apply-review

A command that records architecture-review findings in a project’s design document. It handles “Must Fix” and “Should Fix” items, but does not change source code.

In plain words
What is it for?
Use it to apply all review findings, only required findings, or selected findings to the design document for a numbered issue.
Why use it?
It keeps review decisions and implementation guidance in one design document, so developers can use them later without altering code automatically.

Command for Claude Code

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/kewton/commandmate/apply-review
Clone the repo
git clone --depth 1 https://github.com/Kewton/CommandMate

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,374 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 $0.00010 $0.01374
Opus 5 $0.00005 $0.00687
Sonnet 5 $0.00002 $0.00275
Haiku 4.5 $0.00001 $0.00137

Measured 2d ago against content hash 5e950fa83b41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

apply-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.

.claude/commands/apply-review.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

レビュー指摘反映コマンド

概要

アーキテクチャレビューの指摘事項(Must Fix, Should Fix)を設計方針書に反映するコマンドです。

重要: このコマンドは設計方針書のみを更新します。 ソースコードの実装は行いません。レビュー結果を設計方針書に反映し、 実装時の指針として活用します。

使用方法

/apply-review [Issue番号]
/apply-review [Issue番号] --scope=must_fix
/apply-review [Issue番号] --skip="項目1,項目2"

:

/apply-review 76                    # 全指摘事項を反映
/apply-review 76 --scope=must_fix   # 必須項目のみ
/apply-review 76 --skip="パフォーマンス最適化"  # 特定項目をスキップ

実行内容

あなたはレビュー指摘反映の統括者です。サブエージェントを使用して指摘事項を実装に反映します。

パラメータ

  • issue_number: 対象Issue番号(必須)
  • scope: 反映範囲(all|must_fix|should_fix)デフォルト: all
  • skip: スキップする項目(カンマ区切り)

実行フェーズ

Phase 1: レビュー結果の確認

1-1. レビュー結果ファイルの検索
ls dev-reports/issue/{issue_number}/review/review-result.json
# または
ls dev-reports/review/*-issue{issue_number}-*.md
1-2. レビュー結果の読み込み

レビュー結果JSONから以下を抽出:

  • Must Fix: 必須改善項目
  • Should Fix: 推奨改善項目
  • Consider: 検討事項(今回は対象外)

Phase 2: コンテキストファイル作成

ファイルパス: dev-reports/issue/{issue_number}/review/apply-review-context.json

{
  "issue_number": {issue_number},
  "review_result_path": "dev-reports/issue/{issue_number}/review/review-result.json",
  "design_doc_path": "dev-reports/design/issue-{issue_number}-xxx-design-policy.md",
  "scope": "all",
  "skip_items": [],
  "additional_instructions": ""
}

Phase 3: サブエージェント呼び出し

Use apply-review-agent to update design policy for Issue #{issue_number}.
Target: dev-reports/design/issue-{issue_number}-*-design-policy.md

Context file: dev-reports/issue/{issue_number}/review/apply-review-context.json
Output file: dev-reports/issue/{issue_number}/review/apply-review-result.json

IMPORTANT: Only update design policy documents. Do NOT modify source code.

Phase 4: 結果確認と報告

4-1. 結果ファイルの確認

apply-review-result.json を読み込み、以下を確認:

  • 設計方針書に反映した項目数
  • スキップした項目
  • 追加された実装チェックリスト
4-2. 設計方針書の更新確認

設計方針書の内容を確認:

  • レビュー指摘事項が適切に反映されているか
  • 実装チェックリストが網羅的か
  • 次のアクション(実装コマンド)の提案

Read the full file on GitHub · 173 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. 2d ago First seen · 173 lines · 10 tokens per session scan A 5e950fa83b41

Subscribe to this mod's changes

apply-review is a command published in the GitHub repository Kewton/CommandMate (39 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 1,374 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.