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 agentmods add skills/vosslab/vosslab-skills/rust-code-expertnpx skills add vosslab/vosslab-skills --skill rust-code-expertgit clone --depth 1 https://github.com/vosslab/vosslab-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/vosslab/vosslab-skills/rust-code-expert)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/rust-code-expert"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/rust-code-expert.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.01278 |
| Opus 5 | $0.00031 | $0.00639 |
| Sonnet 5 | $0.00012 | $0.00256 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
rust-code-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 3d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust code expert
Overview
Use this skill for small, compilable Rust changes with explicit ownership, an error contract, a target triple, and executable proof.
Own core Rust language work, Cargo workflow, and native-target delivery.
Route browser and WebAssembly targets to wasm-rust-expert.
Start with references/task_selection.md to classify the request, then use
references/topic_index.md for focused guidance, a local source, and an oracle.
Workflow
- Classify the Rust task and name its contract.
- Identify the crate, binary or library boundary, target triple, public API, inputs, outputs, ownership transfer, error type, and performance concern.
- Match borrow checker, lifetime, trait, Cargo, Tokio, unsafe, FFI/PyO3, Result, CLI, or performance work in references/topic_index.md.
- Select
wasm-rust-expertforwasm-bindgen,wasm-pack,web-sys,wasm32-unknown-unknown, browser bundles, browser canvas, and native-versus-Wasm parity.
- Detect the project shape and establish the work surface.
- Inspect
Cargo.toml,Cargo.lock,src/, workspace members, existing tests, target-specific configuration, CI commands, and the failing compiler output. - Existing project: name the owning module, public call sites, current tests, and the narrowest behavior to preserve.
- Greenfield project: create the smallest crate, domain and error types, an entry point, and one executable success path.
- Read references/project_workflow.md for the project-shaped sequence and artifact locations.
- Model ownership before editing implementation details.
- Draw the value flow: creator, borrower, mutator, consumer, and lifetime relationship at each API edge.
- Express invalid states with enums, compose behavior with traits, and expose
fallible operations as
Resultwith contextual errors. - Keep unsafe, FFI, and PyO3 boundaries small, documented, and wrapped by a safe Rust-facing API.
- Implement one focused vertical slice.
- Make the smallest change that fulfills the contract in the owning module.
- Prefer direct ownership and borrowing, explicit trait bounds, and standard library types before adding dependencies.
- Confirm the crate API and compatible version in
docs.rs, then usecargo addand record feature and target requirements inCargo.toml.
- Build executable evidence as the change develops.
- Run
cargo fmt --check,cargo check, focusedcargo test, andcargo clippy -- -D warningsfrom the relevant workspace root. - Use compiler diagnostics as the first ownership and type oracle, then add a deterministic unit, integration, CLI, FFI, or performance test.
- Read references/testing_and_oracles.md to choose the required oracle and measurement.
- Review the delivered behavior.
- Confirm the command, library API, or binding returns actionable errors with useful
Resultcontext. - Recheck feature flags, platform assumptions, public documentation, and benchmark conditions before reporting a performance conclusion.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 101 lines · 62 tokens per session scan A 48d93fd889b9
rust-code-expert is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 62 tokens to every session and 1,278 once invoked, about $0.0003 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
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.
rust-code-quality
Run a focused Rust quality review when the user requests one, when reviewing a Rust PR/commit, or when another selected review workflow delegates Rust-specific checks. Do not auto-load for every implementation edit.
crate-structure
The Xberg workspace layout — the version source of truth (root Cargo.toml [workspace.package] version), the 19 workspace members and 3 excluded crates, the distribution packages under packages/, the tools/ directory, and the ignore-file allowlists a new workspace member must be added to. Load when navigating the repo…
rust-pro
Master modern Rust (2024 edition) with async patterns, advanced type system features, and production-ready systems programming. Expert in the current Rust ecosystem including Tokio, axum, and modern crates. Use PROACTIVELY for Rust development, performance optimization, or systems programming.
switchyard-rust-review
Review Switchyard Rust changes for correctness and maintainability. Use for pull requests or diffs touching crates, PyO3 bindings, async runtime behavior, streaming, protocol types, translation, algorithms, or LLM clients.
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…