rustkb
CLAUDE.md0 starsChanged 43 days agoMITView on GitHub
This repo is both a Claude Code plugin (skills/agents/commands) and a Rust workspace (the rustkb CLI + MCP server). See README.md for the architecture.
In this repository4 other files it gives its agents.
- rust-architectureSkill
- rust-ecosystemSkill
- rust-idiomsSkill
- rust-securitySkill
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 9
Never write crate versions, APIs or stabilisation versions from memory: use rustkb crate <name>, rustkb item <crate> <path>, rustkb release …
- Very specific: line 11
Every change: cargo run -q -p rustkb -- validate must pass.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 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
rustkb — working in this repo
This repo is both a Claude Code plugin (skills/agents/commands) and a Rust workspace (the
rustkb CLI + MCP server). See README.md for the architecture.
Curated knowledge (skills/)
docs/AUTHORING.mdis the binding spec. Frontmatter is machine-checked; rule ids are stable public identifiers — never renumber, retire instead.- Never write crate versions, APIs or stabilisation versions from memory: use
rustkb crate <name>,rustkb item <crate> <path>,rustkb release --since <ver>(or the MCP tools). - Every change:
cargo run -q -p rustkb -- validatemust pass. Compile non-trivial examples in a scratch crate outside the repo. - Drift work:
cargo run -q -p rustkb -- stalethen followagents/rustkb-curator.md.
Rust code (crates/)
cargo fmt --all,cargo clippy --workspace --all-targets -- -D warnings(pedantic is on),cargo test --workspace. Also check--features rustkb/semanticbuilds.- stdout of
rustkb serveis the MCP transport — log only viatracing(stderr). - The index is shared by concurrent processes (one MCP server per session + CLI): keep writers
short-lived (
Index::write), rebuild via new generations, never delete a live index dir. - rustdoc JSON's format is unstable: parse loosely from
serde_json::Value(seerustdoc.rs). - Be polite upstream: crates.io ≤ 1 req/s, cache everything with TTLs, descriptive User-Agent without personal data.
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.

