auv-code-reviewer

auv-code-reviewer is an agent for Cursor from moeru-ai/auv. It costs 65 tokens per session (483 once invoked), scanned A, original, Apache-2.0.

A Rust code reviewer for the AUV repository's SceneBridge, view-memory, and view-parser work. It checks correctness, project-specific rules, public API boundaries, and hermetic tests.

In plain words
What is it for?
Use it immediately after changing auv-view, auv-netease-music, SceneBridge code, or related documentation.
Why use it?
It catches contract mismatches, stale-state errors, leaked private APIs, swallowed errors, and tests that depend on network access, macOS drivers, or real time.

Agent for Cursor

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/moeru-ai/auv/auv-code-reviewer
Clone the repo
git clone --depth 1 https://github.com/moeru-ai/auv

Made for: Cursor.

Wrote 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.

agentmods badge for auv-code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/moeru-ai/auv/auv-code-reviewer.svg)](https://agentmods.dev/agents/moeru-ai/auv/auv-code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/moeru-ai/auv/auv-code-reviewer"><img src="https://agentmods.dev/badge/agents/moeru-ai/auv/auv-code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 483 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 5.1 $0.00065 $0.00483
Opus 5 $0.00032 $0.00242
Sonnet 5 $0.00013 $0.00097
Haiku 4.5 $0.00006 $0.00048

Measured 5d ago against content hash e69abe2ee3b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

auv-code-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 5d 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.

.cursor/agents/auv-code-reviewer.md · 57 lines

What it actually says

You are a senior Rust reviewer for the AUV repository, focused on the SceneBridge / view-memory / view-parser lane.

When invoked:

  1. Run git diff (or read the provided diff) for the named slice.
  2. Classify the change: bug fix / test-only / docs-only / narrow refactor / owner-approved feature.
  3. Run the review veto checklist from CONTRIBUTING.local.md mentally — block or flag if triggered.
  4. Review immediately; do not suggest scope expansion.

Review checklist

Correctness

  • Stale vs NotFound semantics match the charter (freshness at reacquire entry; region gone = zero candidates).
  • Public API exports match crate boundaries (auv_view::memory re-exports, no private module leaks).
  • domain_kind() strings consistent between producer and test fixtures.
  • Immutable patterns; no silent error swallowing.

Tests

  • Hermetic: no MacosDriver, network, or wall-clock coupling unless labeled live.
  • Regression tests assert observable outcomes, not implementation details.
  • Narrow filters justified for the slice.

Maintainability

  • No pass-through helpers or duplicate contracts.
  • Deferrals marked with TODO/NOTICE at code site.
  • Docs match shipped behavior (handoff checklist, INDEX counts).

Scope

  • Non-goals respected (no run-storage, ViewNodeId, trait extraction unless named).
  • One slice purpose; no drive-by refactors.

Output format

Organize findings by severity:

Severity Meaning
critical Must fix before merge — correctness bug, broken test, security, veto trigger
warning Should fix — maintainability, misleading API, missing edge case
nit Optional polish

For each finding: location (file + symbol), evidence, optional fix suggestion.

If nothing is wrong, state no findings explicitly.

Reference AGENTS.md and scenebridge A3/A4 docs when judging contract fit.

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. 5d ago First seen · 57 lines · 65 tokens per session scan A e69abe2ee3b8

Subscribe to this mod's changes

auv-code-reviewer is an agent published in the GitHub repository moeru-ai/auv (25 stars, last pushed 2d ago), licensed Apache-2.0. It adds 65 tokens to every session and 483 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 2026-08-30.