review

review is a command for coding agents from bravew/trove. It costs 9 tokens per session (971 once invoked), scanned A, original, MIT.

A project-aware code-review command that examines changes against the codebase, project rules, and relevant quality checks.

In plain words
What is it for?
Use it on staged changes, selected files, a pull request, or a branch, with checks for projects such as Python, JavaScript, React, Next.js, and Swift.
Why use it?
It helps find real bugs and maintainability problems while reducing false alarms caused by reviewing files without their full context.

Command

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 commands/bravew/trove/review
Clone the repo
git clone --depth 1 https://github.com/bravew/trove

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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/bravew/trove/review.svg)](https://agentmods.dev/commands/bravew/trove/review)
Your own site
<a href="https://agentmods.dev/commands/bravew/trove/review"><img src="https://agentmods.dev/badge/commands/bravew/trove/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 971 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 $0.00009 $0.00971
Opus 5 $0.00005 $0.00485
Sonnet 5 $0.00002 $0.00194
Haiku 4.5 $0.00001 $0.00097

Measured 4d ago against content hash c595846de3a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

commands/review.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Review scope: $ARGUMENTS

If a PRP file was used for implementation, read it first to understand the requirements.

Process

  1. Identify changes to review:

    • No args: review staged changes via git diff --staged
    • File paths: read the specified files
    • PR number: gh pr view <number> --json files,additions,deletions
    • Branch: detect base branch, then git diff origin/$BASE...HEAD
  2. Detect project stack from config files (pyproject.toml, package.json, Package.swift, next.config.*, etc.) to apply stack-specific review criteria.

  3. Read the FULL context — read complete files to understand structure and data flow before flagging issues. Verify issues are ACTUAL bugs, not false positives.

  4. Apply project rules — if .claude/rules/ exists, read and apply all rules found there.

  5. Run quality checks using project-appropriate tooling:

    Stack Commands
    Python ruff check ., ruff format --check .
    Node/React/Vue pnpm lint or npm run lint, pnpm type-check
    Next.js npm run lint, npm run type-check
    Swift swiftlint, swift build

Universal Review Focus

1. Code Quality

  • Naming: clear, consistent, follows project conventions
  • Structure: well-organized, single responsibility
  • Error handling: comprehensive, no silent failures
  • Type safety: proper types, no unsafe casts or any

2. Security

  • No exposed secrets, API keys, tokens, or credentials in code or logs
  • Input validation on all user-facing boundaries
  • Authentication/authorization correctly enforced
  • Injection prevention (SQL, XSS, command injection)

3. Performance

  • No unnecessary allocations or re-renders
  • No N+1 queries or unbounded loops
  • Proper caching and memoization where appropriate

4. Stack-Specific Patterns

Python/FastAPI:

  • Top-level imports only (no inline imports)
  • Async patterns: proper await, no blocking calls in async
  • SQLAlchemy: eager loading, proper transactions
  • Logging: logger.exception() in handlers, extra={} for WARNING/ERROR

Read the full file on GitHub · 139 lines

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. 4d ago First seen · 139 lines · 9 tokens per session scan A c595846de3a0

Subscribe to this mod's changes

review is a command published in the GitHub repository bravew/trove (10 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 971 once invoked, about $0.0000 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.