agentleFS
Sign inStart free
KyaniteLabsKyaniteLabs/tastecheck/AGENTS.md

tastecheck

AGENTS.md12 starsChanged 11 days agoMITView on GitHub

Brief for coding agents working on this repository (not for agents using the skills).

The file

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

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

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Do not hand-edit generated marker blocks (<!-- release-facts:v1:start -->, <!-- release-status:v1:start -->, and their end markers).

    line 28
  2. Distinctive:

    Never add unsupported effectiveness claims.

    line 29
  3. Common:

    No secrets or machine-specific paths in committed files.

    line 30
  4. Distinctive:

    Do not commit or change git state unless asked.

    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

Brief for coding agents working on this repository (not for agents using the skills).

Layout

  • skills/<name>/SKILL.md + contract.json: the 20 skills
  • commands/*.md: Claude Code slash commands (20 plus the /darkmode alias)
  • tools/: verification, release, calibration and eval scripts
  • tools/release/release-facts.json: the single source for the released inventory
  • evals/corpus/, evals/calibration/: labeled test cases and measured error counts
  • samples/, demos/, index.html: gallery and landing page
  • docs/: verification notes and launch copy

Commands

npm ci
npm test                      # full suite
npm run test:structural       # faster structural suite
node tools/verify.mjs
npm run release:inventory     # checks generated inventory blocks
node tools/release/check-effectiveness-claims.mjs

Rules

  • Do not hand-edit generated marker blocks (<!-- release-facts:v1:start -->, <!-- release-status:v1:start -->, and their end markers). Edit the source and run node tools/release/project-facts.mjs --write. Release status is projected by npm run finalize.
  • Never add unsupported effectiveness claims. Effectiveness is BLOCKED; state measured numbers with their scope.
  • No secrets or machine-specific paths in committed files.
  • Taste data is user-local and must not be committed.
  • Do not commit or change git state unless asked.

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