agentleFS
Sign inStart free
Industrial-AI-Research-LabIndustrial-AI-Research-Lab/nir-agent-overlay/AGENTS.md

nir-agent-overlay

AGENTS.md0 starsChanged 45 days agoMITView on GitHub

These instructions apply on top of the project's own AGENTS.md; the project's file wins on conflict. Rules by topic are in rules/, skills in skills/. 1. Start from a fresh main: branch <type>/<short-description>, types feat, fix, refactor, docs, test, chore, exp. One branch per change. 2. Small steps. Run make check after edits and before finishing; never --no-verify. 3. Before a PR: apply the pre-ship skill to the diff, then write the Done section with pr-describe. 4. A decision that…

  • Reads credentials
  • 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 repository6 other files it gives its agents.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    Start from a fresh main: branch <type>/<short-description>, types feat, fix, refactor, docs, test, chore, exp.

    line 8
  2. Very specific:

    Before a PR: apply the pre-ship skill to the diff, then write the Done section with pr-describe.

    line 11
  3. Very specific:

    Read, print or copy .env, keys, tokens.

    line 20
  4. Very specific:

    Commit data, weights, generated logs, mlruns/, personal agent files.

    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

Lab overlay: shared instructions for LLM assistants

These instructions apply on top of the project's own AGENTS.md; the project's file wins on conflict. Rules by topic are in rules/, skills in skills/.

Working cycle

  1. Start from a fresh main: branch <type>/<short-description>, types feat, fix, refactor, docs, test, chore, exp. One branch per change.
  2. Small steps. Run make check after edits and before finishing; never --no-verify.
  3. Before a PR: apply the pre-ship skill to the diff, then write the Done section with pr-describe.
  4. A decision that changes structure, tooling, data, metric or baseline: draft an ADR with write-adr; the student reviews it.
  5. Experiments: one issue per hypothesis (experiment-issue), one MLflow run per execution, Closes #N in the PR.
  6. Meetings: meeting-record turns a transcript into docs/meetings/YYYY-MM-DD.md.

What you must not do

  • Read, print or copy .env, keys, tokens; write secrets into files, logs or PR text.
  • Commit data, weights, generated logs, mlruns/, personal agent files.
  • Rewrite pushed history on main, force-push, squash during review.
  • Edit an accepted ADR or the Plan section of a PR; remove Draft; resolve review threads; merge.
  • Invent results: every number comes from an MLflow run that you name.

Language

Code, identifiers, commit messages and PR titles in English. Documents in the language the student writes them in; keep the language of a file you edit.

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