agentleFS
Sign inStart free
AmitSinghOMAmitSinghOM/agent-skills/AGENTS.md

agent-skills

AGENTS.md0 starsChanged 2 months agoMITView on GitHub

Guidance for coding agents working in or with this repository. - Load a skill only when its description matches the task. Descriptions are written as "use when …" triggers on purpose. - code-quality-gate runs external tools (git, python3, cqa-analyzer). If the analyzer is missing the wrapper exits 3 with an install hint — relay that to the user. Never report findings you did not obtain from a real run. - source-grounded-claims applies to your own output. If you cite a…

  • 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 31,774 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 repository4 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every skill ships evals/scenarios.json with at least three scenarios and at least one mode: static (tool-free) scenario.

    line 21
  2. Distinctive:

    Before proposing a change, run and paste the output of:

    line 26
  3. Distinctive:

    Do not add a skill that is only a prompt.

    line 33
  4. Distinctive:

    Do not add anything referencing an employer's internal systems.

    line 35

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

Guidance for coding agents working in or with this repository.

If you are using these skills

  • Load a skill only when its description matches the task. Descriptions are written as "use when …" triggers on purpose.
  • code-quality-gate runs external tools (git, python3, cqa-analyzer). If the analyzer is missing the wrapper exits 3 with an install hint — relay that to the user. Never report findings you did not obtain from a real run.
  • source-grounded-claims applies to your own output. If you cite a source, you opened it. If you did not, say unverified and keep confidence below 80%.

If you are changing this repository

  1. One directory per skill under skills/. name in the frontmatter must equal the directory name. Frontmatter keys are limited to the spec set (name, description, license, compatibility, metadata, allowed-tools); anything else goes under metadata.
  2. Every skill ships evals/scenarios.json with at least three scenarios and at least one mode: static (tool-free) scenario. Scenarios describe observable behaviour, not vibes.
  3. Scripts are standard-library only and must fail loudly with an actionable message. No network calls.
  4. Before proposing a change, run and paste the output of:
    python3 scripts/validate.py && python3 -m unittest discover -s tests
    Both must pass. CI runs the same two commands.
  5. Bump metadata.version in the skill you changed and version in .claude-plugin/plugin.json when behaviour changes.
  6. Do not add a skill that is only a prompt. A skill earns a slot here by being backed by a runnable tool or by scenarios that have actually been exercised.
  7. Do not add anything referencing an employer's internal systems. This repository is public.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free