agentleFS
Sign inStart free
ponomrponomr/thinking-toolkit/AGENTS.md

thinking-toolkit

AGENTS.md16 starsChanged 2 months agoMITView on GitHub

A skill for any agent with SKILL.md: selecting and applying thinking models. The stack, structure and invariants are checked by scripts/validate_skill.py and the tests; this file holds only what they do not catch. Commands: python3 scripts/validate_skill.py ., python3 -m unittest discover -s tests -v, python3 scripts/build_release.py. 1. Keep every project file in English, except README.ru.md and README.zh.md. 2. Keep the core skill usable by any capable LLM without provider-specific tools, browsing, code execution, persistent memory, or hidden state. 3. Never…

  • 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 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, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Very specific:

    Keep every project file in English, except README.ru.md and README.zh.md.

    line 12
  2. Distinctive:

    Keep the core skill usable by any capable LLM without provider-specific tools, browsing, code execution, persistent memory, or hidden state.

    line 13
  3. Distinctive:

    Never mention or cite the prohibited source project (names and attributions are scrubbed.

    line 15
  4. Very specific:

    Never add external URLs or external Markdown links to the skill payload (SKILL.md, references/, logic/, agents/).

    line 17
  5. Distinctive:

    Keep claims, assumptions, hypotheses, and user-provided facts distinct.

    line 24

≈ “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

Thinking Toolkit

A skill for any agent with SKILL.md: selecting and applying thinking models. The stack, structure and invariants are checked by scripts/validate_skill.py and the tests; this file holds only what they do not catch.

Commands: python3 scripts/validate_skill.py ., python3 -m unittest discover -s tests -v, python3 scripts/build_release.py.

Rules

  1. Keep every project file in English, except README.ru.md and README.zh.md.
  2. Keep the core skill usable by any capable LLM without provider-specific tools, browsing, code execution, persistent memory, or hidden state.
  3. Never mention or cite the prohibited source project (names and attributions are scrubbed; history was rewritten into a single commit).
  4. Never add external URLs or external Markdown links to the skill payload (SKILL.md, references/, logic/, agents/). READMEs, SECURITY.md and LICENSE may cite external resources.
  5. The card count is not a cap. A new card must meet the admission criteria in MAINTAINING.md; the catalog categories are preserved.
  6. logic/ is an English payload with no Cyrillic, even for trigger phrases: the module learns the user's language by instruction. Keep it lean.
  7. Keep claims, assumptions, hypotheses, and user-provided facts distinct.
  8. In your own task branch, commit and push as you go; elsewhere commit only when the user asks.
  9. Users install copied payloads from immutable releases. Do not restore symlink installation or an install-from-main quick path.
  10. Updates are user-initiated. Verify the release and asset, show the file changes, and preserve a rollback backup. A requested normal upgrade needs no second confirmation; stop and ask before a downgrade, after failed verification, or when the diff reaches outside the selected skill. Never bypass failed verification.

Release and repository safeguards are in MAINTAINING.md. Re-check GitHub settings after a transfer or recreation of the repository.

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