check marks \u2014 if this is not what you are doing, end it or park it and start the work you are in", "meta": {"from": "journal"}} {"content": "the messages test came back - python3 - <<'E'", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 2 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "fact 18 \u2014 cProfile inflates the slow-request profiles about tenfold \u2014 The faults feature writes a profile when a request passes its budget, and the profile is taken with cProfile, which adds per-call overhead. On 2026-09-22 /api/summary profiled at 58ms with 48ms inside Resource.fork's deep copy; with the profiler off the same call ran in 2 to 7ms. Read the profile for where the time goes in relative terms, then time the call with curl before changing anything.", "meta": {"from": "journal"}} {"content": "fact 13 \u2014 This live session runs the installed copy in .journal/journal.pyz \u2014 The running journal (server, hooks, CLI) runs from .journal/journal.pyz with its viewer and skills in .journal/src, never from the repo. A change in the repo reaches it only through python3 src/journal.py --root .journal upgrade, which packs the zip again. A commit alone changes nothing that is running.; rule 38 \u2014 Never change the git branch until the user says so, by name \u2014 The work happens on the branch the user named. That was main until message 5929 and question 80 (2026-09-23), which moved the sins work to the branch sins. Do not create, switch to or merge any other branch unless the user names it in their own words.; rule 43 \u2014 A request or hook over its budget is fixed before the next release \u2014 Comment 1151 on this rule. When the faults feature reports a request, a hook or a command slower than its budget, file it as a to-do at once. It does not jump ahead of the work in hand, but no version is published while one is still open: profile it, fix it, and verify the new time before the release goes out. The budget is 50ms, because everything runs locally against files.; rule 57 \u2014 Never merge the overnight refactor into main before its pull request\u2026 \u2014 Messages 15005, 15006, 15109, 15110 (2026-10-04): all refactor work goes on branch overnight-refactor and reaches the user as one pull request, which they read in the morning; nothing of it is merged into main until they say so. Hotfixes the user explicitly asks for go to main at once and are merged into the branch.; rule 60 \u2014 A hotfix is done by a dispatched agent in a worktree of main \u2014 Message 16836 (2026-10-06): the orchestrator cut a worktree under .claude/worktrees for a Codex hotfix, its session moved to a new environment and the user's messages stopped reaching it. The user: when working on a branch and a hotfix comes in, create a worktree of main and dispatch an agent to do that work. The orchestrator stays on its branch and in its environment, and never cds into another checkout.", "meta": {"from": "journal"}} {"content": "law L5 \u2014 Every subagent dispatch names the agent, in the naming style of the\u2026 \u2014 A name is how the user and the chat tell subagents apart and how they are messaged later; an id or a task line is not a name. Start the dispatch's description with the name, a colon, then the task. The profile in use says how its agents are named.; rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 you're editing `test_every_action.py`, a test/stub/fixture\u2026 \u2014 Code Commandments \u2014 you're editing `test_every_action.py`, a test/stub/fixture that `judge` never scans, so nothing here will flag a symptom-fix. If you're changing it to make a failing check pass, first ask WHERE the failure is born: a failing test usually means the PRODUCTION code is missing behaviour \u2014 a method, a type, a total value on the real type. Fix it THERE (trace to the source; re-open the relevant skill), and change this file only if the TEST itself is wrong. If this is just legitimate test coverage, carry on.; that Edit call returned 75,922 characters, the largest this session \u2014 It stays in the context for good. If you were looking for one thing in it, the next read can be narrower: grep for the line, sed a range, head the file.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 16 stands still while todo 12 is ready \u2014 if work 16 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 12. Stop only when nothing ready is left.; Code Commandments \u2014 before you wrap up \u2014 you've changed 5 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 5 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 16 is still open, with nothing logged \u2014 journal work log 16 \"\" \u2014 then journal work end 16 --how \"\", or journal work park 16 \"\"", "meta": {"from": "journal"}} {"content": "work 16 is still open \u2014 end it or park it before you stop: journal work end 16 --how \"\", or journal work park 16 \"\"", "meta": {"from": "journal"}} {"content": "work 16 is still open \u2014 end it or park it before you stop: journal work end 16 --how \"\", or journal work park 16 \"\"", "meta": {"from": "journal"}} {"content": "the listing test came back - cd\u2026", "meta": {"from": "journal"}} {"content": "work 16 is still open \u2014 end it or park it before you stop: journal work end 16 --how \"\", or journal work park 16 \"\"", "meta": {"from": "journal"}} {"content": "your command ran 31s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "rule 42 \u2014 Every user-facing text passes the formatters before it leaves the\u2026 \u2014 Not only a brief. A title, an abstract, an outcome and every section body are read by a person, so each goes through the same formatters on its way to the viewer \u2014 chat turns, activity items, to-do rows, inspector pages, docs alike. One field formatted out of five is not a rule, it is an accident, and it is how a raw tag ended up in the activity list after the tags feature had been stripping them for weeks. When a new field carries words a person reads, it joins the list in the same place.", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal . A helper added to the base class therefore becomes a command on every type \u2014 which is how journal handled and journal refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.; fact 34 \u2014 A hooks list in a checkout's .claude/settings.json stops every\u2026 \u2014 Seen 2026-10-08: since commit 707a82915 the committed .claude/settings.json held {\"hooks\": []}; current Claude Code answers a hooks value that is not an object with a SettingsWarning dialog, which a headless helper cannot answer, so helpers 183 and 184 exited before doing anything (their launch logs in .journal/runtime/launches/ show it). This repository's journal hooks live in settings.local.json; the committed settings.json stays {}.; rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done --how, or by a commit whose message carries Journal: todos done at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 5 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 5 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "waiting: 5 unread todos 12, 13, 14, 15, 16", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "the listing test came back - python3 - <<'E'", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 18", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 18", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 18", "meta": {"from": "journal"}} {"content": "your command ran 35s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"Still waiting\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "waiting: 3 unread todos 18, 19, 20", "meta": {"from": "journal"}} {"content": "the lists scenarios came back\u2026", "meta": {"from": "journal"}} {"content": "fact 23 \u2014 Every upgrade brings system sequences and their triggers in line\u2026 \u2014 install.py runs ship_sequences after the migrations on each upgrade, so features/sequences/shipped.py is the whole source: change its wording and the next upgrade updates every journal, no migration needed. Shipped rows carry system=True and are read-only for everyone but SYSTEM (controllers/base.py _shipped).", "meta": {"from": "journal"}} {"content": "rule 45 \u2014 No prose words as names in code - said, says, heard, spoke, told\u2026 \u2014 Messages 1360 and 1698. The user has said more than once that code must not read like prose: a variable, attribute, property or function is named for what it holds or does (text, command, labels, lines), never with a verb from a story. 'says' on the Design type (1360) and 'said = call.said.lower()' in features/recital.py (1698) are the examples. Rule 27 states the naming rule; this one carries the words, so writing one of them whispers it. Before writing a name, ask whether a reader who has never seen the code would know what it holds.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 19 stands still while todo 13 is ready \u2014 if work 19 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 13. Stop only when nothing ready is left.; Code Commandments \u2014 before you wrap up \u2014 you've changed 4 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 19 is still open, with nothing logged \u2014 journal work log 19 \"\" \u2014 then journal work end 19 --how \"\", or journal work park 19 \"\"", "meta": {"from": "journal"}} {"content": "work 19 is still open \u2014 end it or park it before you stop: journal work end 19 --how \"\", or journal work park 19 \"\"", "meta": {"from": "journal"}} {"content": "work 19 is still open \u2014 end it or park it before you stop: journal work end 19 --how \"\", or journal work park 19 \"\"", "meta": {"from": "journal"}} {"content": "your command ran 30s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "the end tag does this in one step \u2014 [!end:N] makes the turn itself what landed; it runs only when it opens the last text of your turn", "meta": {"from": "journal"}} {"content": "rule 61 \u2014 Features wait as pull requests until approved; only hotfixes merge\u2026 \u2014 Message 17118 (2026-10-06), after the overnight refactor merged as 2.252.0: start new work in a new branch, do not merge, write the pull request. Every pull request or new feature is parked until the user approves it. Hotfixes can be merged into main immediately (by a dispatched agent in a worktree of main, rule 60).", "meta": {"from": "journal"}} {"content": "fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply \"\" instead of the tag.; rule 67 \u2014 Never answer a journal line in the chat; act on it silently \u2014 The user, messages 19360 and 19365: the agent kept writing chat lines in reply to the journal's own reminders (old helper reports, notices), filling the user's chat with noise. A journal line is an instruction to the agent, not a message: act on it and write nothing, unless the user needs to know something (a failure, a finished piece of work, a decision that waits on them). The journal itself should enforce it, not a local reminder.", "meta": {"from": "journal"}} {"content": "law L6 \u2014 A journal line is an instruction, never a message - act on it and\u2026 \u2014 A line that starts with [journal], a reminder, a notice or an old helper report is the journal telling the agent what to do, not the user speaking. Answering it fills the user's chat with noise. Act on it, or note it and carry on; write in the chat only what the user needs to know, such as a failure, a finished piece of work or a decision that waits on them.; rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.; rule 66 \u2014 The journal never slows the agent down \u2014 The user, message 18990, after hooks timed out and waited on locks under load: the journal must never, ever decrease the performance of an agent. A hook answers at once with what decides the tool call; everything else runs after, in the background, and reaches the agent as a message. No hook waits on a lock it does not need.", "meta": {"from": "journal"}} {"content": "rule 64 \u2014 A finished feature is merged into main without waiting for approval \u2014 The user, message 17815 (2026-10-07): 'make sure that no pull requests are lingering on the repository. You may merge them into main... You are allowed to merge everything into main once the feature is completed.' This replaces rule 61's wait for approval: a feature still goes on its own branch, and once it is complete, tested and its whole suite passes, it is merged into main and released, and no pull request is left open.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 2 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "law L3 \u2014 Read narrowly - grep for the line, sed a range, head the file; never\u2026 \u2014 Everything a tool returns stays in the context for good and is paid for on every turn after it. Search before you read, read the range you need, and cap output with grep, head or tail. Read a whole file only when you need all of it.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 18, 20", "meta": {"from": "journal"}} {"content": "the chat scenarios came back - cd\u2026", "meta": {"from": "journal"}} {"content": "rule 49 \u2014 A dialog whose content grows keeps one fixed height, and its content\u2026 \u2014 Message 5361, after asking more than once: a dialog that shows output as it arrives (install, update, logs) opens at its final height and never jumps; only its content scrolls.; rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.; rule 57 \u2014 Never merge the overnight refactor into main before its pull request\u2026 \u2014 Messages 15005, 15006, 15109, 15110 (2026-10-04): all refactor work goes on branch overnight-refactor and reaches the user as one pull request, which they read in the morning; nothing of it is merged into main until they say so. Hotfixes the user explicitly asks for go to main at once and are merged into the branch.", "meta": {"from": "journal"}} {"content": "rule 40 \u2014 A feature is named for what it is, never for its machinery \u2014 Messages 599, 600 and 703. A feature is a capability the user would name and would think of switching off. File tracking, a write gate, a phrase bank, a tree diff are services used inside a feature, not features of their own: they live in the feature they serve. Before adding a directory under features/, say what the user would call it; if the answer names a mechanism, it belongs inside something else. Report 16 holds the grouping this implies.", "meta": {"from": "journal"}} {"content": "rule 42 \u2014 Every user-facing text passes the formatters before it leaves the\u2026 \u2014 Not only a brief. A title, an abstract, an outcome and every section body are read by a person, so each goes through the same formatters on its way to the viewer \u2014 chat turns, activity items, to-do rows, inspector pages, docs alike. One field formatted out of five is not a rule, it is an accident, and it is how a raw tag ended up in the activity list after the tags feature had been stripping them for weeks. When a new field carries words a person reads, it joins the list in the same place.", "meta": {"from": "journal"}} {"content": "fact 34 \u2014 A hooks list in a checkout's .claude/settings.json stops every\u2026 \u2014 Seen 2026-10-08: since commit 707a82915 the committed .claude/settings.json held {\"hooks\": []}; current Claude Code answers a hooks value that is not an object with a SettingsWarning dialog, which a headless helper cannot answer, so helpers 183 and 184 exited before doing anything (their launch logs in .journal/runtime/launches/ show it). This repository's journal hooks live in settings.local.json; the committed settings.json stays {}.", "meta": {"from": "journal"}} {"content": "rule 54 \u2014 Settings and feature switches are read at boot and on change, never\u2026 \u2014 The user, message 13349: the application boots, determines every feature and setting once, and re-evaluates only when something changes, such as a setting or a plugin. Never lazy-load settings.", "meta": {"from": "journal"}} {"content": "your command ran 33s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "rule 48 \u2014 The viewer is built from its component library, and pages only\u2026 \u2014 Message 4258. Every visual piece the viewer shows more than once, or that a user would recognise as the same kind of thing (a dialog, a side panel or inspector, a dropdown, a list row, a switch, a button), is one component in web/src/kit, extracted aggressively, and every page composes those components instead of building its own copy. Before writing markup or styles in a page, look for the kit component that already does it and extend it with a prop; a second hand-built version is a bug. The side panel that animated in but not out, while a separate skill panel did both, is the example.", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal . A helper added to the base class therefore becomes a command on every type \u2014 which is how journal handled and journal refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.; rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.; rule 65 \u2014 Run only new and affected tests while working; the whole suite only\u2026 \u2014 The user, messages 17914 to 17917 (2026-10-07): 'stop running the whole test suite and wasting my time... please only run the new or affected tests, and then, whenever you are merging to main or publishing to main, you can run the full test suite.' Replaces rule 41's whole suite before every commit: on a feature branch, run the tests beside what changed (journal check touched, or the feature's test.py and the browser scenarios it touches); the whole suite runs once, before a merge into main and its release.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 4 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.", "meta": {"from": "journal"}} {"content": "fact 23 \u2014 Every upgrade brings system sequences and their triggers in line\u2026 \u2014 install.py runs ship_sequences after the migrations on each upgrade, so features/sequences/shipped.py is the whole source: change its wording and the next upgrade updates every journal, no migration needed. Shipped rows carry system=True and are read-only for everyone but SYSTEM (controllers/base.py _shipped).; rule 27 \u2014 Name a declaration with the word a reader already knows \u2014 An attribute, a variable or a field gets the ordinary programming word for what it holds, not an evocative one. was, heard and alone were poetry; aliases, notify_actions and urgent_actions are what they are. The test: could a reader who has never seen this codebase guess what it holds from the name alone? Prose belongs in the help text and the abstract, where it is read as prose. This does not license abbreviations \u2014 a plain word in full, not a short one.