agentleFS
Sign inStart free
ccoalmccoalm/ccl-skills/hooks/AGENTS.md

ccl-skills / hooks

AGENTS.md6 starsChanged 3 months agoApache-2.0View on GitHub

Hooks are plugin-shipped runtime enforcement surfaces. Hosts may execute them on session start or tool use, so changes here are shared-skill behavior changes. - Keep hooks deterministic, fail-closed where safety requires it, and explicit about advisory versus blocking outcomes. - Do not read secrets or personal config unless the hook's contract documents why and how failures degrade. - Avoid broad filesystem mutation from hooks. - Non-wording changes require deterministic validation plus independent review and adversarial challenge before landing.

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:

    Keep hooks deterministic, fail-closed where safety requires it, and explicit about advisory versus blocking outcomes.

    line 8
  2. Common:

    Do not read secrets or personal config unless the hook's contract documents why and how failures degrade.

    line 10
  3. Distinctive:

    Avoid broad filesystem mutation from hooks.

    line 12

≈ “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

hooks Agent Contract

Hooks are plugin-shipped runtime enforcement surfaces. Hosts may execute them on session start or tool use, so changes here are shared-skill behavior changes.

Rules:

  • Keep hooks deterministic, fail-closed where safety requires it, and explicit about advisory versus blocking outcomes.
  • Do not read secrets or personal config unless the hook's contract documents why and how failures degrade.
  • Avoid broad filesystem mutation from hooks.
  • Non-wording changes require deterministic validation plus independent review and adversarial challenge before landing.

Validation:

  • bash skills/skill-extraction-workflow/scripts/check-ccl-skills.sh .
  • git diff --check

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