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 softspark/ai-toolkit --skill rust-rulesgit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/rust-rules)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/rust-rules"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/rust-rules/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/softspark/ai-toolkit/rust-rules"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/rust-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.03021 |
| Opus 5.5 | $0.00017 | $0.01208 |
| Sonnet 5.5 | $0.00009 | $0.00604 |
| Haiku 4.5 | $0.00004 | $0.00302 |
Grade A, and why
rust-rules 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 1mo 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Rules
These rules come from app/rules/rust/ in ai-toolkit. They cover
the project's standards for coding style, frameworks, patterns,
security, and testing in Rust. Apply them when writing or
reviewing Rust code.
Rust Coding Style
Naming
- snake_case: functions, methods, variables, modules, crates.
- PascalCase: types, traits, enums, structs, type parameters.
- SCREAMING_SNAKE: constants and statics.
- Short lifetimes:
'a,'b. Descriptive only when multiple coexist:'input,'output. - Crate names: kebab-case in Cargo.toml, snake_case in code.
Ownership
- Borrow (
&T) when you only need to read. Own (T) when storing or consuming. - Use
&stroverStringin function parameters when possible. - Use
Cow<'_, str>when you sometimes need to allocate. - Avoid
.clone()as a first resort -- restructure ownership instead. - Use
Arc<T>only when shared ownership across threads is required.
Types
- Use newtypes for domain primitives:
struct UserId(Uuid). - Use
#[derive(Debug, Clone, PartialEq)]on data types. - Implement
Displayfor user-facing output,Debugfor developer output. - Use
#[non_exhaustive]on public enums and structs for future compatibility. - Prefer enums over boolean flags for state representation.
Functions
- Return
Result<T, E>for operations that can fail. Avoid panicking. - Use
impl Traitin argument position for flexibility, return position for simplicity. - Use
whereclauses for complex bounds instead of inline. - Prefer iterators over index-based loops.
- Use
let-else(1.65+) for early-exit pattern matching.
Modules
- Use
mod.rsor filename-based modules. Be consistent within the project. - Re-export public API from
lib.rsfor a clean surface. - Keep modules focused. One major type or concept per module.
- Use
pub(crate)for internal-only visibility.
Formatting
- Use
rustfmtwith default settings. Do not fight the formatter. - Use
clippywith-D warningsin CI. Fix all warnings. - Set MSRV (Minimum Supported Rust Version) in
Cargo.toml.
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.
- 1mo ago First seen · 277 lines · 43 tokens per session scan A 8ac24fad76f9
rust-rules is a skill published in the GitHub repository softspark/ai-toolkit (181 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 3,021 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
rust-best-practices
Idiomatic Rust development with ownership, borrowing, lifetimes, error handling (thiserror/anyhow), async Tokio patterns, traits, generics, Clippy linting, cargo workspaces, and production patterns for web services (axum/actix-web), CLI tools (clap), and systems programming. Use when writing, reviewing, or debugging…
rust-performance
Use when writing or reviewing performance-sensitive Rust, profiling slow Rust code, reducing allocations, investigating latency or throughput regressions, or diagnosing bloated binaries and long compile times. Covers allocation, iterators, data layout, hashing, async/concurrency, build profiles, Clippy review gates…
rust-concurrency
Use when implementing or debugging Rust threads, Send/Sync bounds, Arc and synchronization, channels, Tokio async tasks, cancellation, graceful shutdown, backpressure, deadlocks, or choosing Rayon for CPU-bound parallel work.
rust-tdd
Use when implementing Rust features test-first, reproducing Rust bugs with regression tests, characterizing legacy Rust, or applying red-green-refactor with cargo test. Covers boundary and equivalence cases, proptest shrinking, mockall expectations, rstest fixtures, async/concurrent/CLI tests, and coverage…
rust-unsafe-ffi
Use when writing or reviewing Rust unsafe blocks, raw-pointer abstractions, MaybeUninit or manual Drop code, unsafe trait implementations, or C/C++ FFI bindings. Covers pointer validity, aliasing and provenance, C ABI/layout, callbacks, allocator ownership, C strings, unwinding, Rust 2024 unsafe syntax, and…
rust-wasm
Use when compiling Rust to WebAssembly, integrating wasm-bindgen or web-sys with browser JavaScript and the DOM, packaging with wasm-pack, choosing wasm32-unknown-unknown versus wasm32-wasip1 or wasm32-wasip2, designing WIT component interfaces, or debugging Wasm loading, capabilities, and target tests.