doc_mcp
AGENTS.md0 starsChanged 3 months agoMITView on GitHub
For any development task where non-blocking issues are found but intentionally deferred, always apply the tech-debt skill to record debt in tech-debt/<YYYY-MM-DD>.md. For any explicit user request to create a commit, always apply the commiter skill. For any documentation audit or documentation change, apply the check-documentation-gaps and docs-guardian skills as applicable. For any test creation, update, or review involving scenario documentation, apply the test-scenario-guardian skill.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository12 other files it gives its agents.
- backend-doc-syncSkill
- check-documentation-gapsSkill
- check-test-gapsSkill
- commiterSkill
- docs-guardianSkill
- monthly-doc-actualizerSkill
- release-note-writerSkill
- story-checkSkill
- story-guardianSkill
- story-updateSkill
- tech-debtSkill
- test-scenario-guardianSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
check-documentation-gaps: Audit documentation against the current implementation.
- Very specific: line 14
check-test-gaps: Audit behavior coverage and test gaps.
- Very specific: line 21
test-scenario-guardian: Keep scenario documentation synchronized with automated verification.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS
Default Skill
For any development task where non-blocking issues are found but intentionally deferred, always apply the tech-debt skill to record debt in tech-debt/<YYYY-MM-DD>.md.
For any explicit user request to create a commit, always apply the commiter skill.
For any documentation audit or documentation change, apply the check-documentation-gaps and docs-guardian skills as applicable.
For any test creation, update, or review involving scenario documentation, apply the test-scenario-guardian skill.
Skills
- backend-doc-sync: Enforce documentation synchronization for backend Python changes. Invoke as
$backend-doc-sync. (file:.agents/skills/backend-doc-sync/SKILL.md) - check-documentation-gaps: Audit documentation against the current implementation; use
$check-documentation-gaps fixto authorize fixes. (file:.agents/skills/check-documentation-gaps/SKILL.md) - check-test-gaps: Audit behavior coverage and test gaps; use
$check-test-gaps fixto authorize fixes. (file:.agents/skills/check-test-gaps/SKILL.md) - docs-guardian: Standardize and review repository documentation. Invoke as
$docs-guardian. (file:.agents/skills/docs-guardian/SKILL.md) - monthly-doc-actualizer: Run documentation freshness checks and actualization. Invoke as
$monthly-doc-actualizer. (file:.agents/skills/monthly-doc-actualizer/SKILL.md) - release-note-writer: Draft user-facing release notes. Invoke as
$release-note-writer. (file:.agents/skills/release-note-writer/SKILL.md) - story-guardian: Standardize and review stories. Invoke as
$story-guardian. (file:.agents/skills/story-guardian/SKILL.md) - story-check: Compare GitHub stories with the current implementation. Invoke as
$story-check. (file:.agents/skills/story-check/SKILL.md) - story-update: Refresh implementation stories from the current repository solution. Invoke as
$story-update. (file:.agents/skills/story-update/SKILL.md) - test-scenario-guardian: Keep scenario documentation synchronized with automated verification. Invoke as
$test-scenario-guardian. (file:.agents/skills/test-scenario-guardian/SKILL.md) - tech-debt: Capture deferred technical debt items into dated markdown files under
tech-debt/. (file:.agents/skills/tech-debt/SKILL.md) - commiter: Create commit/push flow with standardized commit message format on explicit commit requests. (file:
.agents/skills/commiter/SKILL.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.

