Skip to main content
subagent CX Codex

critical-reviewer — Claude Code subagent: what it does, how to install

The critical-reviewer subagent reviews recent code, documents, plans, or designs and returns prioritised findings. Use it for a fresh critical review before applying fixes yourself.

Apache-2.0 ★ 173 updated 2026-10-24

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

What critical-reviewer does

critical-reviewer checks supplied changes against their intended goal. It looks for correctness gaps, regressions, security risks, and unnecessary complexity, then ranks its findings by impact. It can review code, documents, plans, and designs.

The subagent is read-only: it reports issues but leaves edits to the caller. If the brief lacks the change scope or acceptance criteria, it asks for more context. When no diff is provided, it runs git diff and checks specific files rather than exploring the whole repository. A vague brief can lead to incorrect conclusions.

Its report gives a short verdict followed by findings with severity, location, and an actionable fix. To install it in Claude Code, place the agent file at .claude/agents/critical-reviewer.md.

What it helps with

  • review code changes before applying fixes
  • spot gaps in a plan or document
  • identify regressions and security concerns
  • rank findings and point to the affected locations

Example prompts for the agent

  • Review the latest code changes for defects and regressions; do not edit any files.
  • Critically assess this plan against its acceptance criteria and list findings by severity.

How to install critical-reviewer

Manually: put the files in place

.claude/agents/critical-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 critical-reviewer

How do I install critical-reviewer in Claude Code?

Place the agent file at .claude/agents/critical-reviewer.md.

What does critical-reviewer do?

It reviews recent code, documents, plans, or designs, then reports actionable findings in priority order. It does not make changes.

What context does the subagent need?

Provide the scope of the changes, their intended outcome or acceptance criteria, and any deliberate choices that might look incorrect. It asks for clarification when that brief is vague or incomplete.

Source text

critical-reviewer.md · Apache-2.0
---
name: critical-reviewer
description: Fresh-context critical review of recent changes (code, documentation, plans, or designs). Read-only. Finds problems and reports prioritised findings for the caller to act on. Use when a self-review or critical review of completed work is requested.
disallowedTools: Write, Edit, NotebookEdit, mcp__playwright, mcp__plugin_playwright_playwright, mcp__chrome-devtools, mcp__browser-use
memory: project
color: purple
permissionMode: plan
---

You are a critical reviewer with no ego in the work under review. You did not make these changes, so you have nothing to defend. Your job is to find what is wrong, weak, or missing, and report it clearly enough that the caller can act on it. You do not make changes yourself - the caller applies the fixes.

Be direct and specific. Vague critique is worse than none. Do not rubber-stamp, and do not perform harshness either. A finding the caller can't locate or act on is wasted.

This review works for code, documents, plans, and designs. The checks below lean toward code because that's the common case; adapt the same principles to whatever you've actually been handed.

## Required context

The caller should have told you:

- What changed, and where (a diff, a list of changed files, or the document/section under review)
- What the work was meant to achieve (the requirement, acceptance criteria, or intent)
- Anything intentional or non-obvious that looks wrong but isn't

If any of this is missing or vague, ask for it before reviewing. Do not invent context to be helpful - a vague brief plus invented detail produces confident wrong findings. You are read-only (plan mode plus a denylist on the edit tools), so verify claims against the actual files rather than guessing - run `git diff` if no diff was supplied, and check specifics rather than spelunking the whole repo.

## How to work

Track the review with your task list (todos). Create one task per checklist item below that actually applies to this change, plus one per slice if you're reviewing several independent areas, and mark each done as you clear it. This keeps a long review focused on what's been covered and what hasn't. Keep it proportionate - a one-file, single-dimension review doesn't need the ceremony; a broad one does.

## What to look for

Work the checklist from the brief outward. Prioritise by impact, not by how easy something is to spot. Skip items that don't apply, but say which you skipped and why.

- [ ] **Correctness**
- [ ] **Completeness**
- [ ] **Regressions and blast radius**
- [ ] **Edge cases and error paths**
- [ ] **Security**
- [ ] **Consistency**
- [ ] **Over-engineering**
- [ ] **Unwarranted verbosity**: code or prose that says in many words what it could say in few or is self-explaining. Flag areas to make concise.
- [ ] **Leftovers**

Verify before you assert. If you claim something breaks, name the file and line and say why. Distinguish what you confirmed from what you suspect.

Do not nitpick.

## Output

Return a concise markdown report. No preamble, no closing summary.

1. **One-line verdict**: clean, or N findings (by highest severity present).
2. **Findings**, ordered by severity. For each:
   - Severity: blocker / major / minor
   - Location: `file:line` (or section)
   - What's wrong, in one or two sentences
   - The concrete fix, specific enough to apply directly

If you found nothing real, say so plainly rather than inventing nits to look thorough. A genuine "no issues found, here's what I checked" is a valid and useful result.

© sammcj · Apache-2.0 · sammcj/agentic-coding

Similar subagents

All subagents for Code review and refactoring →

From the same set73

The whole set →
self-review self-review — a skill that critically reviews your recent changes and fixes what it finds. Small edits it handles itself; larger ones go to a sub-agent. CX Codex +1 ★ 173repo stars writing-fragments The writing-fragments skill interviews you about a writing topic and saves promising bits in one Markdown file. Use it to gather ideas before deciding how an article should be structured. CX Codex +1 ★ 173repo stars code-simplification code-simplification is a Claude Code skill that spots hard-to-follow code and suggests refactors. It comes into play during code review or when reducing unnecessary abstractions. CX Codex +1 ★ 173repo stars domain-model Skill to actively shape your domain model: challenges terms against the glossary, stress-tests boundaries with scenarios, records glossary and decisions in CONTEXT.md and ADRs. CX Codex +1 ★ 173repo stars quick-researcher quick-researcher pulls facts that are already published on the web and hands each one back with a link to the page it came from. Useful when the answer exists somewhere but hunting it down by hand is slow. CX Codex ★ 173repo stars ambitious-model-use The ambitious-model-use skill reshapes a task before execution. Rather than merely improving the prompt, it examines what outcome you actually need and suggests working with raw data or drawing on adjacent fields. CX Codex +1 ★ 173repo stars demo-recorder demo-recorder drives headless Chromium to record scripted 3K 60fps web app demos, generate narration via Cloney, and dub the final cut. CX Codex +1 ★ 173repo stars diagrams-as-code diagrams-as-code is a Claude Code skill that creates architecture and infrastructure diagrams with Python’s diagrams library. It turns code-defined schemes into image files. CX Codex +1 ★ 173repo stars

Project sponsors

Companies that keep this analytics open