agentleFS
seankoji-comseankoji-com/.agents/AGENTS.md

.agents

AGENTS.md2 starsChanged 9 days agoMITView on GitHub

Read README.md and the relevant skills/<name>/SKILL.md. Keep each skill independently usable, with name/description metadata, clear triggers and an entrypoint under 1,500 words. Supporting references, templates and helpers belong inside that skill. Prefer native tools. Do not introduce a launcher, runtime engine, model registry, provider SDK or second scheduler. Exceptional helpers must be relocatable, Python 3.10+ and stdlib-only, with meaningful behavior and relocation tests. Inspect the tree and preserve unrelated work. Stage explicit paths and inspect the staged diff before committing.…

  • Reads credentials

The file

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

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Read README.md and the relevant skills/<name>/SKILL.md.

    line 3
  2. Distinctive:

    Prefer native tools. Do not introduce a launcher, runtime engine, model registry, provider SDK or second scheduler.

    line 7
  3. Distinctive:

    Keep the repository-only direct-publish exceptions narrow.

    line 28

≈ “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

Working on .agents

Read README.md and the relevant skills/<name>/SKILL.md. Keep each skill independently usable, with name/description metadata, clear triggers and an entrypoint under 1,500 words. Supporting references, templates and helpers belong inside that skill.

Prefer native tools. Do not introduce a launcher, runtime engine, model registry, provider SDK or second scheduler. Exceptional helpers must be relocatable, Python 3.10+ and stdlib-only, with meaningful behavior and relocation tests.

Inspect the tree and preserve unrelated work. Stage explicit paths and inspect the staged diff before committing. Fixtures must use synthetic data, never credentials, private transcripts, machine paths or private hostnames.

Run python3 scripts/check_library.py and python3 -m unittest discover -s tests -v. Tests must not call live models or mutate GitHub. Run changed skill helpers from a foreign working directory. Keep mandatory organization workflows; no package or documentation build is needed.

Owner maintenance publishes by fast-forward pushes to main. Do not create pull requests for this repository. Use python3 scripts/maintain.py check for validation alone. The default command generates a commit message, commits, pushes and delivers to configured hosts only within existing publication authority. Before publishing or syncing, follow README.md's owner-maintenance setup for the repository-local .env. Keep personal destinations and config backups untracked; use synthetic values in the checked-in .env.example and fixtures. Checks and hooks need no local host configuration. Keep the repository-only direct-publish exceptions narrow; never force-push.

Dotfiles owns external configuration. Preserve installed skills, active jobs, credentials, ignored settings and marketplace state. The README is the reference documentation. site/index.html is the user-facing GitHub Pages site; keep its skill list and plain-language copy in step with skill changes. Report local checks, hosted CI, review, merge, deployment and fresh-session acceptance separately.

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.