review-pr

review-pr is a skill for Claude Code from nanasess/eccube-dev-agents. It costs 13 tokens per session (3,129 once invoked), scanned C, original, MIT.

A read-only review of a GitHub pull request, with suggested comments attached to specific changed lines. It does not publish the review.

In plain words
What is it for?
It helps inspect the pull request description, code differences, existing comments, and related context, then draft findings and a review decision.
Why use it?
It lets you examine proposed changes and prepare feedback without sending anything before you approve the draft.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the eccube-dev-agents plugin — 8 skills shipped together

Good fit It helps inspect the pull request description, code differences, existing comments, and related context, then draft findings and a review decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nanasess/eccube-dev-agents/review-pr
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.

Any agent
npx skills add nanasess/eccube-dev-agents --skill review-pr
Clone the repo
git clone --depth 1 https://github.com/nanasess/eccube-dev-agents

Made for: Claude Code.

Or install eccube-dev-agents, the plugin that ships this one along with the rest of its 8 skills.

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-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/nanasess/eccube-dev-agents/review-pr/github.svg)](https://agentmods.dev/skills/nanasess/eccube-dev-agents/review-pr)
Your own site
<a href="https://agentmods.dev/skills/nanasess/eccube-dev-agents/review-pr"><img src="https://agentmods.dev/badge/skills/nanasess/eccube-dev-agents/review-pr/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 review-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/nanasess/eccube-dev-agents/review-pr"><img src="https://agentmods.dev/badge/skills/nanasess/eccube-dev-agents/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,129 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00013 $0.03129
Opus 5 $0.00006 $0.01564
Sonnet 5 $0.00003 $0.00626
Haiku 4.5 $0.00001 $0.00313

Measured 9d ago against content hash 02ca1482ab32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

review-pr scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- EC-CUBE 4系: `php bin/console cache:clear --no-warmup`、`rm -rf .phpunit.result.cache`
plugins/eccube-dev-agents/skills/review-pr/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR レビュー(投稿しないドラフト作成)

GitHub PR をレビューし、個別インラインコメントのドラフトを作成して提示します。

最重要ルール

この Skill は GitHub へ一切投稿しない。

  • gh pr reviewgh api --method POST .../reviewsgh api --method POST .../commentsgh pr comment を実行してはならない。
  • 読み取り専用の gh 呼び出し(gh pr view / gh pr diff / gh api の GET)のみ使用する。
  • 投稿は利用者がドラフトを確認したうえで /post-review を実行したときにのみ行われる。
  • 利用者から「そのまま投稿して」と言われた場合も、この Skill 内では投稿せず /post-review に引き継ぐ。

引数

$ARGUMENTS から以下を解析:

  1. 対象 PR(いずれか)
    • URL: https://github.com/{owner}/{repo}/pull/{number}
    • 番号のみ: 6958(カレントリポジトリの PR とみなす)
    • 省略: gh pr view --json number,url でカレントブランチに紐づく PR を特定。特定できなければ利用者に確認して終了
  2. 追加観点(自由記述、省略可)
    • 例: 「セキュリティを重点的に」「個人情報保護法・GDPR との兼ね合いもチェック」
    • 例: 「関連 issue の再現手順を確認して」
    • 例: 「~/git-repos/stripe-payment-plugin への影響調査もお願いします」
    • 追加観点は通常のレビュー観点に上乗せする。指定されたものだけを見るのではない

手順

1. コンテキストの収集

# PR メタ情報(headRefOid = HEAD コミット SHA。ドラフトの commit_id に使う)
gh pr view {number} --repo {owner}/{repo} \
  --json number,title,body,author,baseRefName,headRefName,headRefOid,state,isDraft,mergeable,additions,deletions,changedFiles,labels,url

# 差分(ローカル git diff ではなくこれを使う)
gh pr diff {number} --repo {owner}/{repo}

# 既存レビュー・既存インラインコメント(重複指摘の回避)
gh api repos/{owner}/{repo}/pulls/{number}/reviews --jq '.[] | {user: .user.login, state, body: (.body[0:200])}'
gh api repos/{owner}/{repo}/pulls/{number}/comments --paginate \
  --jq '.[] | {user: .user.login, path, line, body: (.body[0:200])}'

# CI 状況
gh pr checks {number} --repo {owner}/{repo}

関連 issue の確認: PR 本文の Closes #N / Refs #N / Fixes #N や、利用者が提示した issue URL があれば gh issue view N --repo {owner}/{repo} --comments で本文とコメントを読む。issue に再現手順が書かれている場合は、それが PR の変更で解消されるかを差分から追う。

既出指摘の除外: CodeRabbit / Gemini Code Assist / 他レビュアーが既に指摘済みの内容は、ドラフトに重複して載せない。既に別 issue 化されているものも同様。

2. 差分の読解

差分だけで判断せず、変更されたファイルの前後関係を Read で確認する。以下は毎回見る観点:

  • 正確性: 分岐漏れ、null/未定義、境界値、例外経路、トランザクション境界
  • 後方互換性: 公開 API・エンティティ・テンプレート・イベント・設定キーの削除や意味変更
  • セキュリティ: 入力検証、権限チェック、CSRF、XSS、SQL/コマンドインジェクション、パストラバーサル、機密情報のログ出力
  • 影響範囲: 変更されたメソッド・定数・設定の呼び出し元を rg で洗い出す(1 箇所ずつではなく全件まとめて)
  • テスト: 変更に対応するテストの有無、テストが実際に退行を検出できるか
  • PR の記述と実装の一致: 本文の説明どおりの変更になっているか

Read the full file on GitHub · 203 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. 9d ago First seen · 203 lines · 13 tokens per session scan C 02ca1482ab32

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository nanasess/eccube-dev-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 3,129 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

issue-analyzing

Use this skill when the user asks to analyze a specific GitHub issue, understand what area of code an issue affects, assess an issue's scope, or research the code context around an issue — example triggers like "analyze issue.

shopwareLabs/ai-coding-tools · 51 tokens

oss-contrib

Use when contributing to open source projects from forked repositories. Handles upstream sync, CONTRIBUTING.md compliance, code style matching, PR preparation, and project-specific patterns. Activates for fork management, PR template filling, and upstream workflow compliance.

Sagargupta16/claude-skills · 52 tokens

review-pr

Review a Pull Request in one of two postures: an expository "tour guide" that walks through changes in logical order, or an adversarial audit that assumes the change is wrong until proven safe and hunts for the failure mode. Triggers: "review PR #123", "adversarial review", "walk me through this PR", "PR tour guide"…

jontsai/claude-plugins · 139 tokens

dev-workflow

Use when performing common development tasks like committing code, reviewing changes, running tests, fixing bugs, creating PRs, or checking repo status. Provides structured workflows for everyday git and development operations.

Sagargupta16/claude-skills · 42 tokens

github-workflows

Use this skill for the full GitHub operating loop: 1) authenticate, 2) manage repos and remotes, 3) open and review PRs, 4) work on issues, and 5) monitor CI.

AtlasOmnia/hermes-custom-pack · 27 tokens

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens