validate-review

validate-review is a skill for Claude Code from nanasess/eccube-dev-agents. It costs 17 tokens per session (2,318 once invoked), scanned A, original, MIT.

A read-only process for checking whether GitHub pull-request review comments are correct by examining the relevant code. It can validate one comment or all comments in a pull request.

In plain words
What is it for?
Use it to inspect review comments on the current pull request, a specified pull request, or one comment URL, and assess each comment's correctness.
Why use it?
It helps separate valid findings from mistaken review comments without automatically replying to GitHub.

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 Use it to inspect review comments on the current pull request, a specified pull request, or one comment URL, and assess each comment's correctness.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/nanasess/eccube-dev-agents/validate-review.svg)](https://agentmods.dev/skills/nanasess/eccube-dev-agents/validate-review)
Your own site
<a href="https://agentmods.dev/skills/nanasess/eccube-dev-agents/validate-review"><img src="https://agentmods.dev/badge/skills/nanasess/eccube-dev-agents/validate-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,318 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 $0.00017 $0.02318
Opus 5 $0.00009 $0.01159
Sonnet 5 $0.00003 $0.00464
Haiku 4.5 $0.00002 $0.00232

Measured 7d ago against content hash 95813662aaef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

validate-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 7d 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.

plugins/eccube-dev-agents/skills/validate-review/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

レビューコメントの妥当性検証

GitHub PR のレビューコメントを取得し、対象コードを確認して指摘の妥当性を判断します。 この Skill は GitHub への書き込み(返信・投稿)を一切行いません。 返信は確認後に /eccube-dev-agents:reply-review でまとめて投稿します。

引数パターン

$ARGUMENTS に応じて対象を決定する:

パターン 引数 対象
A なし 現在ブランチの PR のレビューコメントすべて
B PR URL (.../pull/{n}) または PR 番号 その PR のレビューコメントすべて
C レビューコメント URL (.../pull/{n}#discussion_r{id}) 指定された 1 件のみ

判定は URL に #discussion_r が含まれるかで行う。含まれない場合は「コメント指定なし」= 全件検証。

1. 対象 PR の特定

パターン A(引数なし)

gh pr view --json number,url,title,headRefName,baseRefName,state
gh repo view --json nameWithOwner
  • 現在ブランチに紐づく PR が存在しない場合は、その旨を報告して終了(勝手に PR を作成しない)
  • 複数リポジトリ構成の場合は先に pwdgit remote -v で対象リポジトリを確認する

パターン B / C(URL または PR 番号)

  • URL から owner, repo, pr_number, (あれば)comment_id を正規表現で抽出
  • PR 番号のみが渡された場合は gh repo view --json nameWithOwnerowner/repo を補完

2. レビューコメントの取得

パターン A / B(全件)

レビュースレッド単位で取得し、解決状態と返信状況を把握する:

gh api graphql -f query='
query($owner:String!, $repo:String!, $pr:Int!) {
  repository(owner:$owner, name:$repo) {
    pullRequest(number:$pr) {
      reviewThreads(first:100) {
        nodes {
          isResolved
          isOutdated
          path
          line
          comments(first:50) {
            nodes { databaseId url author { login } body createdAt }
          }
        }
      }
    }
  }
}' -f owner={owner} -f repo={repo} -F pr={pr_number}

コメント本文が長く切り詰められる場合や diff_hunk が必要な場合は、REST でも取得する:

gh api repos/{owner}/{repo}/pulls/{pr_number}/comments --paginate

検証対象の切り分け(すべて一覧に載せ、スキップしたものも理由を明記する):

  • 検証する: 未解決(isResolved: false)のスレッドの先頭コメント
  • スキップ: isResolved: true のスレッド(解決済み)
  • スキップ: 投稿者が PR 作成者自身のコメント(自分の返信)
  • 文脈として読むのみ: スレッド内の 2 件目以降の返信(既に議論済みの内容を再指摘しない)
  • isOutdated: true のスレッドは「該当コードが変更済み」の可能性があるため、現行コードとの差異を判定理由に明記する

パターン C(単一)

gh api repos/{owner}/{repo}/pulls/comments/{comment_id}

いずれの場合も以下を抽出:

  • body: コメント本文(指摘内容)
  • path: 対象ファイルパス
  • diff_hunk: 対象コードの差分
  • line / original_line: 行番号
  • commit_id: コメント対象のコミット SHA
  • user.login / author.login: コメント投稿者
  • html_url: コメント URL(報告と reply-review での参照に使う)

Read the full file on GitHub · 187 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. 7d ago First seen · 187 lines · 17 tokens per session scan A 95813662aaef

Subscribe to this mod's changes

validate-review is a skill published in the GitHub repository nanasess/eccube-dev-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 2,318 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.

Related

Other skills, from other repositories