agentleFS
Sign inStart free
docxologydocxology/codomyrmex/scripts/AGENTS.md

codomyrmex / scripts

AGENTS.md10 starsChanged 38 days agoMITView on GitHub

Define execution and maintenance safety for repository automation. - Run from the repository root unless the script explicitly documents another working directory. - Use uv run --locked and the appropriate dependency group. - Read the nearest nested AGENTS file before editing or executing a script. - Run GitNexus impact analysis before changing a function or class. - Prefer explicit check, dry-run, output, and apply modes. - Make --help and missing-mode invocations read-only for maintained mutators. - Keep output deterministic, repository-relative,…

The file

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

9 rules. About 1 is common, 6 are distinctive, and 2 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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. Distinctive:

    Run from the repository root unless the script explicitly documents another working directory.

    line 11
  2. Very specific:

    Use uv run --locked and the appropriate dependency group.

    line 13
  3. Distinctive:

    Read the nearest nested AGENTS file before editing or executing a script.

    line 14
  4. Distinctive:

    Run GitNexus impact analysis before changing a function or class.

    line 15
  5. Distinctive:

    Prefer explicit check, dry-run, output, and apply modes.

    line 16
  6. Common:

    Keep output deterministic, repository-relative, and credential-free.

    line 18
  7. Distinctive:

    Use real temporary repositories and subprocesses in tests.

    line 21
  8. Very specific:

    Update README, AGENTS, SPEC/PAI/security, Makefile/justfile, and changelog parity when a contributor-facing CLI changes.

    line 22
  9. Distinctive:

    Treat generation, cleanup, dependency installation, publication, deployment, Git operations, external messaging, and broad filesystem …

    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
<!-- agents: curated -->

Agent guidance for repository scripts

Purpose

Define execution and maintenance safety for repository automation.

Development Guidelines

  • Run from the repository root unless the script explicitly documents another working directory.
  • Use uv run --locked and the appropriate dependency group.
  • Read the nearest nested AGENTS file before editing or executing a script.
  • Run GitNexus impact analysis before changing a function or class.
  • Prefer explicit check, dry-run, output, and apply modes.
  • Make --help and missing-mode invocations read-only for maintained mutators.
  • Keep output deterministic, repository-relative, and credential-free.
  • Preserve curated documentation, existing dirty changes, and submodule boundaries.
  • Use real temporary repositories and subprocesses in tests.
  • Update README, AGENTS, SPEC/PAI/security, Makefile/justfile, and changelog parity when a contributor-facing CLI changes.

Key Files

  • README.md — supported script categories and entry points
  • SPEC.md — script-surface specification
  • doc_inventory.py — authoritative volatile metrics
  • src_structure_audit.py — source/documentation parity
  • rasp_gap_report.py — README/AGENTS pair audit
  • run_all_scripts.py — orchestrator CLI wrapper; missing-mode invocation defaults to --dry-run
  • documentation/ — canonical documentation tooling

High-risk categories

Treat generation, cleanup, dependency installation, publication, deployment, Git operations, external messaging, and broad filesystem repair as mutating. Resolve their exact targets before execution and request new authority when the operation exceeds the user's stated scope.

Validation

uv run --locked ruff check scripts tests
uv run --locked ruff format --check scripts tests
uv run --locked ty check --output-format concise scripts tests
uv run --locked pytest -q <relevant-test-path>

For documentation and manuscript scripts, also run make docs-check and make manuscript-check.

Navigation

  • Human overview
  • Documentation scripts
  • Repository agent contract
  • Repository root

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