Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Miaoge-Ge/coding-agent-skills --skill rust-expertgit clone --depth 1 https://github.com/Miaoge-Ge/coding-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/rust-expert)<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/rust-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/rust-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/rust-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/rust-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.01143 |
| Opus 5 | $0.00046 | $0.00571 |
| Sonnet 5 | $0.00019 | $0.00229 |
| Haiku 4.5 | $0.00009 | $0.00114 |
Grade A, and why
rust-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Expert
Fight the design, not the borrow checker — a borrow error is usually a real aliasing/lifetime problem. Make invalid states unrepresentable, return errors as values, and reach for
clone()/unsafedeliberately, never to silence the compiler.
When to Use
- Writing or refactoring Rust.
- Borrow-checker, lifetime, move/
clone, orSend/Syncerrors. - Designing traits, generics, error types, or APIs.
- Async (tokio), iterators, smart pointers, or vetting
unsafe.
When NOT to Use
- Other languages → the relevant language skill.
- High-level system architecture →
software-architect.
Core Principles
1. Ownership & borrowing by design
- Borrow (
&T/&mut T) over cloning;clone()is a real cost you choose, not an error silencer. - The rule: many
&Txor one&mut T. When it fights you, restructure: narrow scopes, split borrows, index-based access, or interior mutability (Cell/RefCellsingle-thread,Mutex/RwLockmulti-thread). - Params take
&str/&[T]/impl AsRef<_>; store ownedString/Vec<T>. Return owned data or borrow tied to an input lifetime.
2. Errors are values
- Return
Result<T, E>; propagate with?. Avoidunwrap()/expect()outside tests,main, or provably-infallible spots (and thenexpect()with a reason). - Libraries: typed errors with
thiserror(implstd::error::Error, use#[from]). Apps:anyhow::Resultwith.context("…"). Optionfor absence,Resultfor failure. Don't panic on recoverable conditions.
3. Model with the type system
- Enums to make illegal states unrepresentable; newtype pattern for domain values and to add trait impls.
- Generics + trait bounds by default;
dyn Trait(boxed) for heterogeneous collections, plugin points, or smaller code size. DeriveDebug/Clone/PartialEqwhere sensible; implFromfor conversions so?composes.
4. Async & concurrency
- Pick one runtime (usually
tokio). Never block the executor — use async I/O; offload CPU/blocking work tospawn_blockingor a thread pool. - Share state with
Arc<Mutex<T>>/Arc<RwLock<T>>; hold locks for the shortest possible scope and never across.await. Move ownership across tasks via channels.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 88 lines · 93 tokens per session scan A 1c9f91f930a9
rust-expert is a skill published in the GitHub repository Miaoge-Ge/coding-agent-skills (6 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 1,143 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
agent-rust-build-resolver
Rust build, compilation, and dependency error resolution specialist. Fixes cargo build errors, borrow checker issues, and Cargo.toml problems with minimal changes. Use when Rust builds fail.
agent-rust-reviewer
Expert Rust code reviewer specializing in ownership, lifetimes, error handling, unsafe usage, and idiomatic patterns. Use for all Rust code changes. MUST BE USED for Rust projects.
raspberry-pi-rust-embedded
Production-grade embedded Rust guidelines for Raspberry Pi (bare-metal nostd and Linux embedded std/rppal/embedded-hal). Use when developing low-latency hardware control apps, embedded Rust drivers, Linux GPIO/SPI/I2C/UART software, real-time interrupt handlers, and memory-safe hardware abstractions.
tauri-rust-and-frontend-desktop
Architectural patterns, security IPC, performance optimization, native integration, and production best practices for building cross-platform desktop applications using Tauri (v2) and Rust with modern web frontends (React, Svelte, Vue). Use when designing, building, or optimizing Tauri desktop apps.
develop-like-oxide
Develop the way Oxide (the company) does: RFD-driven written decisions, Rust-heavy hardware/software co-design, rigor with urgency, radical transparency. Use when the user wants Oxide-style engineering decisions, code review in Oxide's voice, or asks to "develop like Oxide". Profiled 2026-07-11 from public sources.