agentleFS
Sign inStart free
hieusatshieusats/pstack/AGENTS.md

pstack

AGENTS.md4 starsChanged 2 months agoMITView on GitHub

Read UPSTREAM.md before touching anything under skills/ or agents/. This repo is a fork of Cursor's pstack for pi: upstream content is ported deliberately, own development is expected, and the divergence inventory in UPSTREAM.md is the source of truth for how this tree differs.

  • 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 31,700 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

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Read UPSTREAM.md before touching anything under skills/ or agents/.

    line 3
  2. Very specific:

    Every deliberate change gets a CHANGES.md entry in the same commit.

    line 8
  3. Very specific:

    Keep changes small. Ship the shortest diff that solves the problem, and keep each CHANGES.md entry to a sentence or two, with evidence in …

    line 9
  4. Very specific:

    Before opening a pull request, run the checks that exist for this tree: python3 scripts/verify.py, the markdown advisory, pi list, and the …

    line 10
  5. Distinctive:

    Do not add an implicit runtime timeout or a weaker-model fallback.

    line 13

≈ “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

pstack

Read UPSTREAM.md before touching anything under skills/ or agents/. This repo is a fork of Cursor's pstack for pi: upstream content is ported deliberately, own development is expected, and the divergence inventory in UPSTREAM.md is the source of truth for how this tree differs.

  • Pi is the only distribution target. Do not add harness manifests, tool-mapping layers, or skill rewrites for other agents.
  • Upstream sync follows UPSTREAM.md: port intent into our shape, skip Cursor-product-specific content, record every skip or contradiction in the divergence inventory.
  • Own development follows UPSTREAM.md "Own development": one deliberate change per commit, Agent Skills standard frontmatter, inventory updated when it contradicts an upstream variant.
  • Every deliberate change gets a CHANGES.md entry in the same commit. NOTICE.md and LICENSE are the provenance records; keep them truthful when sources change.
  • Keep changes small. Ship the shortest diff that solves the problem, and keep each CHANGES.md entry to a sentence or two, with evidence in the pull request.
  • Before opening a pull request, run the checks that exist for this tree: python3 scripts/verify.py, the markdown advisory, pi list, and the UPSTREAM.md verification probes. CI runs the same script on every push and pull request.
  • Nothing merges, tags, releases, or rolls out until the exact candidate is installed and the changed behavior passes a live test from a real pi session. Unit checks, validators, source inspection, and self-reports do not satisfy this gate. Record the installed version, surface, action, and observed result in the pull request template. A pull request without that evidence remains a draft.
  • GitHub release titles are the bare tag name (v0.1.2), no trailing description. Release notes come from the matching CHANGES.md section.
  • Do not add an implicit runtime timeout or a weaker-model fallback.
  • Edit tracked markdown through the edit tool. No sed -i, perl -i, or ad-hoc script rewrites.
  • pi config can disable individual skills from this package; prefer that over deleting a skill locally.

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