agentleFS
Sign inStart free
wizardpc-comwizardpc-com/autonomous-math-ai/AGENTS.md

autonomous-math-ai

AGENTS.md2 starsChanged 3 months agoMITView on GitHub

- This repository contains only the generic Autonomous Math AI harness, its schemas, policy packs, documentation, and neutral tests. - Never add conjecture-specific statements, claims, prompts, task packets, runs, outcomes, audits, proofs, or research artifacts. - Integration with a research project must use the public amr CLI and that project's autonomous/project.json; do not assume a monorepo or projects/ directory. - Preserve falsification-first scheduling, independent audit, append-only evidence, canonical guards, crash recovery, schema preflight, and mechanical worker isolation. - Model output…

  • 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 31,700 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 1 is common, 3 are distinctive, and 1 is very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never add conjecture-specific statements, claims, prompts, task packets, runs, outcomes, audits, proofs, or research artifacts.

    line 7
  2. Very specific:

    When a project supplies autonomous/semantics.json, treat its research contract and registry as declarative canonical inputs, never as …

    line 20
  3. Common:

    Do not read, print, persist, or request authentication secrets.

    line 28
  4. Distinctive:

    Keep fixtures mathematically neutral and portable.

    line 36
  5. Distinctive:

    Run unit tests, release-content scanning, build/install acceptance, and git diff --check before publishing.

    line 37

≈ “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

Repository instructions

Scope

  • This repository contains only the generic Autonomous Math AI harness, its schemas, policy packs, documentation, and neutral tests.
  • Never add conjecture-specific statements, claims, prompts, task packets, runs, outcomes, audits, proofs, or research artifacts.
  • Integration with a research project must use the public amr CLI and that project's autonomous/project.json; do not assume a monorepo or projects/ directory.

Trust boundary

  • Preserve falsification-first scheduling, independent audit, append-only evidence, canonical guards, crash recovery, schema preflight, and mechanical worker isolation.
  • Model output is never proof by itself. Trusted state changes require the deterministic controller and audit/canonical gates.
  • When a project supplies autonomous/semantics.json, treat its research contract and registry as declarative canonical inputs, never as trusted verification state. Enforce No unverified bridge into trusted final claims from controller-owned candidate/audit receipts; validator success or agreement among agents cannot replace bridge evidence.
  • Projects without semantic metadata remain legacy-compatible and report the independent semantic status UNREVIEWED; do not convert that status into a claim, trust, evidence, or execution failure.
  • Do not read, print, persist, or request authentication secrets.
  • Fast is permitted only when execution.fast_mode=true is explicitly pinned for the run. Request only fast; accept priority solely as its observed server alias. Otherwise reject fast/priority/ultrafast, and keep mechanical tiers null.

Validation

  • Keep fixtures mathematically neutral and portable.
  • Run unit tests, release-content scanning, build/install acceptance, and git diff --check before publishing.

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