rust-reviewer

A reviewer for Rust code changes in the Fallow project. It checks correctness, performance, project conventions, cross-platform behavior, and memory layout.

In plain words
What is it for?
Use it to review Rust diffs and report only high-confidence issues with file locations, fixes, and an approval, concern, or block verdict.
Why use it?
It catches likely bugs, unnecessary copying or allocation, unsafe patterns, panics on user-facing paths, and repository-rule violations before they reach users.

Agent for Codex

Install

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.

agentmods
npx agentmods add agents/fallow-rs/fallow/rust-reviewer
Clone the repo
git clone --depth 1 https://github.com/fallow-rs/fallow

Made for: Codex.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 352 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00352
Opus 5 $0.00008 $0.00176
Sonnet 5 $0.00003 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 3d ago against content hash a368269a86cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust-reviewer 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.

.agents/agents/rust-reviewer.md · 46 lines

What it actually says

Review Rust code changes in the fallow project. Focus on:

What to check

  1. Correctness: Logic errors, edge cases, panic paths
  2. Performance: Unnecessary allocations, missing &str over String, clone() where borrow works
  3. Project conventions:
    • #[expect(clippy::...)] not #[allow]
    • FxHashMap/FxHashSet instead of HashMap/HashSet
    • Size assertions on hot-path structs
    • Early returns with guard clauses
  4. Cross-platform: Path separator issues (use .replace('\\', "/") in tests)
  5. Cache friendliness: Flat storage patterns, avoid Arc/Rc where not needed

What NOT to flag

  • Style preferences already enforced by rustfmt/clippy
  • Missing docs on internal items
  • Test organization choices

Veto rights

Can BLOCK on:

  • Unsafe code without justification
  • Missing --all-targets in test/clippy commands
  • HashMap/HashSet instead of FxHashMap/FxHashSet
  • Panicking code (unwrap/expect) on user-facing paths

Output format

Only report issues with HIGH confidence. For each issue:

  • File and line
  • What's wrong
  • Suggested fix

End with a verdict:

## Verdict: APPROVE | CONCERN | BLOCK
Changes

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.

  1. 3d ago First seen · 46 lines · 16 tokens per session scan A a368269a86cd

Subscribe to this mod's changes

rust-reviewer is an agent published in the GitHub repository fallow-rs/fallow (4,438 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 352 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.

Related

Other agents, from other repositories