cc-fleet
AGENTS.md185 starsChanged 5 months agoApache-2.0View on GitHub
This repo's agent/AI guidance lives in CLAUDE.md — it is the single source of truth for any coding agent (Claude Code, Codex, Cursor, etc.). Read it before editing: what cc-fleet is, the four execution lanes, the load-bearing invariants, and the build/test commands. The system design lives in docs/architecture.md; the skills' canonical source is skills/ (edit there, then make skill-sync — see CLAUDE.md); the user-facing references to keep in sync are docs/cli.md and docs/workflows.md. The contribution standard (required checks, commit/PR rules,…
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 31,774 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.
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Simplest correct implementation: No speculative abstraction, dependency, or config surface (YAGNI).
≈ “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
AGENTS.md
This repo's agent/AI guidance lives in CLAUDE.md — it is the single source
of truth for any coding agent (Claude Code, Codex, Cursor, etc.). Read it before editing:
what cc-fleet is, the four execution lanes, the load-bearing invariants, and the build/test
commands. The system design lives in docs/architecture.md; the
skills' canonical source is skills/ (edit there, then make skill-sync — see CLAUDE.md);
the user-facing references to keep in sync are docs/cli.md and
docs/workflows.md.
The contribution standard (required checks, commit/PR rules, screenshots, AI attribution) is
CONTRIBUTING.md.
Coding standards (the essentials)
- Minimal intrusion. Change the fewest lines that solve the task. No out-of-scope refactor, rename, or reformat. Match the surrounding style.
- Simplest correct implementation. No speculative abstraction, dependency, or config surface (YAGNI). Reuse an existing helper before adding one.
- Concise comments. Explain why, not what; no narration or ticket/changelog notes. Fix comments your change makes stale.
- Respect the invariants documented in CLAUDE.md: keys never in env/argv/history; classified
Resultenvelopes fromsubagent/teammate check; validate names before use; honor the lock order (WithProvidersConfigLock→WithServerLock; there is no team lock). - Verify before done:
go test -race ./...,gofmt -l .,go vet ./...clean; plusclaude plugin validate .if you touched the plugin/skill.
AI attribution
- AI-assisted (a human authored/reviewed the diff) →
Co-Authored-By:trailer naming the tool/model in the commit message. - Fully AI-authored PR → add the autonomous-PR marker as the last line of the PR body
(see
CONTRIBUTING.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.