agentleFS
Sign inStart free
andrasatandrasat/pi-llm-self-verify/AGENTS.md

pi-llm-self-verify

AGENTS.md0 starsChanged 3 months agoMITView on GitHub

This repository is a small, dependency-free Pi package. Read README.md before changing behavior. - extensions/self-verify.ts is the Pi entry point. - src/self-verify.ts contains the testable workflow, prompt, tournament, and OpenAI-compatible/Vertex logprob clients. - skills/self-verify/SKILL.md teaches the agent when to call the tool. - Pi loads TypeScript directly; there is no build output to commit. 1. Keep candidate generation read-only: candidate subprocesses may inspect the project but must not write, execute shell commands, commit, or push. 2. Keep the verifier as…

  • Installs packages
  • 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 31,774 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, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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
  1. Distinctive:

    Keep candidate generation read-only: candidate subprocesses may inspect the project but must not write, execute shell commands, commit, or …

    line 16
  2. Distinctive:

    Keep the verifier as a selection aid, never as a test, review, release, or issue-close gate.

    line 18
  3. Very specific:

    Do not log API keys. Keep provider secrets in environment/Pi auth, not project settings.

    line 20
  4. Distinctive:

    Keep the public package surface small and avoid new runtime dependencies.

    line 21

≈ “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

Agent instructions

This repository is a small, dependency-free Pi package. Read README.md before changing behavior.

Shape

  • extensions/self-verify.ts is the Pi entry point.
  • src/self-verify.ts contains the testable workflow, prompt, tournament, and OpenAI-compatible/Vertex logprob clients.
  • skills/self-verify/SKILL.md teaches the agent when to call the tool.
  • Pi loads TypeScript directly; there is no build output to commit.

Workflow

  1. Keep candidate generation read-only: candidate subprocesses may inspect the project but must not write, execute shell commands, commit, or push.
  2. Keep the verifier as a selection aid, never as a test, review, release, or issue-close gate.
  3. Do not log API keys. Keep provider secrets in environment/Pi auth, not project settings. Run npm run check before handing off a change.
  4. Keep the public package surface small and avoid new runtime dependencies.
  5. Changes to prompts, scoring, or artifact paths need focused tests and a README update when user-visible behavior changes.

Commands

npm install
npm run check
npm test
npm run typecheck

Release check

package.json is the Pi package manifest. Test a local install with:

pi install /absolute/path/to/pi-llm-self-verify

For a published/tagged release, use:

pi install git:github.com/andrasat/pi-llm-self-verify@<tag>

Release only after npm run check, a clean package dry run, a pushed commit, and a pushed v0.1.0 tag. npm publish --access public is optional; Pi can install the tagged Git package directly.

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