agentleFS
Sign inStart free
mwnickersonmwnickerson/skills/AGENTS.md

skills

AGENTS.md1 starsChanged 3 months agoMITView on GitHub

Maintain an identity-neutral, installable Codex marketplace of portable custom skills and agents. Do not add capabilities already shipped by default with Codex or Google Workspace connector workflows. - Never add a person's name, username, handle, email address, employer, client, private organization, domain, host, network identifier, or machine-specific absolute path. - Do not copy credentials, authentication state, sessions, vault content, memory, engagement data, personal projects, or Git identity metadata. - Use repository-relative paths and explicit placeholders for runtime inputs. - Keep…

  • 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

8 rules. About 1 is common, 7 are distinctive, and 0 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Never add a person's name, username, handle, email address, employer, client, private organization, domain, host, network identifier, or …

    line 11
  2. Common:

    Do not copy credentials, authentication state, sessions, vault content, memory, engagement data, personal projects, or Git identity …

    line 14
  3. Distinctive:

    Use repository-relative paths and explicit placeholders for runtime inputs.

    line 16
  4. Distinctive:

    Keep fixtures synthetic and organization-neutral.

    line 17
  5. Distinctive:

    Do not copy source prose from proprietary or provider-owned plugins.

    line 18
  6. Distinctive:

    Keep provider authentication and third-party installation outside repository generation.

    line 34
  7. Distinctive:

    Add narrowly focused plugins instead of widening unrelated install bundles.

    line 36
  8. Distinctive:

    Run the official plugin validator against every plugin when it is available on the current host.

    line 49

≈ “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 Instructions

Purpose

Maintain an identity-neutral, installable Codex marketplace of portable custom skills and agents. Do not add capabilities already shipped by default with Codex or Google Workspace connector workflows.

Privacy boundary

  • Never add a person's name, username, handle, email address, employer, client, private organization, domain, host, network identifier, or machine-specific absolute path.
  • Do not copy credentials, authentication state, sessions, vault content, memory, engagement data, personal projects, or Git identity metadata.
  • Use repository-relative paths and explicit placeholders for runtime inputs.
  • Keep fixtures synthetic and organization-neutral.
  • Do not copy source prose from proprietary or provider-owned plugins. Write original routing instructions and preserve provider boundaries.

Source of truth

  • manifest/skills.json, manifest/agents.json, manifest/plugins.json, and templates/SKILL.md are canonical.
  • .agents/, catalog/, and plugins/ are generated by scripts/generate_repository.py and must not be edited by hand.
  • Each skill and agent has exactly one canonical plugin owner.
  • Agent prompts must not assume a model entitlement, private permission profile, host alias, fixed provider, personal memory system, or external tracker.

Change control

  • Preserve unrelated work and review the complete diff before staging.
  • Keep provider authentication and third-party installation outside repository generation.
  • Add narrowly focused plugins instead of widening unrelated install bundles.
  • Re-run generation after source changes and remove stale generated artifacts.

Validation

Run before committing:

python3 scripts/generate_repository.py --check
python3 scripts/validate_repository.py
git diff --check

Run the official plugin validator against every plugin when it is available on the current host. Publication still requires a manual contextual privacy review.

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