agentleFS
opascopeopascope/skills/AGENTS.md

skills

AGENTS.md0 starsChanged 35 days agoMITView on GitHub

Keep this package domain-independent and dependency-free: markdown and Python's standard library only. Only openrouter and jevify call outside models; they need OPENROUTER_API_KEY, show each call's cost, and stop cleanly without it. Read ARCHITECTURE.md before changing artifact semantics. Canonical skill instructions live in the skill folders at the repo root, never in generated copies. Use feature branches and pull requests to main. Every PR adds one plain line under ## [Unreleased] in CHANGELOG.md, or says no user-visible change; releases follow docs/runbooks/cutting-release.md.…

  • Reads credentials
  • 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 31,843 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 repository9 other files it gives its agents.

The file

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

4 rules. About 1 is common, 0 are distinctive, and 3 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Keep this package domain-independent and dependency-free: markdown and Python's standard library only.

    line 3
  2. Very specific:

    Use feature branches and pull requests to main.

    line 8
  3. Common:

    Never commit real user transcripts, credentials, private project details, or local machine paths.

    line 14
  4. Very specific:

    Before a PR: python3 tools/docs/docs.py check.

    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

Contributing to the Opascope work-process skills

Keep this package domain-independent and dependency-free: markdown and Python's standard library only. Only openrouter and jevify call outside models; they need OPENROUTER_API_KEY, show each call's cost, and stop cleanly without it. Read ARCHITECTURE.md before changing artifact semantics. Canonical skill instructions live in the skill folders at the repo root, never in generated copies.

Use feature branches and pull requests to main. Every PR adds one plain line under ## [Unreleased] in CHANGELOG.md, or says no user-visible change; releases follow docs/runbooks/cutting-release.md. Run python3 -m unittest discover -s tests -v before merging. Runtime smoke tests are separate, opt-in checks using installed Claude Code and Codex accounts.

Never commit real user transcripts, credentials, private project details, or local machine paths. Use fictional filesystem fixtures. Preserve unowned install paths. The optimize skill may write a report, but must never change its audit target. Loop completion needs independent command evidence, never just a worker's claim.

<!-- manage-docs:router -->

Docs and records

  • Docs map: docs/README.md, one line per doc with its receipt status.
  • Where does a new file go? python3 tools/docs/docs.py where "<what it is>".
  • Before a PR: python3 tools/docs/docs.py check.
<!-- /manage-docs:router -->

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.