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done --how, or by a commit whose message carries Journal: todos done at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 23 stands still while todo 14 is ready \u2014 if work 23 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 14. Stop only when nothing ready is left.; work 23 is still open, with nothing logged \u2014 journal work log 23 \"\" \u2014 then journal work end 23 --how \"\", or journal work park 23 \"\"", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 4 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "law L5 \u2014 Every subagent dispatch names the agent, in the naming style of the\u2026 \u2014 A name is how the user and the chat tell subagents apart and how they are messaged later; an id or a task line is not a name. Start the dispatch's description with the name, a colon, then the task. The profile in use says how its agents are named.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 the files changed since the last check (`attachments.py`, `\u2026 \u2014 Code Commandments \u2014 the files changed since the last check (`attachments.py`, `commands.py`) breaks a rule. Fix it now, at its SOURCE, while the code is still in front of you: \u00b7 \u2022 python-blank-string-default at /Users/jessegall/projects/agent-journal/.claude/worktrees/quiet-restart/src/features/open_viewer/attachments.py:63 \u00b7 LOAD the skill `commandments-python-absence` before fixing \u2014 load it even if you believe you already have. \u00b7 Run `commandments info ` if a rule is not one you recognise. This check reads a file at a time, so it is not the whole picture \u2014 `judge` still is.", "meta": {"from": "journal"}} {"content": "rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.", "meta": {"from": "journal"}} {"content": "fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply \"\" instead of the tag.; rule 47 \u2014 The journal sets itself up once, when the server starts, never per\u2026 \u2014 Messages 2220 and 2224. Discovering features and their handlers, seating the feature rows and the rename sweep happen once, at server boot, and again only when a feature is switched on or off, a plugin changes or an environment is added: features.load keeps a set-up generation per journal (SEATED) and redoes the work only when that generation moves. A command, a request or a hook uses what is already there; nothing in their path may rediscover handlers or rescan folders. A cost that repeats per call is a bug to fix, not a budget to raise.", "meta": {"from": "journal"}} {"content": "rule 66 \u2014 The journal never slows the agent down \u2014 The user, message 18990, after hooks timed out and waited on locks under load: the journal must never, ever decrease the performance of an agent. A hook answers at once with what decides the tool call; everything else runs after, in the background, and reaches the agent as a message. No hook waits on a lock it does not need.", "meta": {"from": "journal"}} {"content": "rule 61 \u2014 Features wait as pull requests until approved; only hotfixes merge\u2026 \u2014 Message 17118 (2026-10-06), after the overnight refactor merged as 2.252.0: start new work in a new branch, do not merge, write the pull request. Every pull request or new feature is parked until the user approves it. Hotfixes can be merged into main immediately (by a dispatched agent in a worktree of main, rule 60).; rule 64 \u2014 A finished feature is merged into main without waiting for approval \u2014 The user, message 17815 (2026-10-07): 'make sure that no pull requests are lingering on the repository. You may merge them into main... You are allowed to merge everything into main once the feature is completed.' This replaces rule 61's wait for approval: a feature still goes on its own branch, and once it is complete, tested and its whole suite passes, it is merged into main and released, and no pull request is left open.", "meta": {"from": "journal"}} {"content": "law L3 \u2014 Read narrowly - grep for the line, sed a range, head the file; never\u2026 \u2014 Everything a tool returns stays in the context for good and is paid for on every turn after it. Search before you read, read the range you need, and cap output with grep, head or tail. Read a whole file only when you need all of it.", "meta": {"from": "journal"}} {"content": "work 24 in hand \u2014 Files page loads each tab on demand with skeletons \u2014 if this is not what you are doing, end it or park it and start the work you are in; rule 51 \u2014 Every finished feature is committed, pushed and released with a new\u2026 \u2014 Message 9207 (2026-09-24): when a new feature is ready, commit, push and publish a new tag. This is the user's standing word for releasing, so rule 44's only-when-the-user-says is met by it for finished features; fixes in between wait for the next feature or a patch the user asks for.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 8 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 8 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 24 is still open, with nothing logged \u2014 journal work log 24 \"\" \u2014 then journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "your command ran 32s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself; 13 facts standing, read them \u2014 9. Every public method on a controller becomes a journal command; 13. This live session runs the installed copy in .journal/journal.pyz; 18. cProfile inflates the slow-request profiles about tenfold; 20. A slim supervisor holds the agent and a worker reloads on every build; 23. Every upgrade brings system sequences and their triggers in line with the code; 24. An answer followed by tool calls can be missing from Claude's transcript; 25. A designer's install packs the whole tree, half-done server edits included; 26. Claude Code reads agent profiles when a session starts; 27. Running src/journal.py against the live .journal root starts a second server; 28. The designer agent type exists, so design work goes to a subagent; 29. Codex's transcript records the end of every exec session, polled or not; 30. The tunler server refuses TLS for any subdomain without a tunnel; 34. A hooks list in a checkout's .claude/settings.json stops every helper at start; context 50% full, decide \u2014 a fact is what a later reader would get wrong without, a rule binds every environment, or nothing \"\"; 43 rules in force, read them \u2014 7. journal disable must only ever be run because the user explicitly asked for it,; 9. Research dispatched to a subagent ends in a REPORT for the user, compiled by the; 13. A title names the thing in at most 80 characters and never explains it with a co; 14. A small journal capability is a feature under features, with at most one test; 17. Do not restart the viewer for frontend-only changes; 18. Provider-specific code belongs in providers, never features; 19. Providers report facts; features decide behavior; 22. File distinct user work requests immediately; 27. Name a declaration with the word a reader already knows; 30. The viewer has one API client, and every piece of it does one job; 31. Every finding a reviewing agent reports becomes its own to-do; 35. Write clean code - one funnel per kind of operation, never the same method twice; 36. Clean, DRY, idiomatic before it is committed, never after it is complained about; 37. Close every to-do explicitly with todo done or a Journal commit trailer; 38. Never change the git branch until the user says so, by name; 39. Use only registered exclamation response tags; 40. A feature is named for what it is, never for its machinery; 41. Keep moving, run the whole suite before every commit, never wait; 42. Every user-facing text passes the formatters before it leaves the server; 43. A request or hook over its budget is fixed before the next release; 45. No prose words as names in code - said, says, heard, spoke, told, shown, became; 46. Only commit and push once the whole journal is proven to boot; 47. The journal sets itself up once, when the server starts, never per command; 48. The viewer is built from its component library, and pages only compose it; 49. A dialog whose content grows keeps one fixed height, and its content scrolls; 50. Everything the user does is doable in the viewer; 51. Every finished feature is committed, pushed and released with a new version tag; 52. A chat mark for something the user did sits on the user's side; 54. Settings and feature switches are read at boot and on change, never per call; 55. Always dispatch Codex helpers on gpt-6-sol; 56. Helpers are for work that writes; subagents read, research and design; 57. Never merge the overnight refactor into main before its pull request is approved; 58. A design runs three critique rounds, then is built on a branch; 59. Every viewer heading and label says plainly what it is about; 60. A hotfix is done by a dispatched agent in a worktree of main; 61. Features wait as pull requests until approved; only hotfixes merge at once; 62. The voice profile shapes only the agent's chat speech, never code or text; 63. A small design is drawn once and the user approves it, with no critique rounds; 64. A finished feature is merged into main without waiting for approval; 65. Run only new and affected tests while working; the whole suite only before main; 66. The journal never slows the agent down; 67. Never answer a journal line in the chat; act on it silently; 68. The orchestrator approves the designer's designs itself", "meta": {"from": "journal"}} {"content": "rule 57 \u2014 Never merge the overnight refactor into main before its pull request\u2026 \u2014 Messages 15005, 15006, 15109, 15110 (2026-10-04): all refactor work goes on branch overnight-refactor and reaches the user as one pull request, which they read in the morning; nothing of it is merged into main until they say so. Hotfixes the user explicitly asks for go to main at once and are merged into the branch.", "meta": {"from": "journal"}} {"content": "rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.", "meta": {"from": "journal"}} {"content": "work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "your command ran 31s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "fact 13 \u2014 This live session runs the installed copy in .journal/journal.pyz \u2014 The running journal (server, hooks, CLI) runs from .journal/journal.pyz with its viewer and skills in .journal/src, never from the repo. A change in the repo reaches it only through python3 src/journal.py --root .journal upgrade, which packs the zip again. A commit alone changes nothing that is running.; work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "you ran the same check 3 times in a row - until grep -q \"exited with code\"\u2026 \u2014 if you are waiting for something to change, say journal work await \"\" and end your turn: you are asked to look again every five minutes, and a background command tells you itself when it ends. Keep checking only if each look moves the work on.; work 24 is still open \u2014 end it or park it before you stop: journal work end 24 --how \"\", or journal work park 24 \"\"", "meta": {"from": "journal"}} {"content": "your command ran 33s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "the browser scenarios on the rebuilt viewer came back\u2026", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 24", "meta": {"from": "journal"}} {"content": "the integrations scenario alone came back - cd\u2026", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal . A helper added to the base class therefore becomes a command on every type \u2014 which is how journal handled and journal refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.; rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.", "meta": {"from": "journal"}} {"content": "rule 65 \u2014 Run only new and affected tests while working; the whole suite only\u2026 \u2014 The user, messages 17914 to 17917 (2026-10-07): 'stop running the whole test suite and wasting my time... please only run the new or affected tests, and then, whenever you are merging to main or publishing to main, you can run the full test suite.' Replaces rule 41's whole suite before every commit: on a feature branch, run the tests beside what changed (journal check touched, or the feature's test.py and the browser scenarios it touches); the whole suite runs once, before a merge into main and its release.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 2 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 25 is still open, with nothing logged \u2014 journal work log 25 \"\" \u2014 then journal work end 25 --how \"\", or journal work park 25 \"\"", "meta": {"from": "journal"}} {"content": "work 25 is still open \u2014 end it or park it before you stop: journal work end 25 --how \"\", or journal work park 25 \"\"", "meta": {"from": "journal"}} {"content": "rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done --how, or by a commit whose message carries Journal: todos done at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.", "meta": {"from": "journal"}} {"content": "rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.", "meta": {"from": "journal"}} {"content": "fact 20 \u2014 A slim supervisor holds the agent and a worker reloads on every build \u2014 Since 2.118.0 (2026-09-23). src/supervisor.py is standard library only and never reloads: journal claude hands its process over to it (os.execv), and it owns the pty and the agent process, relays the terminal, writes the printed and screen captures, listens on the typist socket, restarts the agent in the same session from a relaunch command written to its runtime folder while a restart is pending, and stops it with escalation while draining the pty (an agent cannot finish exiting on macOS while its output is unread). It starts the worker (src/worker.py, which runs runner/worker.py; engine/worker.py stays as an alias for supervisors started before 2.201) and starts it again whenever it exits: RELOAD on a new build, RELAUNCH to restart the agent, STOP to end, HEAL or a quick crash to roll back a build through journal heal. The worker holds everything else: seating the session, the start-up confirm typed through the typist, services, viewer, update check, check-in, and the one-time relaunch of sessions launched before agents/terminal.py LAUNCH. agents/terminal.py holds only journal-side helpers. The server (serve.py) still runs the engines and re-execs itself on a .py change. When the agent exits, the supervisor runs journal ended, which puts set-aside hooks back and stops the server when no session is left.; fact 25 \u2014 A designer's install packs the whole tree, half-done server edits\u2026 \u2014 2026-09-25: Eames and Saul run python3 src/journal.py --root .journal upgrade after their viewer builds; it packs every file in src, so a server handler I was halfway through writing went live and raised on every PostToolUse hook. While designers work in parallel, keep server edits whole between tool calls (write and test in the scratchpad first), and reinstall after reverting anything.; rule 40 \u2014 A feature is named for what it is, never for its machinery \u2014 Messages 599, 600 and 703. A feature is a capability the user would name and would think of switching off. File tracking, a write gate, a phrase bank, a tree diff are services used inside a feature, not features of their own: they live in the feature they serve. Before adding a directory under features/, say what the user would call it; if the answer names a mechanism, it belongs inside something else. Report 16 holds the grouping this implies.; rule 54 \u2014 Settings and feature switches are read at boot and on change, never\u2026 \u2014 The user, message 13349: the application boots, determines every feature and setting once, and re-evaluates only when something changes, such as a setting or a plugin. Never lazy-load settings.", "meta": {"from": "journal"}} {"content": "todo 14 next", "meta": {"from": "journal"}} {"content": "origin/main moved since your worktree was cut \u2014 It gained 7 commits (bc3ee2f1c The server renews the row stamps it keeps before they expire, so no request re-reads every row file of every type when they would have; 3f53b6b10 journal secret run works again: the command line's own command has a name no command parameter can take; e6df6e758 A restart the journal began is quiet however long it takes: the marker stays until the new server is answering and is then taken away, as the test for a long restart holds; c0ec4f56c Version 2.267.11; ed84f00f9 The installer gets the restart marker's path through the package it already loads; and 2 more). Rebase onto origin/main in /Users/jessegall/projects/agent-journal/.claude/worktrees/quiet-restart before you report.", "meta": {"from": "journal"}} {"content": "rule 67 \u2014 Never answer a journal line in the chat; act on it silently \u2014 The user, messages 19360 and 19365: the agent kept writing chat lines in reply to the journal's own reminders (old helper reports, notices), filling the user's chat with noise. A journal line is an instruction to the agent, not a message: act on it and write nothing, unless the user needs to know something (a failure, a finished piece of work, a decision that waits on them). The journal itself should enforce it, not a local reminder.", "meta": {"from": "journal"}} {"content": "the end tag does this in one step \u2014 [!end:N] makes the turn itself what landed; it runs only when it opens the last text of your turn", "meta": {"from": "journal"}} {"content": "work deferred in words, not parked \u2014 \"once the build is\" is the title of a to-do: journal todo create \"\" --brief, then say so", "meta": {"from": "journal"}} {"content": "rule 43 \u2014 A request or hook over its budget is fixed before the next release \u2014 Comment 1151 on this rule. When the faults feature reports a request, a hook or a command slower than its budget, file it as a to-do at once. It does not jump ahead of the work in hand, but no version is published while one is still open: profile it, fix it, and verify the new time before the release goes out. The budget is 50ms, because everything runs locally against files.", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 26, 27", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 26, 27", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 26, 27", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 26, 27", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "your command ran 34s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "your command ran 34s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "your command ran 31s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "dashboard profile after idle came back - until grep -q \"exited with code\"\u2026", "meta": {"from": "journal"}} {"content": "work 27 is still open \u2014 end it or park it before you stop: journal work end 27 --how \"<what landed>\", or journal work park 27 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "your command ran 