agentleFS
Sign inStart free
AlenroyfeildAlenroyfeild/ai-dev-workspace/AGENTS.md

ai-dev-workspace

AGENTS.md0 starsChanged 26 days agoMITView on GitHub

  • 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 repository9 other files it gives its agents.

The file

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

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every invariant gets a test and every bug a regression test that fails before the fix.

    line 5
  2. Very specific:

    Commit messages: a title, then Problem:, Cause: (one bullet per cause), Fix: and Verified: (only what was actually run).

    line 8

≈ “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 ai-dev-workspace

  • Tests: python3 -m unittest discover -s tests (no network, no model calls). Run the focused tests for what you changed and rely on full CI (the full suite runs weekly as a sanity check); name the command and the result.
  • Code: standard library only in ws/ and mcp/, Python 3.9+. One implementation in ws/core.py (or a small module next to it); the CLI and MCP server call it.
  • Every invariant gets a test and every bug a regression test that fails before the fix.
  • Packs and docs are public: no company, customer or personal details, paths or credentials. See CONTRIBUTING.md and docs/PACKS.md.
  • Docs: short sentences, exact commands, no claim without a way to check it. User-facing changes get a CHANGELOG line under the unreleased version.
  • Commit messages: a title, then Problem:, Cause: (one bullet per cause), Fix: and Verified: (only what was actually run); no Co-Authored-By trailer.
  • Pull requests target dev. Never push to someone else's branch; never merge your own PR.

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