About audit-agents
A document-audit skill for teams maintaining AGENTS.md files. It evaluates each line for lasting value, actionability, ownership, and iteration speed, then reports prioritized findings with quoted text and proposed replacements; edits are made only when requested.
Key features
- 01Audits AGENTS.md without builds or tests
- 02Assigns keep, rephrase, move, or delete verdicts
- 03Checks lines for durability and actionability
- 04Reviews document structure against an example
- 05Prioritizes quoted findings and replacements
Use cases
- 01Reviewing contributor guidance for lasting value
- 02Finding project-specific details in AGENTS.md
- 03Removing redundant or non-actionable rules
- 04Rewriting guidance when explicitly requested
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/audit-agentsin Claude Code to confirm it loaded.
Bundled filesassets/example-agents.md
Details
From the project READMEAudit Agents
AGENTS.md is read by everyone who will ever work on the project. Picture the next thousand contributors over the next hundred years: a line belongs only if it is still true, and still changes what they do, after every file, tool and dependency has been replaced.
Workflow
- Read the AGENTS.md and the root readme. This is a document audit: run no builds and no tests.
- Give every line one verdict, using the tests below.
- Keep: a principle that passes every test.
- Rephrase: a lasting lesson worded in today's mechanics, or too vague to act on.
- Move: a detail someone needs. Name the owner it belongs to: a readme, a manifest, a skill or a spec.
- Delete: repetition, history, or a line that changes nothing.
- Check the shape against the example below.
- Report the findings, highest impact first. Quote each line, give its verdict and the replacement text, and group repeats. Report no finding you can't quote.
- Edit only when the user asks for a rewrite. Then start from the example, write the file, and reread it as a newcomer with no history of this session.
Tests for a line
- A hundred years. No commands, flags, paths, file or function names, dependency choices, tuned values, plans, status or bug stories. Keep the lesson and move the mechanics to their owner. The one exception is a pointer to an owner (a readme or a skill), which exists so the detail can live there.
- A thousand people. A newcomer can act on it without knowing this session, this author or this month's work.
- Changes what they do. Delete a line a capable contributor already follows.
- Plain and concrete. A principle is not an abstraction. "Look at the picture" works; "match verification to the claim" doesn't. Prefer a short sentence with its consequence, and one example from the product over a general noun.
- Iteration speed. This is the core principle and must be stated outright: optimize the time to feedback you can trust, run the narrowest check that answers the question, and run everything once, when the spec's implementation is finished. Flag any rule that adds process to every loop, puts the full run before a commit, merge, push or finished feature, or names checkpoints for it along the way. The full run comes earlier only when the next piece of work can't be trusted without it. Never trade away a real acceptance requirement for speed.
Shape
assets/example-agents.md is an AGENTS.md any project can adopt, and it owns the section order. Read it before judging the shape or rewriting.
To adopt it, copy it and resolve every <…>; none may survive into the project's file.
<skill: name>names a skill from the pack this skill ships in. Replace it with a link to that skill where the project installs it. If the project doesn't have the skill, drop the pointer and keep the principle.<skill: the project's own …>stands for a skill only this project has. Link it, or delete the sentence.- Every other
<…>is filled from the project's readme.
Delete a section the project doesn't need; add one only for a principle that fits nowhere else.