34s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "the renewal harness result came back - until grep -q \"and again\"\u2026", "meta": {"from": "journal"}} {"content": "rule 57 \u2014 Never merge the overnight refactor into main before its pull request\u2026 \u2014 Messages 15005, 15006, 15109, 15110 (2026-10-04): all refactor work goes on branch overnight-refactor and reaches the user as one pull request, which they read in the morning; nothing of it is merged into main until they say so. Hotfixes the user explicitly asks for go to main at once and are merged into the branch.", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "your command ran 34s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 2 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "your command ran 31s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "fact 34 \u2014 A hooks list in a checkout's .claude/settings.json stops every\u2026 \u2014 Seen 2026-10-08: since commit 707a82915 the committed .claude/settings.json held {\"hooks\": []}; current Claude Code answers a hooks value that is not an object with a SettingsWarning dialog, which a headless helper cannot answer, so helpers 183 and 184 exited before doing anything (their launch logs in .journal/runtime/launches/ show it). This repository's journal hooks live in settings.local.json; the committed settings.json stays {}.; rule 50 \u2014 Everything the user does is doable in the viewer \u2014 Message 6710 (2026-09-23): the user never uses the CLI, only the UI; everything should be doable from the viewer. The journal commands are for agents; any action meant for the user (making boards, confirming, accepting, hosting, watching an agent) needs its place in the viewer.; rule 51 \u2014 Every finished feature is committed, pushed and released with a new\u2026 \u2014 Message 9207 (2026-09-24): when a new feature is ready, commit, push and publish a new tag. This is the user's standing word for releasing, so rule 44's only-when-the-user-says is met by it for finished features; fixes in between wait for the next feature or a patch the user asks for.; rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"To-dos 3661, 3662 and 3669\u2026 \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead; todo 26 next", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "rule 39 \u2014 Use only registered exclamation response tags \u2014 A tag like [!reply:12] runs a command, and only the tags in the tags.runs setting are registered. An invented tag does nothing and shows as raw text in the chat. Use the registered ones (reply, log, end, todo, fact, rule) and nothing else.", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "you ran the same check 3 times in a row - git fetch -q origin --tags 2>&1|tail\u2026 \u2014 if you are waiting for something to change, say journal work await \"<what you wait for>\" and end your turn: you are asked to look again every five minutes, and a background command tells you itself when it ends. Keep checking only if each look moves the work on.", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat; check 2.267.13 on origin/main; then the next round, to-dos 3659, 3660, 3677\u2026 \u2014 look at the thing itself: the background shell's output, the process, the run's status. If it is still going, say journal work await \"<what you wait for>\" again and wait. If it finished or failed, journal work log what came of it and take the next step. Never wait for something you can do without.", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal <noun> <method>. A helper added to the base class therefore becomes a command on every type \u2014 which is how journal <type> handled and journal <type> refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.; rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done <n> --how, or by a commit whose message carries Journal: todos done <n> at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.; rule 38 \u2014 Never change the git branch until the user says so, by name \u2014 The work happens on the branch the user named. That was main until message 5929 and question 80 (2026-09-23), which moved the sins work to the branch sins. Do not create, switch to or merge any other branch unless the user names it in their own words.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.", "meta": {"from": "journal"}} {"content": "fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply <n> \"<text>\" instead of the tag.", "meta": {"from": "journal"}} {"content": "rule 27 \u2014 Name a declaration with the word a reader already knows \u2014 An attribute, a variable or a field gets the ordinary programming word for what it holds, not an evocative one. was, heard and alone were poetry; aliases, notify_actions and urgent_actions are what they are. The test: could a reader who has never seen this codebase guess what it holds from the name alone? Prose belongs in the help text and the abstract, where it is read as prose. This does not license abbreviations \u2014 a plain word in full, not a short one.", "meta": {"from": "journal"}} {"content": "rule 42 \u2014 Every user-facing text passes the formatters before it leaves the\u2026 \u2014 Not only a brief. A title, an abstract, an outcome and every section body are read by a person, so each goes through the same formatters on its way to the viewer \u2014 chat turns, activity items, to-do rows, inspector pages, docs alike. One field formatted out of five is not a rule, it is an accident, and it is how a raw tag ended up in the activity list after the tags feature had been stripping them for weeks. When a new field carries words a person reads, it joins the list in the same place.", "meta": {"from": "journal"}} {"content": "fact 20 \u2014 A slim supervisor holds the agent and a worker reloads on every build \u2014 Since 2.118.0 (2026-09-23). src/supervisor.py is standard library only and never reloads: journal claude hands its process over to it (os.execv), and it owns the pty and the agent process, relays the terminal, writes the printed and screen captures, listens on the typist socket, restarts the agent in the same session from a relaunch command written to its runtime folder while a restart is pending, and stops it with escalation while draining the pty (an agent cannot finish exiting on macOS while its output is unread). It starts the worker (src/worker.py, which runs runner/worker.py; engine/worker.py stays as an alias for supervisors started before 2.201) and starts it again whenever it exits: RELOAD on a new build, RELAUNCH to restart the agent, STOP to end, HEAL or a quick crash to roll back a build through journal heal. The worker holds everything else: seating the session, the start-up confirm typed through the typist, services, viewer, update check, check-in, and the one-time relaunch of sessions launched before agents/terminal.py LAUNCH. agents/terminal.py holds only journal-side helpers. The server (serve.py) still runs the engines and re-execs itself on a .py change. When the agent exits, the supervisor runs journal ended, which puts set-aside hooks back and stops the server when no session is left.; rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.", "meta": {"from": "journal"}} {"content": "rule 67 \u2014 Never answer a journal line in the chat; act on it silently \u2014 The user, messages 19360 and 19365: the agent kept writing chat lines in reply to the journal's own reminders (old helper reports, notices), filling the user's chat with noise. A journal line is an instruction to the agent, not a message: act on it and write nothing, unless the user needs to know something (a failure, a finished piece of work, a decision that waits on them). The journal itself should enforce it, not a local reminder.", "meta": {"from": "journal"}} {"content": "rule 60 \u2014 A hotfix is done by a dispatched agent in a worktree of main \u2014 Message 16836 (2026-10-06): the orchestrator cut a worktree under .claude/worktrees for a Codex hotfix, its session moved to a new environment and the user's messages stopped reaching it. The user: when working on a branch and a hotfix comes in, create a worktree of main and dispatch an agent to do that work. The orchestrator stays on its branch and in its environment, and never cds into another checkout.", "meta": {"from": "journal"}} {"content": "rule 65 \u2014 Run only new and affected tests while working; the whole suite only\u2026 \u2014 The user, messages 17914 to 17917 (2026-10-07): 'stop running the whole test suite and wasting my time... please only run the new or affected tests, and then, whenever you are merging to main or publishing to main, you can run the full test suite.' Replaces rule 41's whole suite before every commit: on a feature branch, run the tests beside what changed (journal check touched, or the feature's test.py and the browser scenarios it touches); the whole suite runs once, before a merge into main and its release.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 32 stands still while todo 26 is ready \u2014 if work 32 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 26. Stop only when nothing ready is left.; Code Commandments \u2014 before you wrap up \u2014 you've changed 4 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; fact 13 \u2014 This live session runs the installed copy in .journal/journal.pyz \u2014 The running journal (server, hooks, CLI) runs from .journal/journal.pyz with its viewer and skills in .journal/src, never from the repo. A change in the repo reaches it only through python3 src/journal.py --root .journal upgrade, which packs the zip again. A commit alone changes nothing that is running.; law L3 \u2014 Read narrowly - grep for the line, sed a range, head the file; never\u2026 \u2014 Everything a tool returns stays in the context for good and is paid for on every turn after it. Search before you read, read the range you need, and cap output with grep, head or tail. Read a whole file only when you need all of it.; work 32 is still open, with nothing logged \u2014 journal work log 32 \"<what was decided or done, and why>\" \u2014 then journal work end 32 --how \"<what landed>\", or journal work park 32 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "work 32 is still open \u2014 end it or park it before you stop: journal work end 32 --how \"<what landed>\", or journal work park 32 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 26, 27, 28, 29", "meta": {"from": "journal"}} {"content": "messages and acknowledgements tests came back - cd\u2026", "meta": {"from": "journal"}} {"content": "rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.; rule 61 \u2014 Features wait as pull requests until approved; only hotfixes merge\u2026 \u2014 Message 17118 (2026-10-06), after the overnight refactor merged as 2.252.0: start new work in a new branch, do not merge, write the pull request. Every pull request or new feature is parked until the user approves it. Hotfixes can be merged into main immediately (by a dispatched agent in a worktree of main, rule 60).; rule 64 \u2014 A finished feature is merged into main without waiting for approval \u2014 The user, message 17815 (2026-10-07): 'make sure that no pull requests are lingering on the repository. You may merge them into main... You are allowed to merge everything into main once the feature is completed.' This replaces rule 61's wait for approval: a feature still goes on its own branch, and once it is complete, tested and its whole suite passes, it is merged into main and released, and no pull request is left open.", "meta": {"from": "journal"}} {"content": "rule 48 \u2014 The viewer is built from its component library, and pages only\u2026 \u2014 Message 4258. Every visual piece the viewer shows more than once, or that a user would recognise as the same kind of thing (a dialog, a side panel or inspector, a dropdown, a list row, a switch, a button), is one component in web/src/kit, extracted aggressively, and every page composes those components instead of building its own copy. Before writing markup or styles in a page, look for the kit component that already does it and extend it with a prop; a second hand-built version is a bug. The side panel that animated in but not out, while a separate skill panel did both, is the example.; rule 66 \u2014 The journal never slows the agent down \u2014 The user, message 18990, after hooks timed out and waited on locks under load: the journal must never, ever decrease the performance of an agent. A hook answers at once with what decides the tool call; everything else runs after, in the background, and reaches the agent as a message. No hook waits on a lock it does not need.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "waiting: 3 unread todos 26, 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 3 unread todos 26, 28, 29", "meta": {"from": "journal"}} {"content": "the peers scenario came back - cat > peers.mjs <<'E'", "meta": {"from": "journal"}} {"content": "rule 49 \u2014 A dialog whose content grows keeps one fixed height, and its content\u2026 \u2014 Message 5361, after asking more than once: a dialog that shows output as it arrives (install, update, logs) opens at its final height and never jumps; only its content scrolls.", "meta": {"from": "journal"}} {"content": "rule 45 \u2014 No prose words as names in code - said, says, heard, spoke, told\u2026 \u2014 Messages 1360 and 1698. The user has said more than once that code must not read like prose: a variable, attribute, property or function is named for what it holds or does (text, command, labels, lines), never with a verb from a story. 'says' on the Design type (1360) and 'said = call.said.lower()' in features/recital.py (1698) are the examples. Rule 27 states the naming rule; this one carries the words, so writing one of them whispers it. Before writing a name, ask whether a reader who has never seen the code would know what it holds.; rule 59 \u2014 Every viewer heading and label says plainly what it is about \u2014 The user, messages 16499, 16839, 16844, 16989, 16992 and 16993 (2026-10-06), after 'Where the words count', 'Watch for the words in', 'This project', 'This browser' and 'Stop the journal' as tab names: viewer text reads like Linear, GitHub or Vercel. A place (page, tab, group, sidebar item) is a short noun: Settings, Project, Browser, Services, Updates, Plugins; never 'This project' or a phrase. A button is a verb for what happens: Stop, Install, Copy link, Pause the plan. A heading names what the reader looks at, and its options finish its sentence: 'Trigger when' / 'A word is written'. Plain literal words: no metaphor or whimsy ('kettle on, waiting'), no app speaking as I, none of the journal's internal words (row, hook, nudge, engine, slate). One word for one thing everywhere, sentence case, as short as it can be while clear. Applies to designers' prototypes, helpers' builds, the viewer's JavaScript lists, feature details, and shipped sequence and trigger titles alike.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 34 stands still while todo 28 is ready \u2014 if work 34 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 28. Stop only when nothing ready is left.; Code Commandments \u2014 before you wrap up \u2014 you've changed 2 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 34 is still open, with nothing logged \u2014 journal work log 34 \"<what was decided or done, and why>\" \u2014 then journal work end 34 --how \"<what landed>\", or journal work park 34 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "work 34 is still open \u2014 end it or park it before you stop: journal work end 34 --how \"<what landed>\", or journal work park 34 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 28, 29", "meta": {"from": "journal"}} {"content": "the agent_sessions test came back - cd\u2026", "meta": {"from": "journal"}} {"content": "work 34 is still open \u2014 end it or park it before you stop: journal work end 34 --how \"<what landed>\", or journal work park 34 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 28, 29", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 28, 29", "meta": {"from": "journal"}} {"content": "the agent_sessions test, second run came back - python3 - <<'E'", "meta": {"from": "journal"}} {"content": "rule 47 \u2014 The journal sets itself up once, when the server starts, never per\u2026 \u2014 Messages 2220 and 2224. Discovering features and their handlers, seating the feature rows and the rename sweep happen once, at server boot, and again only when a feature is switched on or off, a plugin changes or an environment is added: features.load keeps a set-up generation per journal (SEATED) and redoes the work only when that generation moves. A command, a request or a hook uses what is already there; nothing in their path may rediscover handlers or rescan folders. A cost that repeats per call is a bug to fix, not a budget to raise.", "meta": {"from": "journal"}} {"content": "the await tag does this in one step \u2014 [!await] makes the rest of the turn what you wait for; [!await on=(\"<id>\", \"helper:<n>\")] waits on those; it runs only when it opens the last text of your turn", "meta": {"from": "journal"}} {"content": "the migration on the copy of the real record came back - cd\u2026", "meta": {"from": "journal"}} {"content": "todo 29 next; work 34 is still open \u2014 end it or park it before you stop: journal work end 34 --how \"<what landed>\", or journal work park 34 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "fact 25 \u2014 A designer's install packs the whole tree, half-done server edits\u2026 \u2014 2026-09-25: Eames and Saul run python3 src/journal.py --root .journal upgrade after their viewer builds; it packs every file in src, so a server handler I was halfway through writing went live and raised on every PostToolUse hook. While designers work in parallel, keep server edits whole between tool calls (write and test in the scratchpad first), and reinstall after reverting anything.; fact 34 \u2014 A hooks list in a checkout's .claude/settings.json stops every\u2026 \u2014 Seen 2026-10-08: since commit 707a82915 the committed .claude/settings.json held {\"hooks\": []}; current Claude Code answers a hooks value that is not an object with a SettingsWarning dialog, which a headless helper cannot answer, so helpers 183 and 184 exited before doing anything (their launch logs in .journal/runtime/launches/ show it). This repository's journal hooks live in settings.local.json; the committed settings.json stays {}.; rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 `briefing.py`, changed since the last check, breaks a rule.