agentleFS
Sign inStart free
juztripperjuztripper/already-looked/AGENTS.md

already-looked

AGENTS.md0 starsChanged 10 days agoMITView on GitHub

Two skills live in skills/naming and skills/branding. They're installed separately, so nothing in one may import from the other. Tests: - python3 -m unittest discover -s skills/naming/tests - Branding: run each file in skills/branding/tests/ with uv run if it has a # /// script block, otherwise python3. - python3 -m unittest discover -s evals/tests

  • 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 repository3 other files it gives its agents.

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Keep SKILL.md short and put detail in references/.

    line 6

≈ “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

Contributing as an agent

Two skills live in skills/naming and skills/branding. They're installed separately, so nothing in one may import from the other.

  • Platform notes live in shared/platforms/. Edit them there, then run python3 tools/sync_platforms.py.
  • Keep SKILL.md short and put detail in references/. Keep frontmatter to name, description, license, metadata: Codex's validator rejects anything else.
  • Naming scripts are stdlib only. Branding scripts are PEP 723 with pinned versions, run with uv run.
  • A surface that can't be read honestly returns UNKNOWN. No spoofed clients, no captcha bypass, no scraping what robots.txt disallows. Never write "cleared" or "safe".
  • research/ holds the sources behind the skills. A claim in a reference keeps its evidence label.
  • A change to how results are generated needs an eval: see evals/README.md.

Tests:

  • python3 -m unittest discover -s skills/naming/tests
  • Branding: run each file in skills/branding/tests/ with uv run if it has a # /// script block, otherwise python3.
  • python3 -m unittest discover -s evals/tests

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