agentleFS
ViltrumlikViltrumlik/parallel-agents/snippets/AGENTS.md

parallel-agents / snippets

AGENTS.md1 starsChanged 8 days agoMITView on GitHub

Other coding agents may be working in this repository at the same time. Follow the parallel-agents protocol: If pa is not on the PATH, run python3 <path to the parallel-agents skill>/scripts/pa.py instead.

  • 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 repositoryOne other file it gives its agents.

The file

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

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the claim is blocked (exit code 3), do not edit those paths.

    line 7
  2. Very specific:

    Before each new batch of edits, run pa claim again for those paths.

    line 8
  3. Very specific:

    When you finish, leave a note with pa note "<what changed, what is left>" --as <name>, then release with pa release --as <name>.

    line 9
  4. Very specific:

    If pa is not on the PATH, run python3 <path to the parallel-agents skill>/scripts/pa.py instead.

    line 11

≈ “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

Parallel agents

Other coding agents may be working in this repository at the same time. Follow the parallel-agents protocol:

  1. At the start, pick a unique name such as claude-7f2c or codex-a91e, run pa status, and read pa log.
  2. Before editing any file, claim it: pa claim <files or folders> --as <name> --why "<what you are doing>". Claim @migrations, @deps or @port:<n> before running migrations, changing dependencies or starting a server.
  3. If the claim is blocked (exit code 3), do not edit those paths. Work on something else, or ask the user. Exit code 2 means the command was wrong and nothing was claimed: fix it before editing.
  4. Before each new batch of edits, run pa claim again for those paths. It is free for paths you hold and keeps your claims from expiring.
  5. When you finish, leave a note with pa note "<what changed, what is left>" --as <name>, then release with pa release --as <name>.

If pa is not on the PATH, run python3 <path to the parallel-agents skill>/scripts/pa.py instead.

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.