\u2026 \u2014 Code Commandments \u2014 `briefing.py`, changed since the last check, breaks a rule. Fix it now, at its SOURCE, while the code is still in front of you: \u00b7 \u2022 python-nested-conditional at /Users/jessegall/projects/agent-journal/.claude/worktrees/quiet-restart/src/features/journal_laws/briefing.py:88 \u00b7 LOAD the skill `commandments-python-flow` before fixing \u2014 load it even if you believe you already have. \u00b7 Run `commandments info <sin>` if a rule is not one you recognise. This check reads a file at a time, so it is not the whole picture \u2014 `judge` still is.", "meta": {"from": "journal"}} {"content": "rule 40 \u2014 A feature is named for what it is, never for its machinery \u2014 Messages 599, 600 and 703. A feature is a capability the user would name and would think of switching off. File tracking, a write gate, a phrase bank, a tree diff are services used inside a feature, not features of their own: they live in the feature they serve. Before adding a directory under features/, say what the user would call it; if the answer names a mechanism, it belongs inside something else. Report 16 holds the grouping this implies.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 35 stands still while todo 29 is ready \u2014 if work 35 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 29. Stop only when nothing ready is left.; work 35 is still open, with nothing logged \u2014 journal work log 35 \"<what was decided or done, and why>\" \u2014 then journal work end 35 --how \"<what landed>\", or journal work park 35 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 4 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 29", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 29", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "rules, auto_update and session_briefing tests came back\u2026", "meta": {"from": "journal"}} {"content": "your command ran 34s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "law L5 \u2014 Every subagent dispatch names the agent, in the naming style of the\u2026 \u2014 A name is how the user and the chat tell subagents apart and how they are messaged later; an id or a task line is not a name. Start the dispatch's description with the name, a colon, then the task. The profile in use says how its agents are named.", "meta": {"from": "journal"}} {"content": "law L1 \u2014 Every subagent dispatch names its model and chooses the least\u2026 \u2014 Use a fast, economical model for mechanical work with a known answer, a capable general model for careful implementation, and the strongest model only when the task turns on difficult judgement. Inheriting the orchestrator's model is not a model choice. If the dispatch API cannot accept a model, that operation is exempt.; law L2 \u2014 Every subagent is bound to a concrete job; never dispatch a generic\u2026 \u2014 Use the most specific available agent type whose declared purpose matches the assignment. On providers without agent types, give the dispatch a concrete task name and bounded prompt. If no suitable specialization exists, keep the work in the main agent instead of manufacturing an unscoped helper.; law L4 \u2014 Related work goes back to the helper or subagent that already worked\u2026 \u2014 A helper or subagent that drew a design, wrote the code or ran the research keeps what it learned. When new work changes its work, is related to it or touches the same code, send it there with a message (SendMessage, journal helper say) rather than dispatching a new one that has to rediscover everything; start fresh only when the earlier one is gone or the new work is unrelated.", "meta": {"from": "journal"}} {"content": "work 35 is still open \u2014 end it or park it before you stop: journal work end 35 --how \"<what landed>\", or journal work park 35 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "rule 38 \u2014 Never change the git branch until the user says so, by name \u2014 The work happens on the branch the user named. That was main until message 5929 and question 80 (2026-09-23), which moved the sins work to the branch sins. Do not create, switch to or merge any other branch unless the user names it in their own words.", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal <noun> <method>. A helper added to the base class therefore becomes a command on every type \u2014 which is how journal <type> handled and journal <type> refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.; rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done <n> --how, or by a commit whose message carries Journal: todos done <n> at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.", "meta": {"from": "journal"}} {"content": "fact 23 \u2014 Every upgrade brings system sequences and their triggers in line\u2026 \u2014 install.py runs ship_sequences after the migrations on each upgrade, so features/sequences/shipped.py is the whole source: change its wording and the next upgrade updates every journal, no migration needed. Shipped rows carry system=True and are read-only for everyone but SYSTEM (controllers/base.py _shipped).; fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply <n> \"<text>\" instead of the tag.", "meta": {"from": "journal"}} {"content": "rule 51 \u2014 Every finished feature is committed, pushed and released with a new\u2026 \u2014 Message 9207 (2026-09-24): when a new feature is ready, commit, push and publish a new tag. This is the user's standing word for releasing, so rule 44's only-when-the-user-says is met by it for finished features; fixes in between wait for the next feature or a patch the user asks for.; rule 54 \u2014 Settings and feature switches are read at boot and on change, never\u2026 \u2014 The user, message 13349: the application boots, determines every feature and setting once, and re-evaluates only when something changes, such as a setting or a plugin. Never lazy-load settings.", "meta": {"from": "journal"}} {"content": "13 facts standing, read them \u2014 9. Every public method on a controller becomes a journal command; 13. This live session runs the installed copy in .journal/journal.pyz; 18. cProfile inflates the slow-request profiles about tenfold; 20. A slim supervisor holds the agent and a worker reloads on every build; 23. Every upgrade brings system sequences and their triggers in line with the code; 24. An answer followed by tool calls can be missing from Claude's transcript; 25. A designer's install packs the whole tree, half-done server edits included; 26. Claude Code reads agent profiles when a session starts; 27. Running src/journal.py against the live .journal root starts a second server; 28. The designer agent type exists, so design work goes to a subagent; 29. Codex's transcript records the end of every exec session, polled or not; 30. The tunler server refuses TLS for any subdomain without a tunnel; 34. A hooks list in a checkout's .claude/settings.json stops every helper at start; 43 rules in force, read them \u2014 7. journal disable must only ever be run because the user explicitly asked for it,; 9. Research dispatched to a subagent ends in a REPORT for the user, compiled by the; 13. A title names the thing in at most 80 characters and never explains it with a co; 14. A small journal capability is a feature under features, with at most one test; 17. Do not restart the viewer for frontend-only changes; 18. Provider-specific code belongs in providers, never features; 19. Providers report facts; features decide behavior; 22. File distinct user work requests immediately; 27. Name a declaration with the word a reader already knows; 30. The viewer has one API client, and every piece of it does one job; 31. Every finding a reviewing agent reports becomes its own to-do; 35. Write clean code - one funnel per kind of operation, never the same method twice; 36. Clean, DRY, idiomatic before it is committed, never after it is complained about; 37. Close every to-do explicitly with todo done or a Journal commit trailer; 38. Never change the git branch until the user says so, by name; 39. Use only registered exclamation response tags; 40. A feature is named for what it is, never for its machinery; 41. Keep moving, run the whole suite before every commit, never wait; 42. Every user-facing text passes the formatters before it leaves the server; 43. A request or hook over its budget is fixed before the next release; 45. No prose words as names in code - said, says, heard, spoke, told, shown, became; 46. Only commit and push once the whole journal is proven to boot; 47. The journal sets itself up once, when the server starts, never per command; 48. The viewer is built from its component library, and pages only compose it; 49. A dialog whose content grows keeps one fixed height, and its content scrolls; 50. Everything the user does is doable in the viewer; 51. Every finished feature is committed, pushed and released with a new version tag; 52. A chat mark for something the user did sits on the user's side; 54. Settings and feature switches are read at boot and on change, never per call; 55. Always dispatch Codex helpers on gpt-6-sol; 56. Helpers are for work that writes; subagents read, research and design; 57. Never merge the overnight refactor into main before its pull request is approved; 58. A design runs three critique rounds, then is built on a branch; 59. Every viewer heading and label says plainly what it is about; 60. A hotfix is done by a dispatched agent in a worktree of main; 61. Features wait as pull requests until approved; only hotfixes merge at once; 62. The voice profile shapes only the agent's chat speech, never code or text; 63. A small design is drawn once and the user approves it, with no critique rounds; 64. A finished feature is merged into main without waiting for approval; 65. Run only new and affected tests while working; the whole suite only before main; 66. The journal never slows the agent down; 67. Never answer a journal line in the chat; act on it silently; 68. The orchestrator approves the designer's designs itself", "meta": {"from": "journal"}} {"content": "rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.", "meta": {"from": "journal"}} {"content": "your command ran 30s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "the Version commit running in the background came back - cat VERSION; python3\u2026; law L3 \u2014 Read narrowly - grep for the line, sed a range, head the file; never\u2026 \u2014 Everything a tool returns stays in the context for good and is paid for on every turn after it. Search before you read, read the range you need, and cap output with grep, head or tail. Read a whole file only when you need all of it.", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 30", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 30", "meta": {"from": "journal"}} {"content": "rule 61 \u2014 Features wait as pull requests until approved; only hotfixes merge\u2026 \u2014 Message 17118 (2026-10-06), after the overnight refactor merged as 2.252.0: start new work in a new branch, do not merge, write the pull request. Every pull request or new feature is parked until the user approves it. Hotfixes can be merged into main immediately (by a dispatched agent in a worktree of main, rule 60).; rule 64 \u2014 A finished feature is merged into main without waiting for approval \u2014 The user, message 17815 (2026-10-07): 'make sure that no pull requests are lingering on the repository. You may merge them into main... You are allowed to merge everything into main once the feature is completed.' This replaces rule 61's wait for approval: a feature still goes on its own branch, and once it is complete, tested and its whole suite passes, it is merged into main and released, and no pull request is left open.; rule 65 \u2014 Run only new and affected tests while working; the whole suite only\u2026 \u2014 The user, messages 17914 to 17917 (2026-10-07): 'stop running the whole test suite and wasting my time... please only run the new or affected tests, and then, whenever you are merging to main or publishing to main, you can run the full test suite.' Replaces rule 41's whole suite before every commit: on a feature branch, run the tests beside what changed (journal check touched, or the feature's test.py and the browser scenarios it touches); the whole suite runs once, before a merge into main and its release.", "meta": {"from": "journal"}} {"content": "rule 39 \u2014 Use only registered exclamation response tags \u2014 A tag like [!reply:12] runs a command, and only the tags in the tags.runs setting are registered. An invented tag does nothing and shows as raw text in the chat. Use the registered ones (reply, log, end, todo, fact, rule) and nothing else.", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "check 2.267.14 on origin/main; then to-do 3680 on a branch from it now - you\u2026 \u2014 look at the thing itself: the background shell's output, the process, the run's status. If it is still going, say journal work await \"<what you wait for>\" again and wait. If it finished or failed, journal work log what came of it and take the next step. Never wait for something you can do without.", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 31", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 31, 32", "meta": {"from": "journal"}} {"content": "waiting: 3 unread todos 31, 32, 33", "meta": {"from": "journal"}} {"content": "waiting: 3 unread todos 31, 32, 33", "meta": {"from": "journal"}} {"content": "waiting: 3 unread todos 31, 32, 33", "meta": {"from": "journal"}} {"content": "waiting: 3 unread todos 31, 32, 33", "meta": {"from": "journal"}} {"content": "waiting: 3 unread todos 31, 32, 33", "meta": {"from": "journal"}} {"content": "waiting: 3 unread todos 31, 32, 33", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 31, 32, 33, 34", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 31, 32, 33, 34", "meta": {"from": "journal"}} {"content": "waiting: 4 unread todos 31, 32, 33, 34", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat; your chat talked about the journal's workings - \"Still waiting\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "auto mode is on and work 39 stands still while todo 31 is ready \u2014 if work 39 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 31. Stop only when nothing ready is left.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 4 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "rule 42 \u2014 Every user-facing text passes the formatters before it leaves the\u2026 \u2014 Not only a brief. A title, an abstract, an outcome and every section body are read by a person, so each goes through the same formatters on its way to the viewer \u2014 chat turns, activity items, to-do rows, inspector pages, docs alike. One field formatted out of five is not a rule, it is an accident, and it is how a raw tag ended up in the activity list after the tags feature had been stripping them for weeks. When a new field carries words a person reads, it joins the list in the same place.; rule 49 \u2014 A dialog whose content grows keeps one fixed height, and its content\u2026 \u2014 Message 5361, after asking more than once: a dialog that shows output as it arrives (install, update, logs) opens at its final height and never jumps; only its content scrolls.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 2 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "rule 57 \u2014 Never merge the overnight refactor into main before its pull request\u2026 \u2014 Messages 15005, 15006, 15109, 15110 (2026-10-04): all refactor work goes on branch overnight-refactor and reaches the user as one pull request, which they read in the morning; nothing of it is merged into main until they say so. Hotfixes the user explicitly asks for go to main at once and are merged into the branch.", "meta": {"from": "journal"}} {"content": "your command ran 33s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "auto mode is on and work 42 stands still while todo 32 is ready \u2014 if work 42 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 32. Stop only when nothing ready is left.; Code Commandments \u2014 before you wrap up \u2014 you've changed 4 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 32", "meta": {"from": "journal"}} {"content": "your command ran 32s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 32", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 32", "meta": {"from": "journal"}} {"content": "suggestions and every-action tests, result came back - until grep -q\u2026", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"I'm still waiting\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "your command ran 34s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 32", "meta": {"from": "journal"}} {"content": "your command ran 31s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 32, 36", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal <noun> <method>. A helper added to the base class therefore becomes a command on every type \u2014 which is how journal <type> handled and journal <type> refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.; fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply <n> \"<text>\" instead of the tag.; rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done <n> --how, or by a commit whose message carries Journal: todos done <n> at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.", "meta": {"from": "journal"}} {"content": "rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.", "meta": {"from": "journal"}} {"content": "fact 23 \u2014 Every upgrade brings system sequences and their triggers in line\u2026 \u2014 install.py runs ship_sequences after the migrations on each upgrade, so features/sequences/shipped.py is the whole source: change its wording and the next upgrade updates every journal, no migration needed. Shipped rows carry system=True and are read-only for everyone but SYSTEM (controllers/base.py _shipped).", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 5 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 5 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "rule 51 \u2014 Every finished feature is committed, pushed and released with a new\u2026 \u2014 Message 9207 (2026-09-24): when a new feature is ready, commit, push and publish a new tag. This is the user's standing word for releasing, so rule 44's only-when-the-user-says is met by it for finished features; fixes in between wait for the next feature or a patch the user asks for.", "meta": {"from": "journal"}} {"content": "rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.; rule 38 \u2014 Never change the git branch until the user says so, by name \u2014 The work happens on the branch the user named. That was main until message 5929 and question 80 (2026-09-23), which moved the sins work to the branch sins. Do not create, switch to or merge any other branch unless the user names it in their own words.", "meta": {"from": "journal"}} {"content": "law L3 \u2014 Read narrowly - grep for the line, sed a range, head the file; never\u2026 \u2014 Everything a tool returns stays in the context for good and is paid for on every turn after it. Search before you read, read the range you need, and cap output with grep, head or tail. Read a whole file only when you need all of it.", "meta": {"from": "journal"}} {"content": "rule 65 \u2014 Run only new and affected tests while working; the whole suite only\u2026 \u2014 The user, messages 17914 to 17917 (2026-10-07): 'stop running the whole test suite and wasting my time... please only run the new or affected tests, and then, whenever you are merging to main or publishing to main, you can run the full test suite.' Replaces rule 41's whole suite before every commit: on a feature branch, run the tests beside what changed (journal check touched, or the feature's test.py and the browser scenarios it touches); the whole suite runs once, before a merge into main and its release.