agentleFS
Sign inStart free
backnotpropbacknotprop/product-engineering/AGENTS.md

product-engineering

AGENTS.md8 starsChanged 3 months agoApache-2.0View on GitHub

This repository vendors other authors' writing byte-for-byte and proves it with hashes. Most files here are not editable, even to fix a typo. Before touching ANY file, look it up in foundry/MANIFEST.json. 1. Never retype vendored content. Bytes enter this repo only through foundry/scripts/lift.sh. If you find yourself reproducing text from an upstream repo in your own output, stop — run the script instead. 2. Locked files are never edited. Classes verbatim, verbatim-minus, and distilled are hash-locked; CI fails on…

  • 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 31,542 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 repository2 other files it gives its agents.

The file

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

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No text you author may contradict an active ruling.

    line 21
  2. Very specific:

    Verify before any PR: foundry/scripts/check-integrity.sh must pass.

    line 31
  3. Very specific:

    Never commit anything under skills/*/references/course/ — purchased content, gitignored by design.

    line 33

≈ “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 — the fence

This repository vendors other authors' writing byte-for-byte and proves it with hashes. Most files here are not editable, even to fix a typo. Before touching ANY file, look it up in foundry/MANIFEST.json.

The five rules

  1. Never retype vendored content. Bytes enter this repo only through foundry/scripts/lift.sh. If you find yourself reproducing text from an upstream repo in your own output, stop — run the script instead.
  2. Locked files are never edited. Classes verbatim, verbatim-minus, and distilled are hash-locked; CI fails on one changed character. If a change seems needed, propose it: a re-lift (upstream changed), a ledger ruling (we disagree with the content), or an upstream PR (the content has a bug). Never edit in place.
  3. Every change is a logged event. Append one line to foundry/LOG.md for any provenance-changing action. Scripts log their own actions. Never edit existing lines.
  4. Upstream drift is classified, never auto-merged. You may draft re-lift PRs and drift issues; only a human merges. See the runbooks.
  5. The ledger is law. foundry/LEDGER.md holds the contradiction rulings (L-01…). No text you author may contradict an active ruling. Changing a ruling is a new superseding entry, never a silent edit.

Where the full process lives

The foundry skill — .claude/skills/foundry/SKILL.md — carries the methodology (grading, spine + byte-preserved references, anti-slop gates) and seven runbooks (lift, re-lift, distill refresh, new ruling, integrity failure, course drop-in, new skill/upstream). Load it before doing any convergence or maintenance work.

Verify before any PR: foundry/scripts/check-integrity.sh must pass.

Never commit anything under skills/*/references/course/ — purchased content, gitignored by design. The one tracked exception is each course folder's README.md, which documents the drop-in.

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