agentleFS
Sign inStart free
jacksnxlyjacksnxly/keryx/AGENTS.md

keryx

AGENTS.md0 starsChanged 16 days agoMITView on GitHub

These rules apply equally to AGENTS.md and CLAUDE.md. Keep both files identical. Unit tests make no model calls. Live tests run only with KERYX_LIVE=1.

  • Installs packages
  • 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 repository4 other files it gives its agents.

The file

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

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

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    No committed file names an external skill pack.

    line 12
  2. Distinctive:

    Never push, tag or open a PR without the owner's explicit go.

    line 15
  3. Common:

    Never print or store credentials.

    line 17

≈ “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 Agent Instructions

These rules apply equally to AGENTS.md and CLAUDE.md. Keep both files identical.

What lives here

  • bench/ — the replay benchmark (Python package keryx_bench).
  • docs/design/ — designs; docs/plans/ — implementation plans; docs/bench/ — published benchmark summaries (aggregate numbers only).

Rules

  • No committed file names an external skill pack.
  • Private data never enters the repo: cases, system files, results and provenance live in ~/.config/keryx/ and ~/.local/share/keryx/.
  • Commits follow Conventional Commits, never name an AI assistant or tool, and carry no co-author trailers. Stage files by name.
  • Never push, tag or open a PR without the owner's explicit go.
  • Dependencies: latest versions via uv pip install, pinned in bench/requirements.txt to the installed version.
  • Never print or store credentials.

Tests

cd bench && .venv/bin/pytest -q

Unit tests make no model calls. Live tests run only with KERYX_LIVE=1.

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