agentleFS
Sign inStart free
ragnos-labsragnos-labs/skill-index/records/AGENTS.md

skill-index / records

AGENTS.md0 starsChanged 3 months agoMITView on GitHub

Each JSON file describes one skill or domain. Records are maintained inputs; generated indexes are projections. Run make index and make check after changing records.

The file

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

5 rules. About 0 are common, 0 are distinctive, and 5 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.

  • 5

    Very specific

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

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

    Use one file at records/skills/<skill-name>.json.

    line 8
  2. Very specific:

    Keep name, folder name, frontmatter name, and path aligned.

    line 9
  3. Very specific:

    Use active, experimental, or deprecated lifecycle status.

    line 10
  4. Very specific:

    Use bootstrap, routable, explicit, or retired load mode.

    line 11
  5. Very specific:

    Run make index and make check after changing records.

    line 23

≈ “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

Record instructions

Each JSON file describes one skill or domain. Records are maintained inputs; generated indexes are projections.

Skill records

  • Use one file at records/skills/<skill-name>.json.
  • Keep name, folder name, frontmatter name, and path aligned.
  • Use active, experimental, or deprecated lifecycle status.
  • Use bootstrap, routable, explicit, or retired load mode.
  • State concise positive triggers and exclusions that improve routing.
  • Optional aliases add exact human phrases; optional scope_terms require domain evidence for broad queries. Exact names remain discoverable. Exclusions accompany candidates for agent judgment.
  • Reference external evidence as <packet-id>:<source-id>.
  • Active records require a current review receipt.

Domain records

  • Use one file at records/domains/<domain-name>.json.
  • Domain documentation lives below domains/<domain-name>/.
  • An active domain must contain at least one active skill.

Run make index and make check after changing records.

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