agentleFS
Sign inStart free
AgriciDanielAgriciDaniel/gatekeeper/AGENTS.md

gatekeeper

AGENTS.md18 starsChanged 50 days agoMITView on GitHub

Read SKILL.md, then README.md, then the rulebook you are touching in gates/. - Code owns the workflow. Jev answers only the semantic questions a rule cannot. - Thresholds live in rulebooks, never in Python. Move one only with a bench report over hand-reviewed labels, and bump the rulebook version. - Gatekeeper decides who handles work and whether it may proceed. It never takes outside actions (send, publish, deploy, spend) itself. - Hooks must fail open and must never break a…

  • Reads credentials
  • 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 repository2 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, 0 are distinctive, and 2 are 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.

  • 2

    Very specific

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

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

    Read SKILL.md, then README.md, then the rulebook you are touching in gates/.

    line 3
  2. Very specific:

    Never print or store TYPESAFE_API_KEY.

    line 13

≈ “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

Gatekeeper Agent Instructions

Read SKILL.md, then README.md, then the rulebook you are touching in gates/.

Rules

  • Code owns the workflow. Jev answers only the semantic questions a rule cannot.
  • Thresholds live in rulebooks, never in Python. Move one only with a bench report over hand-reviewed labels, and bump the rulebook version.
  • Gatekeeper decides who handles work and whether it may proceed. It never takes outside actions (send, publish, deploy, spend) itself.
  • Hooks must fail open and must never break a session.
  • Never print or store TYPESAFE_API_KEY. The log stores a prompt hash and a short excerpt, never the full prompt.
  • Installing hooks into ~/.claude/settings.json (global) needs the user's explicit approval. Project installs start in shadow mode.

Verification

python3 -m pytest -q
bin/gatekeeper lint agent-selection
bin/gatekeeper lint marketing-team
bin/gatekeeper bench marketing-team    # live; needs the key (your own gate: add a bench file)

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