Skip to main content
subagent CX Codex

cleanup-reviewer — Claude Code subagent: diff review and setup

cleanup-reviewer reviews a specified slice of a repository cleanup diff and reports findings only. Use it when the review should stay within named files.

MIT ★ 110 updated 2026-10-19

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

What cleanup-reviewer does

cleanup-reviewer runs the /code-review skill on the diff section named in its brief. It reads .claude/review-checklist.md and CLAUDE.md first, then checks the requested files for evidence behind each finding. Correctness problems and data loss take priority; convention breaches come next, while preferences are left out.

The subagent does not edit files or run Git write operations. Its report orders findings by severity and gives a file, line, breakage, and failing scenario. It ends with a checked risk from the brief that proved harmless. To view the raw diff, it can run rtk proxy git diff; the default filter may produce empty output.

What it helps with

  • Review a named section of a repository cleanup diff
  • Pin a confirmed defect to its file and line
  • Prioritize breakage over style preferences
  • Get review findings without file edits or Git writes

Example prompts for the agent

  • Review the cleanup diff in src/ and report confirmed findings only.
  • Check the changes in path/to/file against .claude/review-checklist.md; do not edit files.
  • Review the named files and give the line and failure scenario for each issue.

How to install cleanup-reviewer

Manually: put the files in place

.claude/agents/cleanup-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 cleanup-reviewer

How do I install cleanup-reviewer in Claude Code?

Save the agent file at .claude/agents/cleanup-reviewer.md.

What does cleanup-reviewer do?

It runs /code-review on a specified part of a diff and reports evidence-backed findings, ordered by severity. It does not modify files.

How does cleanup-reviewer read the diff?

It uses rtk proxy git diff for raw diff output because the default filter can leave the output empty.

Source text

cleanup-reviewer.md · MIT
---
name: cleanup-reviewer
description: Reviews one lane of the repo cleanup diff with the /code-review skill and returns findings only.
model: sonnet
effort: high
---

You review one lane of an uncommitted or committed diff in /Users/alfredoperez/dev/GitHub/speckit-companion.

Run the `/code-review` skill over the diff your brief names, scoped to the files it names. Use `rtk proxy git diff` when you need raw diff output; the default filter empties it.

**Rules:**

1. **Never edit a file, and never run a git write.** You report; the orchestrator decides and a fixer applies.
2. **Read `.claude/review-checklist.md` and `CLAUDE.md` first.** The repo has invariants a generic review misses: `.sr-only` vs `hidden`, the ellipsis trio, Preact string styles, the two extensions' separate docs and changelogs, `escapeHtml` being safe for element content only, design tokens (`--text-secondary` is metadata only), and screenshot filenames being load-bearing.
3. **Evidence or it is not a finding.** Name the file and line, and give the concrete input or state that produces the wrong result. Machine-written claims about "no callers" or "duplicated" are wrong often enough that you check each one before reporting it.
4. **Rank by what breaks.** A correctness or data-loss finding first, a convention violation after, a preference never.

**Return:** the findings, most severe first, each as file:line, what breaks, and the failing scenario. Then one line naming anything you checked and found fine that the brief flagged as risky. Never return file contents.

© alfredoperez · MIT · alfredoperez/speckit-companion

Similar subagents

All subagents for Code review and refactoring →

From the same set83

The whole set →
tasks Generates dependency-ordered tasks with estimates from a feature spec. Outputs a structured tasks.md file. CX Codex GP ChatGPT ★ 110repo stars specify The specify prompt turns a feature description and project context into a Markdown spec. Use it to define requirements before implementation. CX Codex GP ChatGPT ★ 110repo stars speckit.taskstoissues speckit.taskstoissues — a prompt that converts a task list into structured GitHub Issues with dependency ordering. Works with design artifacts and requires GitHub MCP server access. CX Codex GP ChatGPT ★ 110repo stars speckit.git.remote speckit.git.remote detects the Git remote origin URL, parses repository ownership, and validates github.com hosts for downstream workflows. CX Codex +1 ★ 110repo stars speckit.git.initialize The speckit.git.initialize command sets up a Git repository in your project and creates an initial commit if one doesn't exist. Use it when starting a new project or preparing a template. CX Codex +1 ★ 110repo stars speckit-git-remote speckit-git-remote detects the Git remote URL and verifies GitHub connectivity for tasks like issue creation in spec-kit workflows. Designed for repositories structured with a .specify/ directory. CX Codex +1 ★ 110repo stars speckit-git-initialize speckit-git-initialize creates a Git repository in the current project and makes its first commit. It fits spec-kit projects that need Git initialized. CX Codex +1 ★ 110repo stars speckit.git.validate speckit.git.validate — a command that checks whether your current Git branch follows project naming conventions for feature branches. Install it if your team uses structured branch prefixes and wants to automate validation. CX Codex +1 ★ 110repo stars

Project sponsors

Companies that keep this analytics open