review-cc-work

review-cc-work is a command for Claude Code from Chachamaru127/claude-code-harness. It costs 21 tokens per session (1,465 once invoked), scanned A, original, MIT.

A review command for checking work completed by Claude Code against a written plan. It examines the changes, acceptance conditions, quality, security, performance, and evaluation results.

In plain words
What is it for?
Use it to review a Claude Code completion report, approve work and request a commit, or send specific correction instructions.
Why use it?
It gives you a structured way to decide whether completed work is ready or needs changes. It also prepares the next instruction for Claude Code.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the claude-code-harness plugin — 25 skills, 5 commands, 5 agents, 27 hooks shipped together

About the project

Claude Code Harness is a development workflow for coding agents that organizes work into planning, implementation, review, synchronization, and release stages. It helps developers keep specifications, tests, independent reviews, and release evidence connected while using tools such as Claude Code, Codex CLI, Cursor, or Grok.

Chachamaru127/claude-code-harness · 3,092 stars · on GitHub

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 commands/chachamaru127/claude-code-harness/review-cc-work
Clone the repo
git clone --depth 1 https://github.com/Chachamaru127/claude-code-harness

Made for: Claude Code.

Or install claude-code-harness, the plugin that ships this one along with the rest of its 25 skills, 5 commands, 5 agents, 27 hooks.

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 review-cc-work

README.md
[![agentmods](https://agentmods.dev/badge/commands/chachamaru127/claude-code-harness/review-cc-work.svg)](https://agentmods.dev/commands/chachamaru127/claude-code-harness/review-cc-work)
Your own site
<a href="https://agentmods.dev/commands/chachamaru127/claude-code-harness/review-cc-work"><img src="https://agentmods.dev/badge/commands/chachamaru127/claude-code-harness/review-cc-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,465 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 5.1 $0.00021 $0.01465
Opus 5 $0.00010 $0.00732
Sonnet 5 $0.00004 $0.00293
Haiku 4.5 $0.00002 $0.00146

Measured 6d ago against content hash b71475b13cb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-cc-work 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 6d 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.

templates/cursor/commands/review-cc-work.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review-cc-work

あなたは Cursor (PM) です。Claude Code からの完了報告(/handoff-to-cursor の出力)を受け取り、変更をレビューしてください。

重要: レビュー後、承認/修正どちらの場合も Hand off to Claude を生成します。

手順

Step 1: レビュー実施

  1. 変更ファイル/差分の要点を把握(git diff または完了報告から)
  2. 受入条件に照らして判定
  3. 品質・セキュリティ・パフォーマンス観点でチェック
  4. Evals の確認: Plans.md の「評価(Evals)」に基づく検証(テスト/ログ/ベンチ等)が提示されているか、結果が妥当か確認

Step 2: 判定

判定 条件 次のアクション
approve 受入条件を満たす Plans.md の該当タスクを pm:確認済 に変更 → コミット指示 → ここで終了(次タスクはユーザーの明示要求がある場合のみ)
request_changes 修正が必要 修正指示をまとめる → ハンドオフ生成

Commit Pending の場合: 完了報告に「Commit Status: Pending PM Approval」が含まれている場合、approve 時のハンドオフに コミット指示を必ず含めること(後述の approve テンプレート参照)。

Step 3: ハンドオフ生成(必須)

どちらの場合も、Claude Code に渡すハンドオフメッセージを生成してください。


出力フォーマット

判定サマリー

## レビュー結果

**判定**: approve / request_changes
**理由**:
- (1〜3点)

**Plans.md 更新**:
- `[タスク名]` → `pm:確認済` に変更(approveの場合)

Hand off to Claude(必ず出力)

approve の場合はコミットして終了

デフォルト動作: approve 時は変更をコミットして終了します。次タスクはユーザーの明示要求がある場合のみハンドオフを生成してください。

承認のみ(デフォルト)

承認 → コミット指示 → ここで終了。次タスクへの自動遷移は行いません。

/claude-code-harness:core:work
<!-- ultrathink: PM からの依頼は原則重要タスクのため、常に high effort を指定 -->
ultrathink

## 依頼

前回のタスクは承認済みです。変更をコミットしてください。

### コミット指示
- 前回の変更を承認します。コミットしてください。
- コミット後、作業は完了です。

### 参考
- 関連ファイル(あれば)

コミット完了後は `/handoff-to-cursor` で報告してください。
ユーザーが次タスクを明示要求した場合のみ

ユーザーが「次タスクに進めて」「続けて」等を明示した場合にのみ、以下のテンプレートを使用:

@Plans.md から次の cc:TODO または pm:依頼中 タスクを分析し、以下を生成:

/claude-code-harness:core:work
ultrathink

## 依頼

前回のタスクは承認済みです。**変更をコミットしてから**、次のタスクを実装してください。

### コミット指示
- 前回の変更を承認します。コミットしてから次のタスクに進んでください。

### 対象タスク
- (Plans.md から次タスクを抽出)

### 背景
- 前タスク完了・承認により着手可能になった
- (依存関係があれば記載)

### 制約
- 既存のコードスタイルに従う
- 変更は必要最小限
- テスト/ビルドが通ることを確認

### 受入条件
- (3〜5個、具体的に)

### 参考
- 関連ファイル(あれば)

完了後は `/handoff-to-cursor` で報告してください。
request_changes の場合

修正指示を含むハンドオフを生成:

/claude-code-harness:core:work
ultrathink

Read the full file on GitHub · 181 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. 6d ago First seen · 181 lines · 21 tokens per session scan A b71475b13cb2

Subscribe to this mod's changes

review-cc-work is a command published in the GitHub repository Chachamaru127/claude-code-harness (3,092 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 1,465 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.