Borrowing it
Nothing to install: this file belongs to apokamo/kaji. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/apokamo/kaji/main/.claude/skills/pr-verify/SKILL.mdgit clone --depth 1 https://github.com/apokamo/kajiWrote 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.
[](https://agentmods.dev/skills/apokamo/kaji/pr-verify)<a href="https://agentmods.dev/skills/apokamo/kaji/pr-verify"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/pr-verify.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.03136 |
| Opus 5 | $0.00018 | $0.01568 |
| Sonnet 5 | $0.00007 | $0.00627 |
| Haiku 4.5 | $0.00004 | $0.00314 |
Grade A, and why
pr-verify 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Verify
重要: このスキルは修正を行ったセッションとは 別のセッション で実行することを推奨します。 同一セッションで実行すると、修正時のバイアスが確認判断に影響する可能性があります。
PR レビュー修正後の確認を行う。
重要: このスキルは「指摘事項が適切に修正されたか」のみを確認する。 新規の指摘は行わない。これはレビューサイクルの収束を保証するためである。
いつ使うか
| タイミング | このスキルを使用 |
|---|---|
/pr-fix 後の修正確認 |
✅ 必須 |
| 新規レビューが必要な場合 | ❌ PR 上で直接レビューを実施 |
provider.type='github' 配下 |
✅ 受理（gh CLI 経由） |
provider.type='local' 配下 |
❌ Step 0 で ABORT。代替は /issue-verify-code |
ワークフロー内の位置: i-pr → [PR review] → (pr-fix → pr-verify) → close
引数
$ARGUMENTS = <issue_id>
- Issue 番号を受け付ける（関連 PR を自動解決する）
コンテキスト変数
| 変数 | 型 | 説明 |
|---|---|---|
issue_id |
str | 正規化済み Issue ID（GitHub 数値、または local-*） |
issue_ref |
str | 人間可読の Issue 参照 |
provider_type |
str | github / local のいずれか。Step 0 のガード判定に使用 |
解決ルール
コンテキスト変数 issue_id が存在すればそちらを使用。
なければ $ARGUMENTS の第1引数を issue_id として使用。
issue_ref はハーネス経由ではプロンプトに自動注入される（prompt.py 側で provider 別に整形）。手動実行時は issue_id から導出する: GitHub 数値 ID なら #<issue_id>、local-* 形式なら bare ID（# を付けない）。
pr_id / pr_ref はハーネス経由ではプロンプトに自動注入される（runner.py の _resolve_pr_context_safe が GitHubProvider.resolve_pr_context() 経由でブランチから PR を逆引きして展開する）。手動実行時、および auto-resolve が失敗した（branch 未 push / PR 未作成）場合は Step 1 で fallback として kaji pr list --head から取得する。pr_ref は gh:<pr_id> 形式で組み立てる（kaji_harness/providers/models.py PRContext 準拠）。
前提知識の読み込み
変更対象に応じて、以下のドキュメントを Read ツールで読み込んでから作業を開始すること。
- テスト規約:
docs/dev/testing-convention.md - コーディング規約:
docs/reference/python/python-style.md（型ヒント、docstring 等） - エラーハンドリング:
docs/reference/python/error-handling.md
verify と新規レビューの違い
| 項目 | 新規レビュー | verify |
|---|---|---|
| 目的 | フルレビュー | 修正確認のみ |
| 新規指摘 | する | しない |
| 確認範囲 | コード全体 | 前回指摘箇所のみ |
| 使用タイミング | 初回レビュー | pr-fix 後 |
共通ルール
- _shared/report-unrelated-issues.md — 作業中に発見した無関係な問題の報告ルール
実行手順
Step 0: provider check
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.
- 8d ago First seen · 310 lines · 36 tokens per session scan A cf68eaf43f48
pr-verify is a skill published in the GitHub repository apokamo/kaji (12 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 3,136 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 2026-08-30.
Other skills, from other repositories
software-development-norms
Use when writing, reviewing, or refactoring code in any language to apply industrial-grade development norms abstracted from the Alibaba Java Development Handbook. Covers naming, type safety, exceptions, logging, concurrency, databases, project structure, testing, and security with language-agnostic principles and…
software-development-pragmatic-programmer
Apply meta-principles of software craftsmanship: DRY, orthogonality, tracer bullets, and design by contract. Use when the user mentions "best practices", "pragmatic approach", "broken windows", "tracer bullet", "software craftsmanship", "technical debt prevention", "prototype vs tracer bullet", or "code ownership".…
software-design-patterns-and-refactoring
Use when architecture or backend work needs pre-code structural guidance from design patterns, or post-code cleanup guidance from refactoring and code-smell-driven improvement.
superpowers-verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
superpowers-receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.