skills
AGENTS.md1 starsChanged 4 months agoMITView on GitHub
- This repository is the generated public installation surface for skills owned by the Agentic Constellation. - Never edit skills/ or provenance.lock.json manually. They are complete, non-canonical outputs written only by the Publisher workflow. - Change skill behavior in its owning source repository, publish a stable immutable release, and let reconciliation update this bundle. - Repository documentation, trust files, workflows, tests, scripts, and the positive allowlist may change through reviewed pull requests. Run the canonical local check before claiming a…
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 31,542 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 repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agentic-osSkill
- captureSkill
- domain-reconnaissanceSkill
- lookupSkill
- orchestrateSkill
- postSkill
- setup-agentic-osSkill
- setup-career-systemSkill
- setup-knowledge-systemSkill
- setup-mastery-systemSkill
- tweetSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Very specific: line 7
Never edit skills/ or provenance.lock.json manually.
- Distinctive: line 16
Run the canonical local check before claiming a change is complete:
- Very specific: line 22
Keep GitHub Actions permissions explicit and least-privilege.
≈ “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.
Files
Agent instructions
Repository boundary
- This repository is the generated public installation surface for skills owned by the Agentic Constellation.
- Never edit
skills/orprovenance.lock.jsonmanually. They are complete, non-canonical outputs written only by the Publisher workflow. - Change skill behavior in its owning source repository, publish a stable immutable release, and let reconciliation update this bundle.
- Repository documentation, trust files, workflows, tests, scripts, and the positive allowlist may change through reviewed pull requests.
Validation
Run the canonical local check before claiming a change is complete:
bash scripts/check.sh && git diff --checkKeep GitHub Actions permissions explicit and least-privilege. Preserve the
fail-safe publication and forward-only rollback contracts documented in
docs/distribution.md.
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
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.