agentleFS
Sign inStart free
jerssonjersson/tony-ai-tools/AGENTS.md

tony-ai-tools

AGENTS.md0 starsChanged 56 days agoMITView on GitHub

Guidance for AI coding agents working in this repo. When asked to run a consistency check (or to fix inconsistencies), follow this order: 1. Run tools/check_consistency.py — mechanical checks; must exit 0 before anything else. 2. Follow tools/CONSISTENCY.md — the semantic LLM audit catalog. Sweep all skills/docs against its rules, fix every instance, sweep the sibling skills for the same defect. 3. When you discover a NEW inconsistency pattern, add a rule to tools/CONSISTENCY.md so it does not recur, then…

  • 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 31,439 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

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When asked to run a consistency check (or to fix inconsistencies), follow this order:

    line 7
  2. Very specific:

    Run tools/check_consistency.py — mechanical checks.

    line 9
  3. Very specific:

    Follow tools/CONSISTENCY.md — the semantic LLM audit catalog.

    line 10
  4. Very specific:

    When you discover a NEW inconsistency pattern, add a rule to tools/CONSISTENCY.md so it does not recur, then re-run the mechanical checks.

    line 12
  5. Distinctive:

    After any approved modification, update the documentation that names what changed (tools, paths, versions, commands, sections, constants) …

    line 22

≈ “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

Guidance for AI coding agents working in this repo.

Consistency audits

When asked to run a consistency check (or to fix inconsistencies), follow this order:

  1. Run tools/check_consistency.py — mechanical checks; must exit 0 before anything else.
  2. Follow tools/CONSISTENCY.md — the semantic LLM audit catalog. Sweep all skills/docs against its rules, fix every instance, sweep the sibling skills for the same defect.
  3. When you discover a NEW inconsistency pattern, add a rule to tools/CONSISTENCY.md so it does not recur, then re-run the mechanical checks.

Conventions

  • Skills under skills/ are shipped operating constraints for the LLM, not aspirational docs.
  • Package version lives in package.json and .claude-plugin/plugin.json and must stay in sync with any version-pinned README install command. .claude-plugin/marketplace.json is a catalog entry, not a version source — keep its plugin name aligned with plugin.json.
  • Product nouns are "epic", "user story", "story", "knowledge base"; the consumer is the "PO".
  • After any approved modification, update the documentation that names what changed (tools, paths, versions, commands, sections, constants) in the SAME change. A stale doc is the same defect as broken code.

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