Skip to main content
subagent CX Codex

reviewer · ruvnet — Claude Code subagent: what it does, how to install

A reviewer persona for Claude that reads a change like a senior engineer: behaviour, security holes, slow paths, standards, docs. You get a summary with critical issues.

no license ★ 850 updated 2026-10-26

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/reviewer.md
Open on GitHub

What reviewer does

The agent takes the role of a senior reviewer and goes over a change on five fronts: what the code actually does, where it can be attacked, what will be slow, how it sits with the project's conventions, and whether the docs keep up. The file ships worked examples of the usual offenders — a raw userId interpolated into SQL, a password written to the log, a loop that fires one query per user, a class holding four unrelated jobs.

Two hooks bracket the run. Ahead of the review it pulls similar past reviews from claude-flow memory, including cases where problems slipped through, and writes a five-point checklist. Afterwards it saves a scored record of the outcome and, when nothing critical surfaced and more than 10 issues were found, starts a pattern training pass with npx claude-flow neural train.

Both hooks shell out to npx claude-flow. On a machine without that CLI the memory lookups and the training step never happen; you are left with the written checklist and whatever the model can do from the agent file alone.

What it helps with

  • catch an SQL injection in the payment handler
  • drop the N+1 when loading users with their posts
  • check whether one class is doing persistence, email and reports at once
  • produce a review summary with critical issues and strengths
  • match the API docs against what the code really does

Example prompts for the agent

  • Review src/api/payments.ts for amount validation and unsafe database queries.
  • Walk this pull request and point out slow paths like N+1 lookups.
  • Write up a review of the orders module with critical issues first.

How to install reviewer

Manually: put the files in place

.claude/agents/reviewer.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about reviewer

How do I install reviewer in Claude Code?

Place the subagent file at .claude/agents/reviewer.md.

What does reviewer do?

It reviews code on five fronts: behaviour, security, performance, coding standards and documentation. The output leads with strengths, then lists critical issues with line references.

Do the hooks need claude-flow?

Yes. Both hooks call npx claude-flow — one searches stored reviews, the other records the score and runs pattern training. Without that CLI those steps do not run.

Similar subagents

All subagents for Code review and refactoring →

reviewer by other authors comes first.

reviewer VoltAgent reviewer is a Codex subagent for PR-style checks of correctness, security, regressions, and test gaps. It joins tasks that call for a focused code review. CX Codex ★ 6,505repo stars reviewer Rohit Ghumare reviewer — a subagent that reviews code line by line, reading actual files and citing every finding with exact quotes. Use before committing, during PR review, or after major changes. CX Codex ★ 2,966repo stars reviewer mralexivy The reviewer subagent for Claude Code performs an independent audit of code changes. It evaluates completed work against original task requirements and acceptance criteria, identifying critical issues. CX Codex ★ 80repo stars ns-reviewer nextstage-brasil ns-reviewer grades code changes against SOLID principles, clean code patterns, performance, security, and testability. Approves only at score 10; score 9 triggers rejection. CX Codex +1 140installs qa-reviewer First Fluke qa-reviewer — a code review agent that scans for OWASP vulnerabilities, performance bottlenecks, accessibility gaps and code quality issues. Runs before you merge and flags each finding with severity and remediation. CX Codex ★ 1,472repo stars code-reviewer official Anthropic The code-reviewer subagent checks code changes for bugs, security issues, and project-rule violations. Use it when a review should focus on findings that matter. CX Codex 31,050installs gem-reviewer official github gem-reviewer is a GitHub Copilot subagent that performs independent reviews of plans, code, and configurations. It identifies risks and potential issues in development workflows. CX Codex +1 ★ 41,430repo stars code-documentation-code-reviewer Seth Hobson code-documentation-code-reviewer — a code review subagent that hunts for vulnerabilities, performance bottlenecks and configuration mistakes. Useful when changes head to production and you want a second pass. CX Codex ★ 42,780repo stars gsd-code-reviewer davepoon The gsd-code-reviewer subagent inspects code changes for bugs, vulnerabilities, and quality flaws, saving findings to REVIEW.md. It runs through /gsd:code-review or directly. CX Codex ★ 3,785repo stars

From the same set76

The whole set →
multi-repo-swarm multi-repo-swarm — a subagent for Claude Code that orchestrates multiple agents across your organization's repositories. Runs synchronized tasks, manages dependencies, and links pull requests between projects. CX Codex ★ 850repo stars consensus-coordinator consensus-coordinator — a Claude subagent that computes distributed consensus: Byzantine fault tolerance, voting and agreement across an agent swarm. CX Codex ★ 850repo stars specification SPARC specification subagent for requirements analysis. Gathers acceptance criteria, outlines project scope, and learns from previous patterns via claude-flow. CX Codex ★ 850repo stars pr-manager pr-manager coordinates pull request reviews, tests, and merge work through GitHub tools and a swarm of agents. It can also reuse patterns saved from earlier PR tasks. CX Codex ★ 850repo stars refinement SPARC refinement phase agent for iterative code polish. Drives test-driven development: creates failing tests, satisfies them, and cleans up structure. CX Codex ★ 850repo stars release-swarm release-swarm coordinates release work from change analysis and changelog preparation to builds, tests, and deployment across configured targets. CX Codex ★ 850repo stars sona-learning-optimizer sona-learning-optimizer — a subagent that logs every task as a trajectory and nudges quality up by reusing similar past patterns and LoRA fine-tuning. CX Codex ★ 850repo stars tester tester is a Claude Code subagent that creates tests and checks code, recording past failures in claude-flow. CX Codex ★ 850repo stars

Project sponsors

Companies that keep this analytics open