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 2 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "the end tag does this in one step \u2014 [!end:N] makes the turn itself what landed; it runs only when it opens the last text of your turn", "meta": {"from": "journal"}} {"content": "rule 48 \u2014 The viewer is built from its component library, and pages only\u2026 \u2014 Message 4258. Every visual piece the viewer shows more than once, or that a user would recognise as the same kind of thing (a dialog, a side panel or inspector, a dropdown, a list row, a switch, a button), is one component in web/src/kit, extracted aggressively, and every page composes those components instead of building its own copy. Before writing markup or styles in a page, look for the kit component that already does it and extend it with a prop; a second hand-built version is a bug. The side panel that animated in but not out, while a separate skill panel did both, is the example.", "meta": {"from": "journal"}} {"content": "work 48 in hand \u2014 A repented sin settles its card and a re-found sin raises no\u2026 \u2014 if this is not what you are doing, end it or park it and start the work you are in", "meta": {"from": "journal"}} {"content": "that Edit call returned 83,759 characters, the largest this session \u2014 It stays in the context for good. If you were looking for one thing in it, the next read can be narrower: grep for the line, sed a range, head the file.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 48 stands still while todo 39 is ready \u2014 if work 48 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 39. Stop only when nothing ready is left.; work 48 is still open, with nothing logged \u2014 journal work log 48 \"<what was decided or done, and why>\" \u2014 then journal work end 48 --how \"<what landed>\", or journal work park 48 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat; Code Commandments \u2014 before you wrap up \u2014 you've changed 3 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 3 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 48 stands still while todo 39 is ready \u2014 if work 48 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 39. Stop only when nothing ready is left.; work 48 is still open \u2014 end it or park it before you stop: journal work end 48 --how \"<what landed>\", or journal work park 48 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "your command ran 30s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "fact 25 \u2014 A designer's install packs the whole tree, half-done server edits\u2026 \u2014 2026-09-25: Eames and Saul run python3 src/journal.py --root .journal upgrade after their viewer builds; it packs every file in src, so a server handler I was halfway through writing went live and raised on every PostToolUse hook. While designers work in parallel, keep server edits whole between tool calls (write and test in the scratchpad first), and reinstall after reverting anything.; fact 28 \u2014 The designer agent type exists, so design work goes to a subagent \u2014 Since 2026-10-01 .claude/agents/designer.md (Dieter, Opus, Claude Design tools, read-only on the repository) is an agent type; rule 56 says design is a subagent's job, never a helper's.; rule 58 \u2014 A design runs three critique rounds, then is built on a branch \u2014 Messages 17276 and 17281 (2026-10-06): the norm is a three-round cycle. Round by round, the designer designs (or revises), separate critic agents review the design through their lenses (the critic agent type, .claude/agents/critic.md: read-only, with a browser; one per lens, such as first-time, native, words and parity), and the designer adjusts it to their findings; three rounds in all. The three rounds stand in for the user's approval of the design: the user does not approve it. After the third round the design is built on a branch of its own, which ends in a pull request that waits for the user's approval (rule 61). Replaces message 15725's prototype approval.; rule 63 \u2014 A small design is drawn once and the user approves it, with no\u2026 \u2014 The user, messages 17628 and 17629 (2026-10-07), about the tooltip and waiting-status designs: 'This design round doesn't really need multiple rounds... I just want the designer agent to design it, and I will approve it.' Rule 58's three critique rounds are for large designs such as the phone app; a small one (a tooltip, a status word, one control) is drawn once by the designer, the link goes to the user, and it is built once the user approves it.; rule 68 \u2014 The orchestrator approves the designer's designs itself \u2014 Message 19718 (and 18972): whenever a designer subagent is sent out, here or on a remote, the orchestrator makes the final call on whether the design is right and approves it; it never waits for the user to. This replaces the user-approval step in rule 63, which only the user can strike.", "meta": {"from": "journal"}} {"content": "rule 27 \u2014 Name a declaration with the word a reader already knows \u2014 An attribute, a variable or a field gets the ordinary programming word for what it holds, not an evocative one. was, heard and alone were poetry; aliases, notify_actions and urgent_actions are what they are. The test: could a reader who has never seen this codebase guess what it holds from the name alone? Prose belongs in the help text and the abstract, where it is read as prose. This does not license abbreviations \u2014 a plain word in full, not a short one.", "meta": {"from": "journal"}} {"content": "rule 54 \u2014 Settings and feature switches are read at boot and on change, never\u2026 \u2014 The user, message 13349: the application boots, determines every feature and setting once, and re-evaluates only when something changes, such as a setting or a plugin. Never lazy-load settings.; rule 57 \u2014 Never merge the overnight refactor into main before its pull request\u2026 \u2014 Messages 15005, 15006, 15109, 15110 (2026-10-04): all refactor work goes on branch overnight-refactor and reaches the user as one pull request, which they read in the morning; nothing of it is merged into main until they say so. Hotfixes the user explicitly asks for go to main at once and are merged into the branch.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 `parts.py`, changed since the last check, breaks a rule. Fi\u2026 \u2014 Code Commandments \u2014 `parts.py`, changed since the last check, breaks a rule. Fix it now, at its SOURCE, while the code is still in front of you: \u00b7 \u2022 python-dict-bag at /Users/jessegall/projects/agent-journal/.claude/worktrees/quiet-restart/src/features/plugins/parts.py:106 \u00b7 LOAD the skill `commandments-python-value-objects` before fixing \u2014 load it even if you believe you already have. \u00b7 Run `commandments info <sin>` if a rule is not one you recognise. This check reads a file at a time, so it is not the whole picture \u2014 `judge` still is.", "meta": {"from": "journal"}} {"content": "fact 13 \u2014 This live session runs the installed copy in .journal/journal.pyz \u2014 The running journal (server, hooks, CLI) runs from .journal/journal.pyz with its viewer and skills in .journal/src, never from the repo. A change in the repo reaches it only through python3 src/journal.py --root .journal upgrade, which packs the zip again. A commit alone changes nothing that is running.; law L6 \u2014 A journal line is an instruction, never a message - act on it and\u2026 \u2014 A line that starts with [journal], a reminder, a notice or an old helper report is the journal telling the agent what to do, not the user speaking. Answering it fills the user's chat with noise. Act on it, or note it and carry on; write in the chat only what the user needs to know, such as a failure, a finished piece of work or a decision that waits on them.; rule 42 \u2014 Every user-facing text passes the formatters before it leaves the\u2026 \u2014 Not only a brief. A title, an abstract, an outcome and every section body are read by a person, so each goes through the same formatters on its way to the viewer \u2014 chat turns, activity items, to-do rows, inspector pages, docs alike. One field formatted out of five is not a rule, it is an accident, and it is how a raw tag ended up in the activity list after the tags feature had been stripping them for weeks. When a new field carries words a person reads, it joins the list in the same place.; rule 45 \u2014 No prose words as names in code - said, says, heard, spoke, told\u2026 \u2014 Messages 1360 and 1698. The user has said more than once that code must not read like prose: a variable, attribute, property or function is named for what it holds or does (text, command, labels, lines), never with a verb from a story. 'says' on the Design type (1360) and 'said = call.said.lower()' in features/recital.py (1698) are the examples. Rule 27 states the naming rule; this one carries the words, so writing one of them whispers it. Before writing a name, ask whether a reader who has never seen the code would know what it holds.; rule 49 \u2014 A dialog whose content grows keeps one fixed height, and its content\u2026 \u2014 Message 5361, after asking more than once: a dialog that shows output as it arrives (install, update, logs) opens at its final height and never jumps; only its content scrolls.; rule 59 \u2014 Every viewer heading and label says plainly what it is about \u2014 The user, messages 16499, 16839, 16844, 16989, 16992 and 16993 (2026-10-06), after 'Where the words count', 'Watch for the words in', 'This project', 'This browser' and 'Stop the journal' as tab names: viewer text reads like Linear, GitHub or Vercel. A place (page, tab, group, sidebar item) is a short noun: Settings, Project, Browser, Services, Updates, Plugins; never 'This project' or a phrase. A button is a verb for what happens: Stop, Install, Copy link, Pause the plan. A heading names what the reader looks at, and its options finish its sentence: 'Trigger when' / 'A word is written'. Plain literal words: no metaphor or whimsy ('kettle on, waiting'), no app speaking as I, none of the journal's internal words (row, hook, nudge, engine, slate). One word for one thing everywhere, sentence case, as short as it can be while clear. Applies to designers' prototypes, helpers' builds, the viewer's JavaScript lists, feature details, and shipped sequence and trigger titles alike.; that Edit call returned 85,462 characters, the largest this session \u2014 It stays in the context for good. If you were looking for one thing in it, the next read can be narrower: grep for the line, sed a range, head the file.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 5 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 5 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "your command ran 32s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "plugins test result came back - cd\u2026", "meta": {"from": "journal"}} {"content": "fact 34 \u2014 A hooks list in a checkout's .claude/settings.json stops every\u2026 \u2014 Seen 2026-10-08: since commit 707a82915 the committed .claude/settings.json held {\"hooks\": []}; current Claude Code answers a hooks value that is not an object with a SettingsWarning dialog, which a headless helper cannot answer, so helpers 183 and 184 exited before doing anything (their launch logs in .journal/runtime/launches/ show it). This repository's journal hooks live in settings.local.json; the committed settings.json stays {}.; rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.", "meta": {"from": "journal"}} {"content": "rule 39 \u2014 Use only registered exclamation response tags \u2014 A tag like [!reply:12] runs a command, and only the tags in the tags.runs setting are registered. An invented tag does nothing and shows as raw text in the chat. Use the registered ones (reply, log, end, todo, fact, rule) and nothing else.; rule 43 \u2014 A request or hook over its budget is fixed before the next release \u2014 Comment 1151 on this rule. When the faults feature reports a request, a hook or a command slower than its budget, file it as a to-do at once. It does not jump ahead of the work in hand, but no version is published while one is still open: profile it, fix it, and verify the new time before the release goes out. The budget is 50ms, because everything runs locally against files.", "meta": {"from": "journal"}} {"content": "check 2.267.14 and 2.267.15 on origin/main; then rebase, Version 2.267.16 and\u2026 \u2014 look at the thing itself: the background shell's output, the process, the run's status. If it is still going, say journal work await \"<what you wait for>\" again and wait. If it finished or failed, journal work log what came of it and take the next step. Never wait for something you can do without.", "meta": {"from": "journal"}} {"content": "fact 18 \u2014 cProfile inflates the slow-request profiles about tenfold \u2014 The faults feature writes a profile when a request passes its budget, and the profile is taken with cProfile, which adds per-call overhead. On 2026-09-22 /api/summary profiled at 58ms with 48ms inside Resource.fork's deep copy; with the profiler off the same call ran in 2 to 7ms. Read the profile for where the time goes in relative terms, then time the call with curl before changing anything.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 54 stands still while todo 43 is ready \u2014 if work 54 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 43. Stop only when nothing ready is left.; work 54 is still open, with nothing logged \u2014 journal work log 54 \"<what was decided or done, and why>\" \u2014 then journal work end 54 --how \"<what landed>\", or journal work park 54 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 4 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; rule 52 \u2014 A chat mark for something the user did sits on the user's side \u2014 Message 10960 (2026-09-25): marks for the user's own actions, such as answering a question, are right-aligned like the user's messages. A mark is put there by giving its card side=user.", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal <noun> <method>. A helper added to the base class therefore becomes a command on every type \u2014 which is how journal <type> handled and journal <type> refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.; rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done <n> --how, or by a commit whose message carries Journal: todos done <n> at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "fact 20 \u2014 A slim supervisor holds the agent and a worker reloads on every build \u2014 Since 2.118.0 (2026-09-23). src/supervisor.py is standard library only and never reloads: journal claude hands its process over to it (os.execv), and it owns the pty and the agent process, relays the terminal, writes the printed and screen captures, listens on the typist socket, restarts the agent in the same session from a relaunch command written to its runtime folder while a restart is pending, and stops it with escalation while draining the pty (an agent cannot finish exiting on macOS while its output is unread). It starts the worker (src/worker.py, which runs runner/worker.py; engine/worker.py stays as an alias for supervisors started before 2.201) and starts it again whenever it exits: RELOAD on a new build, RELAUNCH to restart the agent, STOP to end, HEAL or a quick crash to roll back a build through journal heal. The worker holds everything else: seating the session, the start-up confirm typed through the typist, services, viewer, update check, check-in, and the one-time relaunch of sessions launched before agents/terminal.py LAUNCH. agents/terminal.py holds only journal-side helpers. The server (serve.py) still runs the engines and re-execs itself on a .py change. When the agent exits, the supervisor runs journal ended, which puts set-aside hooks back and stops the server when no session is left.", "meta": {"from": "journal"}} {"content": "rule 66 \u2014 The journal never slows the agent down \u2014 The user, message 18990, after hooks timed out and waited on locks under load: the journal must never, ever decrease the performance of an agent. A hook answers at once with what decides the tool call; everything else runs after, in the background, and reaches the agent as a message. No hook waits on a lock it does not need.