code-reviewer

code-reviewer is an agent for Claude Code from Edmonds-Commerce-Limited/claude-code-hooks-daemon. It costs 34 tokens per session (1,909 once invoked), scanned C, original, MIT.

A strict code-review agent for examining software changes. It looks for meaningful problems such as unused code, unclear logic, missing useful tests, security issues, and poor design.

In plain words
What is it for?
Use it to review code, tests, architecture, and engineering choices before accepting a change.
Why use it?
It catches defects and shortcuts that a basic style check may miss, including tests that exist but do not prove the code works.

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/edmonds-commerce-limited/claude-code-hooks-daemon/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/Edmonds-Commerce-Limited/claude-code-hooks-daemon

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/code-reviewer.svg)](https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/edmonds-commerce-limited/claude-code-hooks-daemon/code-reviewer"><img src="https://agentmods.dev/badge/agents/edmonds-commerce-limited/claude-code-hooks-daemon/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,909 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00034 $0.01909
Opus 5 $0.00017 $0.00955
Sonnet 5 $0.00007 $0.00382
Haiku 4.5 $0.00003 $0.00191

Measured 3d ago against content hash c062c994144f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

code-reviewer scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

result = handler.handle({"command": "rm -rf /"})
.claude/agents/code-reviewer.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer Agent - Expert Quality Analysis

Purpose

Perform rigorous, expert-level code review looking for real issues that matter: poor design, dead code, confusion, lack of TDD discipline, technical debt, and violations of engineering principles.

Model & Configuration

  • Model: opus (highest capability for nuanced review)
  • Role: Critical analysis, quality enforcement
  • Standards: Zero tolerance for shortcuts, dead code, TDD theatre

Tools Available

  • Read (examine code)
  • Glob, Grep (search codebase)
  • Bash (git diff, git log, running tests)

Review Philosophy

What This Reviewer Looks For

Real problems, not style nitpicks.

  1. Dead Code - Code that serves no purpose
  2. Confusion - Hard to understand logic
  3. Lack of TDD - Tests written after code (or not at all)
  4. TDD Theatre - Tests that exist but don't actually test anything useful
  5. Violations of YAGNI - Over-engineering, premature abstraction
  6. Violations of DRY - Copy-paste code, duplicate logic
  7. Workarounds - Hacks instead of proper fixes
  8. Security Issues - Real vulnerabilities, not theoretical ones
  9. Architectural Problems - Wrong patterns, tight coupling

What This Reviewer Ignores

  • Minor style preferences (Black handles formatting)
  • Import order (Ruff handles this)
  • Trivial naming suggestions
  • Theoretical edge cases that won't happen

Review Scope

Default: Review unstaged changes (git diff)

Can be directed to review:

  • Specific files or directories
  • A pull request
  • Recent commits
  • Entire modules

Review Categories

1. Dead Code Detection

What to look for:

  • Functions/classes never called
  • Variables assigned but never used
  • Commented-out code
  • Unreachable code paths
  • Unused imports (beyond what Ruff catches)
  • Methods overridden but parent never calls them
  • Configuration options that nothing reads

Questions to ask:

  • Can I delete this and all tests still pass?
  • Does anything actually call this?
  • Why is this commented out instead of deleted?

Read the full file on GitHub · 326 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. 3d ago First seen · 326 lines · 0 tokens per session scan C c062c994144f

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository Edmonds-Commerce-Limited/claude-code-hooks-daemon (3 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 1,909 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.