cc-recommender: Command for Claude Code

.claude/commands/dependabot-review.md

dependabot-review is a command for Claude Code from yuji0809/cc-recommender. It costs 18 tokens per session (873 once invoked), scanned A, original, MIT.

A command for reviewing Dependabot pull requests. Dependabot is a service that automatically proposes updates to a project's packages and dependencies.

In plain words
What is it for?
Use it to review one Dependabot pull request or all open Dependabot requests, assess compatibility and security concerns, and post an approval, comment, or change request.
Why use it?
It gathers the relevant changes and checks so you can judge update risk without manually inspecting every dependency-update request.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is yuji0809/cc-recommender's own configuration. It tells Claude Code how to work on cc-recommender itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cc-recommender configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yuji0809/cc-recommender. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yuji0809/cc-recommender/main/.claude/commands/dependabot-review.md
Clone the repo
git clone --depth 1 https://github.com/yuji0809/cc-recommender

Made for: Claude Code.

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 dependabot-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/yuji0809/cc-recommender/dependabot-review/github.svg)](https://agentmods.dev/commands/yuji0809/cc-recommender/dependabot-review)
Your own site
<a href="https://agentmods.dev/commands/yuji0809/cc-recommender/dependabot-review"><img src="https://agentmods.dev/badge/commands/yuji0809/cc-recommender/dependabot-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dependabot-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/yuji0809/cc-recommender/dependabot-review"><img src="https://agentmods.dev/badge/commands/yuji0809/cc-recommender/dependabot-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 873 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00018 $0.00873
Opus 5 $0.00009 $0.00436
Sonnet 5 $0.00004 $0.00175
Haiku 4.5 $0.00002 $0.00087

Measured 9d ago against content hash 3203ea1b8c42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dependabot-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 9d 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/dependabot-review.md · 86 lines

What it actually says

Dependabot PR レビュー

このコマンドは、Dependabot が作成した依存関係更新PRを分析し、レビューコメントを投稿します。

引数

  • $ARGUMENTS にPR番号が指定された場合、そのPRのみを分析
  • 引数なしの場合、全てのオープンなDependabot PRを分析

実行手順

1. 対象PRの取得

PR番号指定あり($ARGUMENTS が空でない場合):

gh pr view $ARGUMENTS --json title,body,commits,files,statusCheckRollup,mergeable,additions,deletions,headRefName,baseRefName,author

PR番号指定なし:

gh pr list --state open --json number,title,author,labels,url --jq '.[] | select(.author.login == "app/dependabot")'

Dependabot PRが見つからない場合は、その旨をユーザーに報告して終了してください。

2. 各PRの詳細分析

Dependabot Review Agent を使用して、各PRに対して以下の分析を実行してください。 複数PRがある場合は並列でエージェントを起動します。

各エージェントに渡す指示:

Dependabot PR #<番号> を分析してください。

以下の手順で実行:
1. `gh pr view <番号> --json title,body,commits,files,statusCheckRollup,mergeable,additions,deletions` でPR情報を取得
2. `gh pr diff <番号>` で差分を確認
3. PRのbodyからリリースノート・チェンジログを確認
4. 以下を分析:
   - パッケージ名、更新タイプ(patch/minor/major)、依存種別(deps/devDeps/actions)
   - CIステータス(全チェックの成功/失敗)
   - 破壊的変更の有無
   - セキュリティ修正の有無
   - 互換性の懸念
5. リスク評価(Low/Medium/High)を決定
6. レビューコメントを `gh pr review` で投稿
   - Approve: 全CIパス+リスク低〜中
   - Comment: メジャー更新で要注意
   - Request Changes: CI失敗またはセキュリティ懸念
7. 分析結果のサマリーを返す

3. サマリーの表示

全PRの分析完了後、以下の形式でユーザーにサマリーを表示:

## Dependabot PR レビュー結果

| PR | パッケージ | 種別 | 更新 | CI | リスク | 判定 |
|----|----------|------|------|----|--------|------|
| #XX | pkg-name | devDeps | 1.0→2.0 (Major) | PASS | Low | Approve |

### 推奨マージ順序
1. セキュリティ修正を含むPR(最優先)
2. パッチ更新(リスク低)
3. マイナー更新
4. メジャー更新(慎重に)

### 注意事項
- (各PRの注意点があれば記載)

注意事項

  • 各PRのレビューは独立して実行可能なため、並列処理を推奨
  • セキュリティ修正を含むPRは優先的に処理すること
  • CIが失敗しているPRは原因を調査し、ユーザーに報告すること
  • ランタイム依存のメジャー更新は特に慎重に分析すること
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. 9d ago First seen · 86 lines · 18 tokens per session scan A 3203ea1b8c42

Subscribe to this mod's changes

dependabot-review is a command published in the GitHub repository yuji0809/cc-recommender (10 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 873 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 2026-08-31.