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 46", "meta": {"from": "journal"}} {"content": "the restart boots test came back\u2026", "meta": {"from": "journal"}} {"content": "auto mode is on and work 58 stands still while todo 46 is ready \u2014 if work 58 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 46. Stop only when nothing ready is left.", "meta": {"from": "journal"}} {"content": "work 58 is still open \u2014 end it or park it before you stop: journal work end 58 --how \"<what landed>\", or journal work park 58 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "law L3 \u2014 Read narrowly - grep for the line, sed a range, head the file; never\u2026 \u2014 Everything a tool returns stays in the context for good and is paid for on every turn after it. Search before you read, read the range you need, and cap output with grep, head or tail. Read a whole file only when you need all of it.", "meta": {"from": "journal"}} {"content": "your command ran 80s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 78s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself; rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.", "meta": {"from": "journal"}} {"content": "your command ran 74s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 59s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 35s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 46s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 48s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself; fact 26 \u2014 Claude Code reads agent profiles when a session starts \u2014 Seen 2026-09-26: after the board-filler's profile in .claude/agents gained its steps and the Grep rule, dispatches from the running session still used the old profile (a 3.5-minute first question, shell grep refused); after the session restarted, the same request took 21 seconds with 4 calls. A change to an agent type reaches only sessions started after it is written.; rule 62 \u2014 The voice profile shapes only the agent's chat speech, never code or\u2026 \u2014 The user, message 17620 (2026-10-07): the profile (butler, homie, coach, colleague) must not leak into the code the agent writes or into user-facing text of any application it works on: names, labels, comments, commit messages, docs and briefs written into a project use plain words (helper, subagent). Speaking in the chat in the profile's voice is fine.", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "your command ran 60s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 64s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 69s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 81s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 85s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "rule 61 \u2014 Features wait as pull requests until approved; only hotfixes merge\u2026 \u2014 Message 17118 (2026-10-06), after the overnight refactor merged as 2.252.0: start new work in a new branch, do not merge, write the pull request. Every pull request or new feature is parked until the user approves it. Hotfixes can be merged into main immediately (by a dispatched agent in a worktree of main, rule 60).; rule 64 \u2014 A finished feature is merged into main without waiting for approval \u2014 The user, message 17815 (2026-10-07): 'make sure that no pull requests are lingering on the repository. You may merge them into main... You are allowed to merge everything into main once the feature is completed.' This replaces rule 61's wait for approval: a feature still goes on its own branch, and once it is complete, tested and its whole suite passes, it is merged into main and released, and no pull request is left open.; rule 65 \u2014 Run only new and affected tests while working; the whole suite only\u2026 \u2014 The user, messages 17914 to 17917 (2026-10-07): 'stop running the whole test suite and wasting my time... please only run the new or affected tests, and then, whenever you are merging to main or publishing to main, you can run the full test suite.' Replaces rule 41's whole suite before every commit: on a feature branch, run the tests beside what changed (journal check touched, or the feature's test.py and the browser scenarios it touches); the whole suite runs once, before a merge into main and its release.", "meta": {"from": "journal"}} {"content": "your command ran 120s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 188s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 211s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 265s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 332s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 339s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 350s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 4 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "your command ran 361s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"I'm still waiting\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "rule 51 \u2014 Every finished feature is committed, pushed and released with a new\u2026 \u2014 Message 9207 (2026-09-24): when a new feature is ready, commit, push and publish a new tag. This is the user's standing word for releasing, so rule 44's only-when-the-user-says is met by it for finished features; fixes in between wait for the next feature or a patch the user asks for.", "meta": {"from": "journal"}} {"content": "your command ran 412s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 447s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 466s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 484s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "your command ran 505s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"Nothing else is open on my\u2026 \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"Still waiting\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "your command ran 581s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 610s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 618s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 636s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 664s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "the hook hit an error \u2014 journal: the hook hit an error and kept going; the last of it is below and the whole of it is in .journal/runtime/engine.log. Fix it, then say so. the hook got no answer from the server 1 times (codes 000)", "meta": {"from": "journal"}} {"content": "your command ran 696s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself; law L5 \u2014 Every subagent dispatch names the agent, in the naming style of the\u2026 \u2014 A name is how the user and the chat tell subagents apart and how they are messaged later; an id or a task line is not a name. Start the dispatch's description with the name, a colon, then the task. The profile in use says how its agents are named.", "meta": {"from": "journal"}} {"content": "your command ran 730s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 746s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself; rule 40 \u2014 A feature is named for what it is, never for its machinery \u2014 Messages 599, 600 and 703. A feature is a capability the user would name and would think of switching off. File tracking, a write gate, a phrase bank, a tree diff are services used inside a feature, not features of their own: they live in the feature they serve. Before adding a directory under features/, say what the user would call it; if the answer names a mechanism, it belongs inside something else. Report 16 holds the grouping this implies.", "meta": {"from": "journal"}} {"content": "your command ran 788s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply <n> \"<text>\" instead of the tag.", "meta": {"from": "journal"}} {"content": "your command ran 882s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 913s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 919s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 926s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "todo 50 next", "meta": {"from": "journal"}} {"content": "your command ran 924s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "you stopped with work 61, A viewer test's journal server outlived its run by\u2026 \u2014 carry on with it now. If it waits on something outside your hands, say journal work await \"<what you wait for>\"; if it waits on the user, put the question on its row with journal todo ask and take the next ready row; if something else goes first, journal work park 61 \"<why>\".; work 61 is still open, with nothing logged \u2014 journal work log 61 \"<what was decided or done, and why>\" \u2014 then journal work end 61 --how \"<what landed>\", or journal work park 61 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "the await tag does this in one step \u2014 [!await] makes the rest of the turn what you wait for; [!await on=(\"<id>\", \"helper:<n>\")] waits on those; it runs only when it opens the last text of your turn", "meta": {"from": "journal"}} {"content": "your command ran 878s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "you stopped with work 61, A viewer test's journal server outlived its run by\u2026 \u2014 carry on with it now. If it waits on something outside your hands, say journal work await \"<what you wait for>\"; if it waits on the user, put the question on its row with journal todo ask and take the next ready row; if something else goes first, journal work park 61 \"<why>\".; work 61 is still open \u2014 end it or park it before you stop: journal work end 61 --how \"<what landed>\", or journal work park 61 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "you ran the same check 3 times in a row - cat\u2026 \u2014 if you are waiting for something to change, say journal work await \"<what you wait for>\" and end your turn: you are asked to look again every five minutes, and a background command tells you itself when it ends. Keep checking only if each look moves the work on.", "meta": {"from": "journal"}} {"content": "the stop test for the viewer server watcher (3704) came back - stop test\u2026", "meta": {"from": "journal"}} {"content": "your command ran 910s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "you stopped with work 61, A viewer test's journal server outlived its run by\u2026 \u2014 carry on with it now. If it waits on something outside your hands, say journal work await \"<what you wait for>\"; if it waits on the user, put the question on its row with journal todo ask and take the next ready row; if something else goes first, journal work park 61 \"<why>\".; Code Commandments \u2014 before you wrap up \u2014 you've changed 2 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "your command ran 950s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 954s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "a viewer browser scenario run through the new watcher (3704) came back\u2026", "meta": {"from": "journal"}} {"content": "your command ran 978s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "fact 25 \u2014 A designer's install packs the whole tree, half-done server edits\u2026 \u2014 2026-09-25: Eames and Saul run python3 src/journal.py --root .journal upgrade after their viewer builds; it packs every file in src, so a server handler I was halfway through writing went live and raised on every PostToolUse hook. While designers work in parallel, keep server edits whole between tool calls (write and test in the scratchpad first), and reinstall after reverting anything.; rule 57 \u2014 Never merge the overnight refactor into main before its pull request\u2026 \u2014 Messages 15005, 15006, 15109, 15110 (2026-10-04): all refactor work goes on branch overnight-refactor and reaches the user as one pull request, which they read in the morning; nothing of it is merged into main until they say so. Hotfixes the user explicitly asks for go to main at once and are merged into the branch.", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"I'm still waiting\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "your command ran 1005s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your command ran 962s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"Nothing else is open on my\u2026 \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"Still waiting\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"To-do 3706 is closed\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "your command ran 849s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself; origin/main moved since your worktree was cut \u2014 It gained 35 commits (7caa3ef2d The pre-push boot guard stretches its install wait and its time limit by the machine's load; eb0e6a2ab Version 2.267.14; dee043bc4 The agent cell's row labels stay on one line and the value takes the rest; 50852f721 The agent cell's running row is labelled Running, the timer beside it; bc59ecce6 The journal's block is written once, into AGENTS.md; CLAUDE.md keeps the project's own text and imports AGENTS.md, and a copy of the block left in it is taken out; and 30 more). Rebase onto origin/main in /Users/jessegall/projects/agent-journal/.claude/worktrees/quiet-restart before you report.", "meta": {"from": "journal"}} {"content": "you ran the same check 3 times in a row - git fetch -q origin --tags 2>&1 |\u2026 \u2014 if you are waiting for something to change, say journal work await \"<what you wait for>\" and end your turn: you are asked to look again every five minutes, and a background command tells you itself when it ends. Keep checking only if each look moves the work on.", "meta": {"from": "journal"}} {"content": "rule 38 \u2014 Never change the git branch until the user says so, by name \u2014 The work happens on the branch the user named. That was main until message 5929 and question 80 (2026-09-23), which moved the sins work to the branch sins. Do not create, switch to or merge any other branch unless the user names it in their own words.", "meta": {"from": "journal"}} {"content": "origin/main moved since your worktree was cut \u2014 It gained 36 commits (a476949cc Every secret on the Secrets page has Programs it may go to, an agent proposes one with journal secret propose_programs and you allow it there, and the refusal names that control; 7caa3ef2d The pre-push boot guard stretches its install wait and its time limit by the machine's load; eb0e6a2ab Version 2.267.14; dee043bc4 The agent cell's row labels stay on one line and the value takes the rest; 50852f721 The agent cell's running row is labelled Running, the timer beside it; and 31 more). Rebase onto origin/main in /Users/jessegall/projects/agent-journal/.claude/worktrees/quiet-restart before you report.", "meta": {"from": "journal"}} {"content": "your command ran 32s in the foreground and was moved to the background \u2014 carry on with other work; you are told when it ends. Start a command you expect to take long in the background yourself", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "rule 42 \u2014 Every user-facing text passes the formatters before it leaves the\u2026 \u2014 Not only a brief. A title, an abstract, an outcome and every section body are read by a person, so each goes through the same formatters on its way to the viewer \u2014 chat turns, activity items, to-do rows, inspector pages, docs alike. One field formatted out of five is not a rule, it is an accident, and it is how a raw tag ended up in the activity list after the tags feature had been stripping them for weeks. When a new field carries words a person reads, it joins the list in the same place.; rule 48 \u2014 The viewer is built from its component library, and pages only\u2026 \u2014 Message 4258. Every visual piece the viewer shows more than once, or that a user would recognise as the same kind of thing (a dialog, a side panel or inspector, a dropdown, a list row, a switch, a button), is one component in web/src/kit, extracted aggressively, and every page composes those components instead of building its own copy. Before writing markup or styles in a page, look for the kit component that already does it and extend it with a prop; a second hand-built version is a bug. The side panel that animated in but not out, while a separate skill panel did both, is the example.; rule 49 \u2014 A dialog whose content grows keeps one fixed height, and its content\u2026 \u2014 Message 5361, after asking more than once: a dialog that shows output as it arrives (install, update, logs) opens at its final height and never jumps; only its content scrolls.; rule 68 \u2014 The orchestrator approves the designer's designs itself \u2014 Message 19718 (and 18972): whenever a designer subagent is sent out, here or on a remote, the orchestrator makes the final call on whether the design is right and approves it; it never waits for the user to. This replaces the user-approval step in rule 63, which only the user can strike.", "meta": {"from": "journal"}} {"content": "fact 13 \u2014 This live session runs the installed copy in .journal/journal.pyz \u2014 The running journal (server, hooks, CLI) runs from .journal/journal.pyz with its viewer and skills in .journal/src, never from the repo. A change in the repo reaches it only through python3 src/journal.py --root .journal upgrade, which packs the zip again. A commit alone changes nothing that is running.", "meta": {"from": "journal"}} {"content": "fact 34 \u2014 A hooks list in a checkout's .claude/settings.json stops every\u2026 \u2014 Seen 2026-10-08: since commit 707a82915 the committed .claude/settings.json held {\"hooks\": []}; current Claude Code answers a hooks value that is not an object with a SettingsWarning dialog, which a headless helper cannot answer, so helpers 183 and 184 exited before doing anything (their launch logs in .journal/runtime/launches/ show it). This repository's journal hooks live in settings.local.json; the committed settings.json stays {}.; rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.", "meta": {"from": "journal"}} {"content": "rule 45 \u2014 No prose words as names in code - said, says, heard, spoke, told\u2026 \u2014 Messages 1360 and 1698. The user has said more than once that code must not read like prose: a variable, attribute, property or function is named for what it holds or does (text, command, labels, lines), never with a verb from a story. 'says' on the Design type (1360) and 'said = call.said.lower()' in features/recital.py (1698) are the examples. Rule 27 states the naming rule; this one carries the words, so writing one of them whispers it. Before writing a name, ask whether a reader who has never seen the code would know what it holds.", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal <noun> <method>. A helper added to the base class therefore becomes a command on every type \u2014 which is how journal <type> handled and journal <type> refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.; rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.", "meta": {"from": "journal"}} {"content": "rule 54 \u2014 Settings and feature switches are read at boot and on change, never\u2026 \u2014 The user, message 13349: the application boots, determines every feature and setting once, and re-evaluates only when something changes, such as a setting or a plugin. Never lazy-load settings.", "meta": {"from": "journal"}} {"content": "rule 52 \u2014 A chat mark for something the user did sits on the user's side \u2014 Message 10960 (2026-09-25): marks for the user's own actions, such as answering a question, are right-aligned like the user's messages. A mark is put there by giving its card side=user.; rule 66 \u2014 The journal never slows the agent down \u2014 The user, message 18990, after hooks timed out and waited on locks under load: the journal must never, ever decrease the performance of an agent. A hook answers at once with what decides the tool call; everything else runs after, in the background, and reaches the agent as a message. No hook waits on a lock it does not need.