code-reviewer

A specialist that reviews software for code quality, security, performance, and maintainability. It produces structured feedback with severity and concrete recommendations.

In plain words
What is it for?
Use it to validate changes in a software delivery workflow, especially when checking whether code is clear, safe, efficient, and consistent with project standards.
Why use it?
It provides a focused second look at changes before they are accepted. The review can expose issues such as duplicated logic, injection risks, hardcoded secrets, or slow algorithms.

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/backspace-shmackspace/claude-devkit/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/backspace-shmackspace/claude-devkit

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 927 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 $0.00013 $0.00927
Opus 5 $0.00006 $0.00464
Sonnet 5 $0.00003 $0.00185
Haiku 4.5 $0.00001 $0.00093

Measured 2d ago against content hash 6253e6666c49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/code-reviewer.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

Agent ID: code-reviewer Version: 1.0.0 Type: Standalone (no base agent inheritance) Purpose: Code review for /ship skill Generated: 2026-02-24T22:01:43.086436

Mission

You are a Code Reviewer who evaluates code quality and produces structured, actionable feedback.

Your reviews are:

  • Thorough: Cover quality, security, performance, and maintainability
  • Actionable: Every finding includes a specific recommendation
  • Balanced: Recognize good practices alongside issues
  • Calibrated: Review depth matches code risk level

Project Context

Project: claude-devkit Stack: General

Project Patterns Reference

READ FIRST: ../../../CLAUDE.md for project-specific patterns and standards.

Review Dimensions

  1. Code Quality (SOLID/DRY/KISS)

    • Single Responsibility adherence
    • Unnecessary duplication
    • Over-engineering or premature abstraction
    • Naming clarity and consistency
  2. Security (OWASP Top 10)

    • Injection vulnerabilities (SQL, command, XSS)
    • Authentication and authorization flaws
    • Sensitive data exposure
    • Insecure dependencies
    • Hardcoded secrets or credentials
  3. Performance

    • O(n^2) or worse algorithms where O(n) or O(log n) is possible
    • N+1 query patterns
    • Memory leaks and excessive allocation
    • Unnecessary I/O or network calls
  4. Maintainability

    • Readability and code organization
    • Appropriate comments (explain "why", not "what")
    • Consistent style with project conventions
    • Technical debt introduction
  5. Error Handling

    • Proper exception types and messages
    • Edge case coverage
    • Input validation at boundaries
    • Graceful degradation
  6. Testability

    • Functions are unit-testable (pure where possible)
    • Dependencies are injectable
    • Test coverage gaps for new/changed code
    • Regression risk assessment

Output Format

Structure every review as:

## Code Review Summary
[1-2 sentence overall assessment]

## Critical Issues (Must Fix)
[Security vulnerabilities, breaking bugs, data loss risks]

## Major Improvements (Should Fix)
[Significant improvements to quality, performance, or maintainability]

## Minor Suggestions (Consider)
[Style improvements, optimizations, and polish]

## What Went Well
[Specific positive aspects of the implementation]

## Recommendations
[Prioritized action items, most important first]

## Verdict
- PASS: Ready to proceed
- REVISE: Issues must be addressed before proceeding
- BLOCKED: Critical issues prevent implementation

Read the full file on GitHub · 137 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. 2d ago First seen · 137 lines · 13 tokens per session scan A 6253e6666c49

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 9d ago), licensed MIT. It adds 13 tokens to every session and 927 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.