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.
git clone --depth 1 https://github.com/EmilLindfors/a2a-rsWrote 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/commands/emillindfors/a2a-rs/rust-review)<a href="https://agentmods.dev/commands/emillindfors/a2a-rs/rust-review"><img src="https://agentmods.dev/badge/commands/emillindfors/a2a-rs/rust-review.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 5.1 | $0.00028 | $0.00866 |
| Opus 5 | $0.00014 | $0.00433 |
| Sonnet 5 | $0.00006 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
rust-review 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 8d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rust-review
Run a combined Rust-patterns and hexagonal-architecture review over the scope given in $ARGUMENTS (default: the working-tree diff against the merge base of the current branch).
Procedure
-
Determine scope.
- If
$ARGUMENTSis empty ordiff, review uncommitted changes plus committed changes on the current branch vs. its merge base withmain/master. Usegit diffandgit logto enumerate touched files. - If
$ARGUMENTSisbranch, review every Rust file changed on the current branch vs. its merge base. - If
$ARGUMENTSlooks like a path or glob, review those files. - If
$ARGUMENTSis a number (a PR), fetch that PR's diff via the available GitHub tooling and review it.
- If
-
First pass — idiomatic Rust. Apply the
refactor_idiomatic_rustskill. Flag: generics vs.dynmisuse, missing?/error-propagation cleanups, imperative loops that would read better as combinators, weak closure bounds, stringly-typed APIs, missingimpl Into/AsRef/Cowopportunities, panic-prone code in expected-failure paths. -
Second pass — advanced architecture. Apply the
architectural_reviewskill. Flag: opportunities for capability mixins, typed commands replacing untyped buffers, mis-chosen concurrency primitives (Mutex where atomic/channel fits), unbounded channels,lazy_static!instead ofOnceLock/LazyLock, library code returninganyhow::Error. -
Third pass — hexagonal compliance. Apply the
hexagonal_reviewskill against the touched files. Flag the smells listed inrules/hexagonal_architecture.md§8: domain leaking framework types, ports exposing technology, errors leaking up, services constructing adapters, feature flags on the wrong layer. -
Synthesize. Combine findings into a single review. Deduplicate — if one root cause produces findings across multiple passes (e.g. "this port returns
reqwest::Error" is both an error-architecture issue and a hex-boundary leak), report it once and tag it with both passes it came from.
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.
- 8d ago First seen · 56 lines · 28 tokens per session scan A 73c42a536027
rust-review is a command published in the GitHub repository EmilLindfors/a2a-rs (87 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 866 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
tidy
Refactor and tidy OCaml code to be more idiomatic and maintainable.
cargo-clippy
Command "cargo-clippy" from olorehq/olore, covering cargo-clippy(1), name, description and see also.
unsafe-review
Interactive review session for unsafe Rust code.
rust-review
Lightweight Rust code review using clippy.
rust-critique
Deep code critique — read the target Rust code and apply the full review process. Evaluates soundness, ownership, error handling, type design, async correctness, performance, and architecture. Think like a senior Rust engineer giving honest feedback.
rust-teach
One-time setup that scans your Rust project, understands its patterns and conventions, and writes a Rust-specific context section to your CLAUDE.md. Run once per project to establish persistent Rust guidelines.