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you commit \u2014 you've changed 3 judged files since the\u2026 \u2014 Code Commandments \u2014 before you commit: you've changed 3 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "fact 18 \u2014 cProfile inflates the slow-request profiles about tenfold \u2014 The faults feature writes a profile when a request passes its budget, and the profile is taken with cProfile, which adds per-call overhead. On 2026-09-22 /api/summary profiled at 58ms with 48ms inside Resource.fork's deep copy; with the profiler off the same call ran in 2 to 7ms. Read the profile for where the time goes in relative terms, then time the call with curl before changing anything.; rule 43 \u2014 A request or hook over its budget is fixed before the next release \u2014 Comment 1151 on this rule. When the faults feature reports a request, a hook or a command slower than its budget, file it as a to-do at once. It does not jump ahead of the work in hand, but no version is published while one is still open: profile it, fix it, and verify the new time before the release goes out. The budget is 50ms, because everything runs locally against files.", "meta": {"from": "journal"}} {"content": "law L3 \u2014 Read narrowly - grep for the line, sed a range, head the file; never\u2026 \u2014 Everything a tool returns stays in the context for good and is paid for on every turn after it. Search before you read, read the range you need, and cap output with grep, head or tail. Read a whole file only when you need all of it.; rule 47 \u2014 The journal sets itself up once, when the server starts, never per\u2026 \u2014 Messages 2220 and 2224. Discovering features and their handlers, seating the feature rows and the rename sweep happen once, at server boot, and again only when a feature is switched on or off, a plugin changes or an environment is added: features.load keeps a set-up generation per journal (SEATED) and redoes the work only when that generation moves. A command, a request or a hook uses what is already there; nothing in their path may rediscover handlers or rescan folders. A cost that repeats per call is a bug to fix, not a budget to raise.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 62 is still open \u2014 end it or park it before you stop: journal work end 62 --how \"<what landed>\", or journal work park 62 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "law L6 \u2014 A journal line is an instruction, never a message - act on it and\u2026 \u2014 A line that starts with [journal], a reminder, a notice or an old helper report is the journal telling the agent what to do, not the user speaking. Answering it fills the user's chat with noise. Act on it, or note it and carry on; write in the chat only what the user needs to know, such as a failure, a finished piece of work or a decision that waits on them.; rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.", "meta": {"from": "journal"}} {"content": "work 62 is still open \u2014 end it or park it before you stop: journal work end 62 --how \"<what landed>\", or journal work park 62 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done <n> --how, or by a commit whose message carries Journal: todos done <n> at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.", "meta": {"from": "journal"}} {"content": "fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply <n> \"<text>\" instead of the tag.; law L1 \u2014 Every subagent dispatch names its model and chooses the least\u2026 \u2014 Use a fast, economical model for mechanical work with a known answer, a capable general model for careful implementation, and the strongest model only when the task turns on difficult judgement. Inheriting the orchestrator's model is not a model choice. If the dispatch API cannot accept a model, that operation is exempt.; rule 61 \u2014 Features wait as pull requests until approved; only hotfixes merge\u2026 \u2014 Message 17118 (2026-10-06), after the overnight refactor merged as 2.252.0: start new work in a new branch, do not merge, write the pull request. Every pull request or new feature is parked until the user approves it. Hotfixes can be merged into main immediately (by a dispatched agent in a worktree of main, rule 60).; rule 64 \u2014 A finished feature is merged into main without waiting for approval \u2014 The user, message 17815 (2026-10-07): 'make sure that no pull requests are lingering on the repository. You may merge them into main... You are allowed to merge everything into main once the feature is completed.' This replaces rule 61's wait for approval: a feature still goes on its own branch, and once it is complete, tested and its whole suite passes, it is merged into main and released, and no pull request is left open.", "meta": {"from": "journal"}} {"content": "rule 65 \u2014 Run only new and affected tests while working; the whole suite only\u2026 \u2014 The user, messages 17914 to 17917 (2026-10-07): 'stop running the whole test suite and wasting my time... please only run the new or affected tests, and then, whenever you are merging to main or publishing to main, you can run the full test suite.' Replaces rule 41's whole suite before every commit: on a feature branch, run the tests beside what changed (journal check touched, or the feature's test.py and the browser scenarios it touches); the whole suite runs once, before a merge into main and its release.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 3 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 3 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 63 is still open, with nothing logged \u2014 journal work log 63 \"<what was decided or done, and why>\" \u2014 then journal work end 63 --how \"<what landed>\", or journal work park 63 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "work 63 is still open \u2014 end it or park it before you stop: journal work end 63 --how \"<what landed>\", or journal work park 63 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "work 63 is still open \u2014 end it or park it before you stop: journal work end 63 --how \"<what landed>\", or journal work park 63 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "fact 13 \u2014 This live session runs the installed copy in .journal/journal.pyz \u2014 The running journal (server, hooks, CLI) runs from .journal/journal.pyz with its viewer and skills in .journal/src, never from the repo. A change in the repo reaches it only through python3 src/journal.py --root .journal upgrade, which packs the zip again. A commit alone changes nothing that is running.", "meta": {"from": "journal"}} {"content": "work 64 is still open, with nothing logged \u2014 journal work log 64 \"<what was decided or done, and why>\" \u2014 then journal work end 64 --how \"<what landed>\", or journal work park 64 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 2 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "fact 34 \u2014 A hooks list in a checkout's .claude/settings.json stops every\u2026 \u2014 Seen 2026-10-08: since commit 707a82915 the committed .claude/settings.json held {\"hooks\": []}; current Claude Code answers a hooks value that is not an object with a SettingsWarning dialog, which a headless helper cannot answer, so helpers 183 and 184 exited before doing anything (their launch logs in .journal/runtime/launches/ show it). This repository's journal hooks live in settings.local.json; the committed settings.json stays {}.; rule 56 \u2014 Helpers are for work that writes; subagents read, research and design \u2014 The user, message 13464: there must be a clear distinction. A subagent can be dispatched for anything read-only: research, review, design. A helper is for actual work that writes, best in its own worktree when the work is separate. Dieter designing in Claude Design should have been a subagent, not a helper.", "meta": {"from": "journal"}} {"content": "fact 25 \u2014 A designer's install packs the whole tree, half-done server edits\u2026 \u2014 2026-09-25: Eames and Saul run python3 src/journal.py --root .journal upgrade after their viewer builds; it packs every file in src, so a server handler I was halfway through writing went live and raised on every PostToolUse hook. While designers work in parallel, keep server edits whole between tool calls (write and test in the scratchpad first), and reinstall after reverting anything.", "meta": {"from": "journal"}} {"content": "fact 9 \u2014 Every public method on a controller becomes a journal command \u2014 The CLI is generated from the controllers: each public method of Controller, or of a typed controller, turns into journal <noun> <method>. A helper added to the base class therefore becomes a command on every type \u2014 which is how journal <type> handled and journal <type> refuse came to exist, from the CRUD funnel and the refusal funnel. An internal helper on a controller is named with a leading underscore, as _shaped and _status already are, or it ships as a command nobody meant.; rule 40 \u2014 A feature is named for what it is, never for its machinery \u2014 Messages 599, 600 and 703. A feature is a capability the user would name and would think of switching off. File tracking, a write gate, a phrase bank, a tree diff are services used inside a feature, not features of their own: they live in the feature they serve. Before adding a directory under features/, say what the user would call it; if the answer names a mechanism, it belongs inside something else. Report 16 holds the grouping this implies.", "meta": {"from": "journal"}} {"content": "rule 54 \u2014 Settings and feature switches are read at boot and on change, never\u2026 \u2014 The user, message 13349: the application boots, determines every feature and setting once, and re-evaluates only when something changes, such as a setting or a plugin. Never lazy-load settings.", "meta": {"from": "journal"}} {"content": "fact 28 \u2014 The designer agent type exists, so design work goes to a subagent \u2014 Since 2026-10-01 .claude/agents/designer.md (Dieter, Opus, Claude Design tools, read-only on the repository) is an agent type; rule 56 says design is a subagent's job, never a helper's.; rule 46 \u2014 Only commit and push once the whole journal is proven to boot \u2014 Messages 2178 and 2179. A release that has not been started for real can crash every project that installs it, as 2.78.3 did for Codex and 2.84.0 did to project records. Before every commit and push: the full suite passes, including tests/test_it_boots.py, which installs a packed copy into a fresh project, launches Claude and Codex from it, writes a project record, upgrades again and checks the record survives. When a change touches launching, installing or upgrading, also start a real journal in a scratch project and close it properly afterwards, leaving no process behind.; rule 58 \u2014 A design runs three critique rounds, then is built on a branch \u2014 Messages 17276 and 17281 (2026-10-06): the norm is a three-round cycle. Round by round, the designer designs (or revises), separate critic agents review the design through their lenses (the critic agent type, .claude/agents/critic.md: read-only, with a browser; one per lens, such as first-time, native, words and parity), and the designer adjusts it to their findings; three rounds in all. The three rounds stand in for the user's approval of the design: the user does not approve it. After the third round the design is built on a branch of its own, which ends in a pull request that waits for the user's approval (rule 61). Replaces message 15725's prototype approval.; rule 63 \u2014 A small design is drawn once and the user approves it, with no\u2026 \u2014 The user, messages 17628 and 17629 (2026-10-07), about the tooltip and waiting-status designs: 'This design round doesn't really need multiple rounds... I just want the designer agent to design it, and I will approve it.' Rule 58's three critique rounds are for large designs such as the phone app; a small one (a tooltip, a status word, one control) is drawn once by the designer, the link goes to the user, and it is built once the user approves it.; rule 68 \u2014 The orchestrator approves the designer's designs itself \u2014 Message 19718 (and 18972): whenever a designer subagent is sent out, here or on a remote, the orchestrator makes the final call on whether the design is right and approves it; it never waits for the user to. This replaces the user-approval step in rule 63, which only the user can strike.", "meta": {"from": "journal"}} {"content": "fact 23 \u2014 Every upgrade brings system sequences and their triggers in line\u2026 \u2014 install.py runs ship_sequences after the migrations on each upgrade, so features/sequences/shipped.py is the whole source: change its wording and the next upgrade updates every journal, no migration needed. Shipped rows carry system=True and are read-only for everyone but SYSTEM (controllers/base.py _shipped).; rule 41 \u2014 Keep moving, run the whole suite before every commit, never wait \u2014 The full suite runs in about seven seconds: .venv/bin/python -m pytest -q --timeout=300 -n auto. Run it before every commit instead of picking tests by name. Group rows that sit in the same code into one sitting: write them all, test once, commit once. And never wait, not for a subagent, a build, or an answer you can carry on without. Dispatch it and keep working. If you truly are waiting on something, say so in the work log.; rule 43 \u2014 A request or hook over its budget is fixed before the next release \u2014 Comment 1151 on this rule. When the faults feature reports a request, a hook or a command slower than its budget, file it as a to-do at once. It does not jump ahead of the work in hand, but no version is published while one is still open: profile it, fix it, and verify the new time before the release goes out. The budget is 50ms, because everything runs locally against files.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 the edit you just made to `updates.py` breaks a rule. Fix i\u2026 \u2014 Code Commandments \u2014 the edit you just made to `updates.py` breaks a rule. Fix it now, at its SOURCE, while the code is still in front of you: \u00b7 \u2022 python-dict-return-bag at /Users/jessegall/projects/agent-journal/.claude/worktrees/quiet-restart/src/features/plugins/updates.py:57 \u00b7 LOAD the skill `commandments-python-value-objects` before fixing \u2014 load it even if you believe you already have. \u00b7 Run `commandments info <sin>` if a rule is not one you recognise. This check reads a file at a time, so it is not the whole picture \u2014 `judge` still is.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 the edit you just made to `PluginUpdateBand.vue` breaks a r\u2026 \u2014 Code Commandments \u2014 the edit you just made to `PluginUpdateBand.vue` breaks a rule. Fix it now, at its SOURCE, while the code is still in front of you: \u00b7 \u2022 control-flow-on-element at /Users/jessegall/projects/agent-journal/.claude/worktrees/quiet-restart/src/web/src/layout/PluginUpdateBand.vue:25; control-flow-on-element at /Users/jessegall/projects/agent-journal/.claude/worktrees/quiet-restart/src/web/src/layout/PluginUpdateBand.vue:31 \u00b7 LOAD the skill `commandments-frontend-vue-control-flow` before fixing \u2014 load it even if you believe you already have. \u00b7 Run `commandments info <sin>` if a rule is not one you recognise. This check reads a file at a time, so it is not the whole picture \u2014 `judge` still is.; rule 66 \u2014 The journal never slows the agent down \u2014 The user, message 18990, after hooks timed out and waited on locks under load: the journal must never, ever decrease the performance of an agent. A hook answers at once with what decides the tool call; everything else runs after, in the background, and reaches the agent as a message. No hook waits on a lock it does not need.", "meta": {"from": "journal"}} {"content": "rule 36 \u2014 Clean, DRY, idiomatic before it is committed, never after it is\u2026 \u2014 The user should never be the one who finds duplication, dead code, a clumsy name or a pattern the codebase does not use. Read the diff before every commit as a reviewer would, and fix what is not clean then, not in a follow-up after a complaint.", "meta": {"from": "journal"}} {"content": "law L6 \u2014 A journal line is an instruction, never a message - act on it and\u2026 \u2014 A line that starts with [journal], a reminder, a notice or an old helper report is the journal telling the agent what to do, not the user speaking. Answering it fills the user's chat with noise. Act on it, or note it and carry on; write in the chat only what the user needs to know, such as a failure, a finished piece of work or a decision that waits on them.", "meta": {"from": "journal"}} {"content": "rule 52 \u2014 A chat mark for something the user did sits on the user's side \u2014 Message 10960 (2026-09-25): marks for the user's own actions, such as answering a question, are right-aligned like the user's messages. A mark is put there by giving its card side=user.", "meta": {"from": "journal"}} {"content": "work 65 in hand \u2014 Plugin update check and bar (3714) \u2014 if this is not what you are doing, end it or park it and start the work you are in; rule 59 \u2014 Every viewer heading and label says plainly what it is about \u2014 The user, messages 16499, 16839, 16844, 16989, 16992 and 16993 (2026-10-06), after 'Where the words count', 'Watch for the words in', 'This project', 'This browser' and 'Stop the journal' as tab names: viewer text reads like Linear, GitHub or Vercel. A place (page, tab, group, sidebar item) is a short noun: Settings, Project, Browser, Services, Updates, Plugins; never 'This project' or a phrase. A button is a verb for what happens: Stop, Install, Copy link, Pause the plan. A heading names what the reader looks at, and its options finish its sentence: 'Trigger when' / 'A word is written'. Plain literal words: no metaphor or whimsy ('kettle on, waiting'), no app speaking as I, none of the journal's internal words (row, hook, nudge, engine, slate). One word for one thing everywhere, sentence case, as short as it can be while clear. Applies to designers' prototypes, helpers' builds, the viewer's JavaScript lists, feature details, and shipped sequence and trigger titles alike.; that Edit call returned 85,919 characters, the largest this session \u2014 It stays in the context for good. If you were looking for one thing in it, the next read can be narrower: grep for the line, sed a range, head the file.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 65 stands still while todo 59 is ready \u2014 if work 65 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 59. Stop only when nothing ready is left.; work 65 is still open \u2014 end it or park it before you stop: journal work end 65 --how \"<what landed>\", or journal work park 65 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 6 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 6 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; the await tag does this in one step \u2014 [!await] makes the rest of the turn what you wait for; [!await on=(\"<id>\", \"helper:<n>\")] waits on those; it runs only when it opens the last text of your turn", "meta": {"from": "journal"}} {"content": "your wait for the plugins test for the update check is over, because you are\u2026 \u2014 say journal work await \"<what you wait for>\" again if you are still only waiting", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 59, 60", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 59, 60", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 59, 60", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"Still waiting\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 59, 60", "meta": {"from": "journal"}} {"content": "waiting: 2 unread todos 59, 60", "meta": {"from": "journal"}} {"content": "rule 35 \u2014 Write clean code - one funnel per kind of operation, never the same\u2026 \u2014 Every kind of operation has one funnel: one method that creates, one that saves, one that refuses, one that formats. A second method that does the same thing under another name splits the behaviour, and the two drift apart. Before writing a method, search for the one that already does it and extend that. scripts/checks/funnels.py finds bodies written twice.