agentleFS
CE0AlexCE0Alex/skill-hunter/AGENTS.md

skill-hunter

AGENTS.md21 starsChanged 9 months agoMITView on GitHub

Guidance for agents working on the skill-hunter repo.

  • 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 31,542 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. Very specific:

    Keep SKILL.md focused on discovery and decision rules.

    line 24
  2. Distinctive:

    Always update README.md when modifying workflow or install guidance.

    line 26
  3. Very specific:

    When the Skills CLI README changes, update references/agent-skills.md and references/installation.md first.

    line 27
  4. Very specific:

    Ensure new references are linked from SKILL.md (progressive disclosure).

    line 32

≈ “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

AGENTS.md

Guidance for agents working on the skill-hunter repo.

Project Overview

Skill Hunter is a meta-skill that discovers new external skills for a project, evaluates them, and installs only after user confirmation.

Key Files

  • SKILL.md – core workflow and rules (keep lean; link to references for details)
  • README.md – user-facing docs and install instructions
  • references/installation.md – per-agent install guidance (load only after confirmation)

Common Commands

# Package the skill (avoid including .git or dist)
python3 ~/.codex/skills/.system/skill-creator/scripts/package_skill.py /path/to/skill-hunter /path/to/dist

# Sync global installs (Codex + Claude Code)
cp -R /path/to/skill-hunter ~/.codex/skills/skill-hunter
cp -R /path/to/skill-hunter ~/.claude/skills/skill-hunter

Change Guidelines

  • Keep SKILL.md focused on discovery and decision rules; move heavy install details to references/installation.md.
  • Preserve "external-only recommendations" and search-matrix requirements.
  • Always update README.md when modifying workflow or install guidance.
  • When the Skills CLI README changes, update references/agent-skills.md and references/installation.md first.
  • After any content change, rebuild the dist package so dist/skill-hunter.skill stays in sync with the source files.

Quick Verification

  • Confirm SKILL.md still uses only name and description in YAML frontmatter.
  • Ensure new references are linked from SKILL.md (progressive disclosure).

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.