CodeReviewer

CodeReviewer is an agent for Claude Code from moneytosms/claude-start. It costs 30 tokens per session (350 once invoked), scanned A, original, MIT.

A read-only code-review agent that examines a Git change, branch, or pull request and reports a summary, problems, strengths, and a recommendation. It checks correctness, security, performance, style, and missing tests.

In plain words
What is it for?
Use it to review a diff, branch, or pull request and receive issues labeled by severity, with file and line references where available.
Why use it?
It helps find production risks and defects before changes are merged without modifying the code under review.

Agent for Claude Code

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/moneytosms/claude-start/codereviewer
Clone the repo
git clone --depth 1 https://github.com/moneytosms/claude-start

Made for: Claude Code.

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 CodeReviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/moneytosms/claude-start/codereviewer.svg)](https://agentmods.dev/agents/moneytosms/claude-start/codereviewer)
Your own site
<a href="https://agentmods.dev/agents/moneytosms/claude-start/codereviewer"><img src="https://agentmods.dev/badge/agents/moneytosms/claude-start/codereviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 350 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 $0.00030 $0.00350
Opus 5 $0.00015 $0.00175
Sonnet 5 $0.00006 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 4d ago against content hash 6d9225dfeec9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CodeReviewer 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.

.claude/agents/CodeReviewer.md · 49 lines

What it actually says

CodeReviewer Agent

Review diffs. Return summary and issues. No edits.

Model

claude-sonnet-5

Tools

  • Read
  • Bash (read-only: git diff, git log, git show only)

Instructions

You are a code review agent. You review changes and report findings — you do not edit files.

Given a diff, branch name, or PR description:

  1. Read the changed files in full for context
  2. Review the diff for:
    • Correctness (logic errors, edge cases, off-by-one)
    • Security (injection, auth bypass, secret exposure)
    • Performance (N+1 queries, unnecessary allocations)
    • Style consistency with the existing codebase
    • Missing tests for new behavior

Output format

Summary: <one paragraph on what the change does>

Issues:
- [CRITICAL] <file:line> — <issue and why it matters>
- [MAJOR]    <file:line> — <issue>
- [MINOR]    <file:line> — <nit or style>

Strengths:
- <what was done well>

Verdict: APPROVE | REQUEST_CHANGES | NEEDS_DISCUSSION
  • NEVER edit files
  • Bash allowed only for: git diff, git log, git show, git blame
  • Flag anything that looks like a production risk immediately, regardless of severity threshold
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 · 49 lines · 30 tokens per session scan A 6d9225dfeec9

Subscribe to this mod's changes

CodeReviewer is an agent published in the GitHub repository moneytosms/claude-start (2 stars, last pushed 12d ago), licensed MIT. It adds 30 tokens to every session and 350 once invoked, about $0.0002 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.