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done <n> --how, or by a commit whose message carries Journal: todos done <n> at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.; rule 55 \u2014 Always dispatch Codex helpers on gpt-6-sol \u2014 The user's word, message 13431: switch the codex agents to GPT-6-Sol and make it their default. ~/.codex/config.toml names it as the default model too.", "meta": {"from": "journal"}} {"content": "rule 45 \u2014 No prose words as names in code - said, says, heard, spoke, told\u2026 \u2014 Messages 1360 and 1698. The user has said more than once that code must not read like prose: a variable, attribute, property or function is named for what it holds or does (text, command, labels, lines), never with a verb from a story. 'says' on the Design type (1360) and 'said = call.said.lower()' in features/recital.py (1698) are the examples. Rule 27 states the naming rule; this one carries the words, so writing one of them whispers it. Before writing a name, ask whether a reader who has never seen the code would know what it holds.; rule 61 \u2014 Features wait as pull requests until approved; only hotfixes merge\u2026 \u2014 Message 17118 (2026-10-06), after the overnight refactor merged as 2.252.0: start new work in a new branch, do not merge, write the pull request. Every pull request or new feature is parked until the user approves it. Hotfixes can be merged into main immediately (by a dispatched agent in a worktree of main, rule 60).; rule 64 \u2014 A finished feature is merged into main without waiting for approval \u2014 The user, message 17815 (2026-10-07): 'make sure that no pull requests are lingering on the repository. You may merge them into main... You are allowed to merge everything into main once the feature is completed.' This replaces rule 61's wait for approval: a feature still goes on its own branch, and once it is complete, tested and its whole suite passes, it is merged into main and released, and no pull request is left open.", "meta": {"from": "journal"}} {"content": "rule 65 \u2014 Run only new and affected tests while working; the whole suite only\u2026 \u2014 The user, messages 17914 to 17917 (2026-10-07): 'stop running the whole test suite and wasting my time... please only run the new or affected tests, and then, whenever you are merging to main or publishing to main, you can run the full test suite.' Replaces rule 41's whole suite before every commit: on a feature branch, run the tests beside what changed (journal check touched, or the feature's test.py and the browser scenarios it touches); the whole suite runs once, before a merge into main and its release.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 66 stands still while todo 60 is ready \u2014 if work 66 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 60. Stop only when nothing ready is left.; Code Commandments \u2014 before you wrap up \u2014 you've changed 1 judged file since the\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 1 judged file since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 66 is still open, with nothing logged \u2014 journal work log 66 \"<what was decided or done, and why>\" \u2014 then journal work end 66 --how \"<what landed>\", or journal work park 66 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply <n> \"<text>\" instead of the tag.; origin/main moved since your worktree was cut \u2014 It gained 57 commits (dd8bd2717 The hook's failure log line holds the machine's load as its fifth field, and the test that reads it expects it; fd05389ed Version 2.267.16; 22841d9f1 A fact or rule is whispered once to a session and again only when its words change, not every hundred uses; 28bc700c0 A channel queue an agent's channel is still reading is never cut to its tail: the cut moved its byte offset and replayed the whole queue as new notices; 39f55c2d6 A hook that gets no answer while the machine's load is above its cores is logged with the load and not reported to the agent; and 52 more). Rebase onto origin/main in /Users/jessegall/projects/agent-journal/.claude/worktrees/quiet-restart before you report.", "meta": {"from": "journal"}} {"content": "work 67 is still open, with nothing logged \u2014 journal work log 67 \"<what was decided or done, and why>\" \u2014 then journal work end 67 --how \"<what landed>\", or journal work park 67 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 3 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 3 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 60", "meta": {"from": "journal"}} {"content": "your wait for the stale-dist scenario run to end, then a manual viewer build\u2026 \u2014 say journal work await \"<what you wait for>\" again if you are still only waiting", "meta": {"from": "journal"}} {"content": "your wait for the rect probe of the helpers popover is over, because you are\u2026 \u2014 say journal work await \"<what you wait for>\" again if you are still only waiting", "meta": {"from": "journal"}} {"content": "fact 24 \u2014 An answer followed by tool calls can be missing from Claude's\u2026 \u2014 Seen 2026-09-24 for messages 9391-9404: text blocks opening with [!reply:n] that were followed by tool calls never appeared in the session's jsonl (only thinking and tool_use rows did), so the journal never saw them and the replies were lost. When a turn goes on after answering, send the answer with journal message reply <n> \"<text>\" instead of the tag.; rule 37 \u2014 Close every to-do explicitly with todo done or a Journal commit\u2026 \u2014 Ending work does not close its row. A to-do is closed by journal todo done <n> --how, or by a commit whose message carries Journal: todos done <n> at column 0, several numbers separated by commas. A row left open after its work landed misleads the next session and auto mode.; rule 51 \u2014 Every finished feature is committed, pushed and released with a new\u2026 \u2014 Message 9207 (2026-09-24): when a new feature is ready, commit, push and publish a new tag. This is the user's standing word for releasing, so rule 44's only-when-the-user-says is met by it for finished features; fixes in between wait for the next feature or a patch the user asks for.", "meta": {"from": "journal"}} {"content": "rule 42 \u2014 Every user-facing text passes the formatters before it leaves the\u2026 \u2014 Not only a brief. A title, an abstract, an outcome and every section body are read by a person, so each goes through the same formatters on its way to the viewer \u2014 chat turns, activity items, to-do rows, inspector pages, docs alike. One field formatted out of five is not a rule, it is an accident, and it is how a raw tag ended up in the activity list after the tags feature had been stripping them for weeks. When a new field carries words a person reads, it joins the list in the same place.; rule 45 \u2014 No prose words as names in code - said, says, heard, spoke, told\u2026 \u2014 Messages 1360 and 1698. The user has said more than once that code must not read like prose: a variable, attribute, property or function is named for what it holds or does (text, command, labels, lines), never with a verb from a story. 'says' on the Design type (1360) and 'said = call.said.lower()' in features/recital.py (1698) are the examples. Rule 27 states the naming rule; this one carries the words, so writing one of them whispers it. Before writing a name, ask whether a reader who has never seen the code would know what it holds.", "meta": {"from": "journal"}} {"content": "rule 61 \u2014 Features wait as pull requests until approved; only hotfixes merge\u2026 \u2014 Message 17118 (2026-10-06), after the overnight refactor merged as 2.252.0: start new work in a new branch, do not merge, write the pull request. Every pull request or new feature is parked until the user approves it. Hotfixes can be merged into main immediately (by a dispatched agent in a worktree of main, rule 60).; rule 64 \u2014 A finished feature is merged into main without waiting for approval \u2014 The user, message 17815 (2026-10-07): 'make sure that no pull requests are lingering on the repository. You may merge them into main... You are allowed to merge everything into main once the feature is completed.' This replaces rule 61's wait for approval: a feature still goes on its own branch, and once it is complete, tested and its whole suite passes, it is merged into main and released, and no pull request is left open.", "meta": {"from": "journal"}} {"content": "fact 23 \u2014 Every upgrade brings system sequences and their triggers in line\u2026 \u2014 install.py runs ship_sequences after the migrations on each upgrade, so features/sequences/shipped.py is the whole source: change its wording and the next upgrade updates every journal, no migration needed. Shipped rows carry system=True and are read-only for everyone but SYSTEM (controllers/base.py _shipped).", "meta": {"from": "journal"}} {"content": "fact 13 \u2014 This live session runs the installed copy in .journal/journal.pyz \u2014 The running journal (server, hooks, CLI) runs from .journal/journal.pyz with its viewer and skills in .journal/src, never from the repo. A change in the repo reaches it only through python3 src/journal.py --root .journal upgrade, which packs the zip again. A commit alone changes nothing that is running.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 68 stands still while todo 61 is ready \u2014 if work 68 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 61. Stop only when nothing ready is left.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 2 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 68 is still open, with nothing logged \u2014 journal work log 68 \"<what was decided or done, and why>\" \u2014 then journal work end 68 --how \"<what landed>\", or journal work park 68 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "law L6 \u2014 A journal line is an instruction, never a message - act on it and\u2026 \u2014 A line that starts with [journal], a reminder, a notice or an old helper report is the journal telling the agent what to do, not the user speaking. Answering it fills the user's chat with noise. Act on it, or note it and carry on; write in the chat only what the user needs to know, such as a failure, a finished piece of work or a decision that waits on them.", "meta": {"from": "journal"}} {"content": "rule 54 \u2014 Settings and feature switches are read at boot and on change, never\u2026 \u2014 The user, message 13349: the application boots, determines every feature and setting once, and re-evaluates only when something changes, such as a setting or a plugin. Never lazy-load settings.", "meta": {"from": "journal"}} {"content": "work 68 is still open \u2014 end it or park it before you stop: journal work end 68 --how \"<what landed>\", or journal work park 68 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "rule 48 \u2014 The viewer is built from its component library, and pages only\u2026 \u2014 Message 4258. Every visual piece the viewer shows more than once, or that a user would recognise as the same kind of thing (a dialog, a side panel or inspector, a dropdown, a list row, a switch, a button), is one component in web/src/kit, extracted aggressively, and every page composes those components instead of building its own copy. Before writing markup or styles in a page, look for the kit component that already does it and extend it with a prop; a second hand-built version is a bug. The side panel that animated in but not out, while a separate skill panel did both, is the example.", "meta": {"from": "journal"}} {"content": "work 68 is still open \u2014 end it or park it before you stop: journal work end 68 --how \"<what landed>\", or journal work park 68 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 2 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 2 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 61", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 61", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 61", "meta": {"from": "journal"}} {"content": "fact 25 \u2014 A designer's install packs the whole tree, half-done server edits\u2026 \u2014 2026-09-25: Eames and Saul run python3 src/journal.py --root .journal upgrade after their viewer builds; it packs every file in src, so a server handler I was halfway through writing went live and raised on every PostToolUse hook. While designers work in parallel, keep server edits whole between tool calls (write and test in the scratchpad first), and reinstall after reverting anything.; rule 27 \u2014 Name a declaration with the word a reader already knows \u2014 An attribute, a variable or a field gets the ordinary programming word for what it holds, not an evocative one. was, heard and alone were poetry; aliases, notify_actions and urgent_actions are what they are. The test: could a reader who has never seen this codebase guess what it holds from the name alone? Prose belongs in the help text and the abstract, where it is read as prose. This does not license abbreviations \u2014 a plain word in full, not a short one.", "meta": {"from": "journal"}} {"content": "rule 52 \u2014 A chat mark for something the user did sits on the user's side \u2014 Message 10960 (2026-09-25): marks for the user's own actions, such as answering a question, are right-aligned like the user's messages. A mark is put there by giving its card side=user.", "meta": {"from": "journal"}} {"content": "your answer to a journal line was kept out of the chat \u2014 a journal line is an instruction, not a message: act on it and write nothing, unless the user needs to know something such as a failure, finished work or a decision that waits on them", "meta": {"from": "journal"}} {"content": "work 69 is still open, with nothing logged \u2014 journal work log 69 \"<what was decided or done, and why>\" \u2014 then journal work end 69 --how \"<what landed>\", or journal work park 69 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "rule 57 \u2014 Never merge the overnight refactor into main before its pull request\u2026 \u2014 Messages 15005, 15006, 15109, 15110 (2026-10-04): all refactor work goes on branch overnight-refactor and reaches the user as one pull request, which they read in the morning; nothing of it is merged into main until they say so. Hotfixes the user explicitly asks for go to main at once and are merged into the branch.", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 3 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 3 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; work 70 is still open, with nothing logged \u2014 journal work log 70 \"<what was decided or done, and why>\" \u2014 then journal work end 70 --how \"<what landed>\", or journal work park 70 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "your wait for the six delivery test files is over, because you are working again \u2014 say journal work await \"<what you wait for>\" again if you are still only waiting", "meta": {"from": "journal"}} {"content": "work 70 is still open \u2014 end it or park it before you stop: journal work end 70 --how \"<what landed>\", or journal work park 70 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"nothing is waiting\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}} {"content": "check 3 failed - the same body is written 2 times, make it one funnel\u2026 \u2014 journal check show 3 says why; fix it, then journal check run 3", "meta": {"from": "journal"}} {"content": "check 5 failed - features/members/test.py -18 No module named 'tests' \u2014 journal check show 5 says why; fix it, then journal check run 5", "meta": {"from": "journal"}} {"content": "rule 66 \u2014 The journal never slows the agent down \u2014 The user, message 18990, after hooks timed out and waited on locks under load: the journal must never, ever decrease the performance of an agent. A hook answers at once with what decides the tool call; everything else runs after, in the background, and reaches the agent as a message. No hook waits on a lock it does not need.", "meta": {"from": "journal"}} {"content": "auto mode is on and work 71 stands still while todo 62 is ready \u2014 if work 71 waits on the user, decide it yourself when you can; otherwise put the question on its row with journal todo ask, end or park the work, and start todo 62. Stop only when nothing ready is left.; work 71 is still open, with nothing logged \u2014 journal work log 71 \"<what was decided or done, and why>\" \u2014 then journal work end 71 --how \"<what landed>\", or journal work park 71 \"<why it waits>\"", "meta": {"from": "journal"}} {"content": "Code Commandments \u2014 before you wrap up \u2014 you've changed 4 judged files since th\u2026 \u2014 Code Commandments \u2014 before you wrap up: you've changed 4 judged files since the last commit. Consider running `commandments judge --changes` to confirm they conform, and fix any sin at its SOURCE (don't launder a finding with a default/cast/null-check). This is a one-time nudge for this batch \u2014 if you've already judged, or these changes aren't worth a scan, just say so and carry on.; the log tag does this in one step \u2014 [!log:N] makes the turn itself the log entry; it runs only when it opens the last text of your turn", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 62", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 62", "meta": {"from": "journal"}} {"content": "chat etiquette - a line from the journal is an instruction, not a message\u2026 \u2014 a turn that only handles a journal line needs no words: act on it, or say once in the chat what you wait on, then carry on; what the user needs to know still goes to the chat", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 62", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 62", "meta": {"from": "journal"}} {"content": "waiting: 1 unread todo 62", "meta": {"from": "journal"}} {"content": "your chat talked about the journal's workings - \"nothing is pending\" \u2014 the user sees replies, reactions, pills and reads themselves; say what the work is instead", "meta": {"from": "journal"}}