parallel-review

A command that runs three kinds of code review in parallel, combines their findings, and applies selected fixes. Code review is the process of checking code for defects, project-rule violations, and avoidable complexity.

In plain words
What is it for?
Use it to review code with Codex Review, check CLAUDE.md instructions, detect AI-generated code noise, resolve conflicting findings, and report remaining issues.
Why use it?
It brings several independent checks into one repeatable review and limits repeated review rounds to three.

Command

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/mh4gf/claude-code/parallel-review
Clone the repo
git clone --depth 1 https://github.com/MH4GF/claude-code
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 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 $0.00040 $0.00738
Opus 5 $0.00020 $0.00369
Sonnet 5 $0.00008 $0.00148
Haiku 4.5 $0.00004 $0.00074

Measured 2d ago against content hash 4f7437443632, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parallel-review 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.

user-scope/commands/parallel-review.md · 62 lines

What it actually says

Task

以下の 3 つのレビューを並列で実行し、結果を統合して報告する。

実行するレビュー

  1. codex-review — codex review CLI によるコードレビュー
  2. claude-md-checker — CLAUDE.md 準拠チェック (ユーザースコープ agent)
  3. deslop — AI 生成コード由来のノイズ(過剰コメント・防御的 try/catch・any キャスト等)を検出(Skill ツール経由)

実行方法

以下を同時に起動する:

Agent tool: subagent_type: "claude-md-checker" → CLAUDE.md 準拠チェック
Skill tool: skill: "codex-review" → コードレビュー
Skill tool: skill: "deslop" → AI 生成ノイズ検出

出力形式

各レビューの結果を以下の形式でまとめる:

## レビュー結果サマリー

### Codex Review
[結果]

### CLAUDE.md Checker
[結果]

### Deslop
[結果]

## 対応が必要な項目
[優先度の高い指摘をリストアップ]

レビュー後の修正

レポート出力後、「対応が必要な項目」に挙げた指摘を処理する。

  • 各指摘について該当ファイルを編集し、問題を解消する
  • 対応せずに見送る指摘は、理由を 1 行添えて「プッシュバック」として記録する
  • 修正完了後、最終的な変更サマリーを報告する

再実行の停止条件

3 ツールはいずれも非決定的で、毎ラウンド別の指摘を出す。「指摘ゼロ」は停止条件として機能しないため、次の 3 つで打ち切る。

  1. ラウンド上限は 3。3 ラウンド目を終えたら、未対応の指摘が残っていても再実行せず、残件を一覧にして報告し停止する
  2. コード変更を伴う対応をしなかったラウンドの後は再実行しない。プッシュバックと起票だけで終えたラウンドは、再実行しても同じ入力に同じツールを当てるだけになる
  3. プッシュバックした指摘は蒸し返さない。次ラウンドで同じ指摘が再出現しても対応対象から除外する。ラウンドをまたいでプッシュバック一覧を保持し、再実行時にツールの出力と突き合わせてから対応要否を判断する

ツール同士の指摘が矛盾した場合は、どちらを採ったかと理由を記録して 1 つに決める。両方を満たそうとして往復しない。

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 · 62 lines · 40 tokens per session scan A 4f7437443632

Subscribe to this mod's changes

parallel-review is a command published in the GitHub repository MH4GF/claude-code (2 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 738 once invoked, about $0.0002 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 2026-08-31.