docs-upkeep
Skill0 starsChanged 15 days agoMITView on GitHub
Update AGENTS.md, the decision log, the architecture doc and the runbook after a change. Use at the end of each task.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/CLAUDE.mdCLAUDE.md
- a11y-auditSkill
- architecture-reviewSkill
- bootstrap-projectSkill
- capture-screenshotsSkill
- customizeSkill
- deliver-featureSkill
- design-reviewSkill
- fix-bugSkill
- handoffSkill
- implementSkill
- leadSkill
- log-decisionSkill
- refine-requirementsSkill
- release-readinessSkill
- reproduce-in-worktreeSkill
- security-auditSkill
- ship-prSkill
- start-taskSkill
- sync-branchSkill
- threat-modelSkill
- verify-featureSkill
- vet-dependencySkill
- write-adrSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Look at the diff and the conversation, then update each doc that's affected.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Docs upkeep
Playbook files named here: when the project has its own copy at
.playbook/local/<same path>, use that copy instead.
Look at the diff and the conversation, then update each doc that's affected. Skip a doc only when nothing in it changed.
| If the change… | Update |
| Adds or changes a rule someone must follow when coding (a convention, a helper to use, a "never do X") | AGENTS.md: one bullet in the right section, with the code path. Keep it operational, with no history. |
| Involved a decision (product from the owner, technical, process, an accepted risk) | Decision Log: a row at the top of the right section: date, bold summary, why, source. Name the owner for product decisions. |
| Adds or changes a table, column, flow, job, function or integration | Architecture & Data Model: the schema line, a flow diagram (text), "built" with ticket and PR |
| Hit a trap (a tool behaved surprisingly, a command needed a flag, something cost over 10 minutes) | Developer Runbook: a "Traps already hit" row (trap → fix with commands), or a new how-to section |
| Changes setup, env vars or commands | README and the runbook's local loop |
| Is a hard-to-reverse choice | ADR via write-adr |
| Completes or advances a ticket | Ticket: status, PR link, and a comment with what was done, the verification, and anything not verified |
How
- Where the docs live and how to edit them safely is in
AGENTS.md→ "Tracker": Linear documents, Confluence pages,docs/in the repo, Notion, …. Follow its editing notes, such as anchors without ticket ids in Linear, or the page version number in Confluence. Patch small sections instead of rewriting whole documents. - Repo docs change in the same commit as the code.
- Plain language, concrete names, links to code paths, tickets and PRs. One home per fact: link, don't copy.
Report which docs you updated and which you checked and left unchanged.
Rules: ${CLAUDE_PLUGIN_ROOT}/principles/12-documentation-knowledge.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

