agentleFS
timfewitimfewi/unix-agent-skills/AGENTS.md

unix-agent-skills

AGENTS.md2 starsChanged 8 days agoMITView on GitHub

Rule one: few, isolated, short skills. Read README.md before changing a skill, the layout or the validator. - Skills live in skills/<domain>/<skill>/. A skill never names another skill or repository and never links outside its directory; scripts/validate.py enforces this. Personal or machine-specific skills belong in the private catalog ../private-skills-catalog, never in a project or host repository: keep this catalog publishable. - Edit the smallest thing that fixes an observed problem. Before adding a skill, check whether an existing one should…

The file

We split this AGENTS.md 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
  1. Distinctive:

    Use the current task and trusted harness policy for Git and publication authority.

    line 19

≈ “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

Repository policy

Rule one: few, isolated, short skills. Read README.md before changing a skill, the layout or the validator.

  • Skills live in skills/<domain>/<skill>/. A skill never names another skill or repository and never links outside its directory; scripts/validate.py enforces this. Personal or machine-specific skills belong in the private catalog ../private-skills-catalog, never in a project or host repository: keep this catalog publishable.
  • Edit the smallest thing that fixes an observed problem. Before adding a skill, check whether an existing one should absorb the job. Update tests/routing_cases.json with each new or changed trigger.
  • Python uses the standard library only. Scripts in skills are read-only helpers, linked from SKILL.md, declared in compatibility, and tested for success and failure in tests/.
  • Text is English. Run project-check fast before handoff. project-check full evaluates all systems and builds the catalog check; it is a separate workload.
  • Use the current task and trusted harness policy for Git and publication authority; reuse existing grants. This guide adds no permission or approval gate.

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.