rust-agent-specialist

SkillAI & models

Apply Rust-native patterns (Type-State, Channel-Based, Actor Model) to ccswarm development.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the rust-agent-specialist skill

What this skill tells your AI

The instructions your AI receives, as published by nwiizo/ccswarm in .agents/skills/rust-agent-specialist/SKILL.md and read by ahel’s review.

Guidance for implementing Rust-idiomatic patterns in ccswarm.

Core Patterns

Type-State (compile-time state validation)

pub struct Agent<State> { inner: AgentInner, _state: PhantomData<State> }
impl Agent<Uninitialized> { fn initialize(self) -> Agent<Ready> { ... } }
impl Agent<Ready> { fn execute(&self, task: Task) -> Result<Output> { ... } }

Channel-Based (replace Arc)

let (tx, rx) = tokio::sync::mpsc::channel(100);
// No shared mutable state between agents

Actor Model (independent actors)

struct AgentActor { mailbox: mpsc::Receiver<Message>, state: AgentState }
impl AgentActor {
    async fn run(mut self) {
        while let Some(msg) = self.mailbox.recv().await { self.handle(msg).await; }
    }
}

Identify & Apply

grep -r "Arc<Mutex" crates/ccswarm/src/ --include="*.rs"    # Convert to channels
grep -r "enum.*State\|State::" crates/ccswarm/src/          # Convert to type-state

Verify: cargo fmt && cargo clippy -- -D warnings && cargo test

Signals

GitHub stars
151
Forks
15
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
rust-agent-specialist
Source
github.com/nwiizo/ccswarm