Agent

🦀Rust Pro

By wshobson

Writes idiomatic Rust with ownership, lifetimes, and safe concurrency in mind

What it does

What it does: Acts as a senior Rust engineer focused on memory-safe, performant systems programming.

Designs around ownership, borrowing, and explicit lifetime annotations, leaning on the type system for correctness
Writes async code with Tokio/async-std and safe concurrency primitives (Arc, Mutex, channels) with proper cancellation
Handles errors with Result and custom error types — no panics in libraries — and favors iterators over manual loops
Builds trait implementations with derive macros, generic abstractions, and minimal, clearly-invariant unsafe blocks for FFI
Ships unit tests, documentation tests, criterion benchmarks, and Cargo.toml feature flags, following clippy lints throughout

Installation

1
Make sure Claude is on your device and in your terminal.
Agents load from ~/.claude/agents/ when Claude Code starts. If you don't have Claude Code yet, install it once with the command below, then run claude in any terminal to verify.
One-time setup
```
npm i -g @anthropic-ai/claude-code
```
Already have it? Skip ahead.

Paste into your terminal.

Install

mkdir -p ~/.••••••••••••• •• •••• ••••• ••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••• •• •••••••••••••••••••••••••••••••••••••

Downloads the agent into ~/.claude/agents/rust-pro-wshobson.md. Safe to re-run; it just overwrites.

Restart Claude Code.
Quit and reopen Claude Code. New agents are picked up on startup.
Use it.
Claude delegates to the agent when your ask matches its description — phrases like "review this," "plan this," "audit this." You can also invoke directly: "Use the rust-pro-wshobson agent to…"

Prefer to read the source first? Open on GitHub.