cafleet
CLAUDE.md56 starsChanged 4 days agoMITView on GitHub
This file provides repository guidance to coding agents. Load relevant skills through the executing backend's supported loader. Assigned CAFleet members continue their existing team workflow with the installed role/core/backend references from their spawn prompt. CAFleet multiplexes coding-agent sessions and coordinates them through durable point-to-point messages. The Rust package at the repository root builds the unified CLI with clap, rusqlite and an embedded refinery schema baseline. The binary embeds its data files from assets/; the documentation site retains its own Node/pnpm…
In this repository4 other files it gives its agents.
- cafleet-model-list-refreshSkill
- clean-docsSkill
- skill-authorSkill
- update-readmeSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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 15
Use full mise monorepo task paths and discover available operations with mise tasks --all.
- Very specific: line 19
Write every Rust test as a unit test in a #[cfg(test)] mod tests block of the implementation file it exercises.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.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
CLAUDE.md
This file provides repository guidance to coding agents.
Skills
Load relevant skills through the executing backend's supported loader. Assigned CAFleet members continue their existing team workflow with the installed role/core/backend references from their spawn prompt.
Project: CAFleet
CAFleet multiplexes coding-agent sessions and coordinates them through durable point-to-point messages. The Rust package at the repository root builds the unified CLI with clap, rusqlite and an embedded refinery schema baseline. The binary embeds its data files from assets/; the documentation site retains its own Node/pnpm toolchain.
Commands
Use full mise monorepo task paths and discover available operations with mise tasks --all. The root mise.toml owns the Rust tasks and selects the documentation site's task file through monorepo.config_roots; see .claude/rules/commands.md for invocation conventions.
Tests
Write every Rust test as a unit test in a #[cfg(test)] mod tests block of the implementation file it exercises; never add a test-only file or folder. .claude/rules/code-quality.md § Test placement owns the convention.
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.

