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 tmj-90/gaffer --skill rust-conventionsgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/rust-conventions)<a href="https://agentmods.dev/skills/tmj-90/gaffer/rust-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/rust-conventions/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/tmj-90/gaffer/rust-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/rust-conventions.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 | $0.00115 | $0.02033 |
| Opus 5.5 | $0.00046 | $0.00813 |
| Sonnet 5.5 | $0.00023 | $0.00407 |
| Haiku 4.5 | $0.00012 | $0.00203 |
Grade A, and why
rust-conventions 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 16d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write idiomatic, safe Rust
Rust rewards code that makes ownership and failure explicit and punishes code that
fights the compiler with clones, unwrap and unsafe. For the builder and the reviewer of a Rust diff; the crate's config and existing code win over it.
Procedure
- Discover the crate's conventions first. Call
search_lorefor Rust conventions. ReadCargo.toml(edition,rust-versionMSRV,[lints]/[workspace.lints], features),rust-toolchain.toml,clippy.toml,rustfmt.toml,deny.toml,.cargo/config.tomland the CI workflow. Identify the error strategy (thiserrorenums in libraries,anyhowat the binary edge, or hand-rolled), the async runtime, and the policy onunsafe(#![forbid(unsafe_code)]?). Copy a sibling module and its tests. - Pin the exact commands from CI,
Makefile/justfileorxtask(therun-testsandrun-lintskills). Use the defaults below only when the repo defines none; match CI's feature flags. - Write the change with the idioms below, then walk the concurrency section for every task, lock, channel, file and outbound call you touched.
- Test each acceptance criterion's own behaviour. One test per AC that fails without
your change, plus its error path. If the AC involves shared state or persistence, add
a test that spawns N threads or tasks against it and asserts the invariant; use
proptestfor wide inputs (theproperty-based-testskill). - Verify, then stop. Done when:
cargo fmt --checkand clippy are clean at CI's level, tests pass with CI's features, public items are documented, and every AC has a test. Record the output with therecord-evidenceskill; the runner submits the work.
Commands
- Format:
cargo fmt --all -- --check. - Lint:
cargo clippy --all-targets --all-features -- -D warnings(or CI's feature set). - Test:
cargo test --all-features(orcargo nextest runwhere configured; nextest skips doctests, so also runcargo test --doc); one test:cargo test name -- --exact. - Docs:
cargo doc --no-depswithRUSTDOCFLAGS="-D warnings"if CI sets it. - Dependencies: never
cargo add/cargo update; a new or bumped crate is a blocker (thedependency-upgradeskill).cargo deny checkwhere CI runs it. - Unsafe:
cargo +nightly miri testfor code withunsafe, only if the repo uses Miri and the nightly toolchain is already installed.
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.
- 16d ago Changed · +47 lines · +23 tokens per session 5e2184620a14
- 19d ago First seen · 71 lines · 92 tokens per session scan A e9782d2cf905
rust-conventions is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 115 tokens to every session and 2,033 once invoked, about $0.0005 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 2026-09-28.
Other skills, from other repositories
sota-rust
State-of-the-art Rust engineering (2026) for writing and auditing Rust code. Covers idiomatic ownership and API design, error handling and panic policy, unsafe discipline with Miri, async/tokio (cancellation safety, structured concurrency, graceful shutdown), security and supply chain (cargo audit/deny/vet, integer…
cargo-workflows
Manage Rust projects effectively with Cargo workspaces, features, and tooling. Use when the user sets up Cargo workspaces, configures feature flags, writes build.rs scripts, prepares crates for publishing, or uses cargo clippy, cargo fmt, and other Cargo development tools.
error-handling-rust
Implement idiomatic Rust error handling with Result, Option, and the ? operator. Use when the user handles errors in Rust, creates custom error types, uses thiserror or anyhow, implements the From trait for error conversion, or asks about Result/Option patterns and error composition strategies.
ownership-borrowing
Master Rust's ownership, borrowing, and lifetime system for memory-safe code. Use when the user encounters borrow checker errors, lifetime annotations, needs smart pointers (Box/Rc/Arc), works with move semantics, or asks about Clone vs Copy, ownership transfer, and reference management in Rust.
rust-expert
Rust programming expert for ownership, lifetimes, async/await, traits, and unsafe code.
yoagent
Use when building, extending or upgrading an agent on the yoagent Rust crate. Maps each job (tools, policies, verifiers, budgets, sub-agents, plugins from other ecosystems, retries, structured output, tests) to the yoagent feature for it, with tips, pitfalls and what changed per version.