agentleFS
Sign inStart free
prathakmalikprathakmalik/agent-standards-kit/AGENTS.md

agent-standards-kit

AGENTS.md0 starsChanged 4 months agoMITView on GitHub

Portable, tool-agnostic instructions for AI coding agents working in this repo. Cursor, Claude Code, GitHub Copilot, and Codex all read a file like this (or have it synced to their config). It is the single portable base for the standards in rules/. This file is generated/maintained from rules/. Edit the .mdc rules and re-run scripts/sync-rules.* to keep them aligned, or edit here directly if your team treats AGENTS.md as canonical. Task workflows live in skills/ (Agent Skills SKILL.md format) and…

  • 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 repository4 other files it gives its agents.

The file

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

7 rules. About 2 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈2

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer clear names over clever ones.

    line 9
  2. Distinctive:

    Keep functions small and single-purpose.

    line 10
  3. Common:

    Never hardcode or log secrets, tokens, credentials, or PII.

    line 17
  4. Distinctive:

    Never change a public API/signature without updating all call sites.

    line 18
  5. Distinctive:

    Never leave dead or narration comments.

    line 19
  6. Distinctive:

    Add/update tests when behavior changes.

    line 23
  7. Common:

    Follow the PR checklist: single-purpose change, tests updated, no secrets/PII in the diff, call sites updated, docs/CHANGELOG updated when …

    line 34

≈ “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

Portable, tool-agnostic instructions for AI coding agents working in this repo. Cursor, Claude Code, GitHub Copilot, and Codex all read a file like this (or have it synced to their config). It is the single portable base for the standards in rules/.

This file is generated/maintained from rules/. Edit the .mdc rules and re-run scripts/sync-rules.* to keep them aligned, or edit here directly if your team treats AGENTS.md as canonical.

Standards (always apply)

  • Prefer clear names over clever ones; names describe intent.
  • Keep functions small and single-purpose; extract duplication.
  • Handle error and edge cases explicitly; never swallow errors silently.
  • Match the conventions already present in the file you are editing.
  • Comments explain why (intent, trade-offs), never narrate what.

Never

  • Never hardcode or log secrets, tokens, credentials, or PII.
  • Never change a public API/signature without updating all call sites.
  • Never leave dead or narration comments.

Tests

  • Add/update tests when behavior changes. A bug fix ships with a regression test.

Available skills

Task workflows live in skills/ (Agent Skills SKILL.md format) and are synced into your tool. Notable ones:

  • generate-readme — generate/refresh a README grounded in the code.
  • review-changes — rigorous review of a diff/PR before commit.

Pull requests

Follow the PR checklist: single-purpose change, tests updated, no secrets/PII in the diff, call sites updated, docs/CHANGELOG updated when behavior changes.

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