agentleFS
qengine13qengine13/forge-skills/AGENTS.md

forge-skills

AGENTS.md1 starsChanged 8 days agoApache-2.0View on GitHub

Preserve the behaviour contracts and source attribution. Keep examples fictional and self-contained. Never publish local credentials, project memories, session transcripts, or private configuration. Do not modify any external source collection while editing this public edition. Read docs/release/preflight.md before changing scope. Model names belong in runtime discovery, not fixed routing tables. Respect the user's subscription and explicit model choices. Run python3 -m unittest discover -s tests -v and the package validation before publishing. Report structural checks, behaviour evaluation, hosted checks, and…

  • 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 32,671 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 repository7 other files it gives its agents.

The file

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

5 rules. About 1 is common, 2 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Common:

    Never publish local credentials, project memories, session transcripts, or private configuration.

    line 4
  2. Distinctive:

    Do not modify any external source collection while editing this public edition.

    line 5
  3. Very specific:

    Read docs/release/preflight.md before changing scope.

    line 7
  4. Very specific:

    Run python3 -m unittest discover -s tests -v and the package validation before publishing.

    line 10
  5. Distinctive:

    Use independent scenario evaluation when changing skill behaviour.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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

Working on Forge Skills

Preserve the behaviour contracts and source attribution. Keep examples fictional and self-contained. Never publish local credentials, project memories, session transcripts, or private configuration. Do not modify any external source collection while editing this public edition.

Read docs/release/preflight.md before changing scope. Model names belong in runtime discovery, not fixed routing tables. Respect the user's subscription and explicit model choices.

Run python3 -m unittest discover -s tests -v and the package validation before publishing. Report structural checks, behaviour evaluation, hosted checks, and public access separately. Use independent scenario evaluation when changing skill behaviour; pass raw tasks, not desired answers.

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.