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/review-poll/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/review-poll)<a href="https://agentmods.dev/skills/apokamo/kaji/review-poll"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/review-poll/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.
<a href="https://agentmods.dev/skills/apokamo/kaji/review-poll"><img src="https://agentmods.dev/badge/skills/apokamo/kaji/review-poll.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00072 | $0.03784 |
| Opus 5.5 | $0.00029 | $0.01514 |
| Sonnet 5.5 | $0.00014 | $0.00757 |
| Haiku 4.5 | $0.00007 | $0.00378 |
Grade A, and why
review-poll 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Poll
GitHub chatgpt-codex-connector[bot] (id 199175422) の auto-review シグナルを polling し、
verdict を出力する skill。review skill との二重起動を避け、auto-review クレジット不足時のみ
BACK_FALLBACK 経由で既存 review skill (codex agent) に fallback させる。
本 skill は LLM agent を起動しない deterministic skill であり、kaji_harness.scripts.review_poll_entry
module を直接 subprocess 実行する。entry module が env から PR 情報を解決し、polling 本体
kaji_harness.scripts.codex_review_poll に委譲する。
起動経路は 2 系統あり、いずれも同じ entry module に合流する:
- builtin workflow（
dev/dev-thorough/docs）: 各 YAML がexec: [kaji, pr, review-poll]で installedkajiCLI 経由で起動し、 CLI 側 (kaji pr review-poll) が同 entry module（review_poll_entry.main）へ委譲する。 dispatch の正本は YAML 側のexecstep であり、agent / model / effort はスキーマレベルで 指定不可（指定するとkaji validateが reject）。対象 repo の Python 環境ではなく installedkajiCLI 経由で起動するため可搬性が高い。 - skill 単体起動・再利用: frontmatter の
exec_script: kaji_harness.scripts.review_poll_entryが契約となり、harness が同 entry module をpython -mで subprocess 実行する。
どちらの経路でも、入力（env）/ verdict 仕様の正本は entry module（review_poll_entry）であり、
本ファイルの記述はその契約のミラーである。
いつ使うか
| タイミング | このスキル |
|---|---|
| PR 作成後、codex auto-review が走っている GitHub 環境 | ✅ 必須 |
review-poll で BACK_FALLBACK を受けた場合 |
既存 review skill (codex agent) に進む |
ワークフロー内の位置: i-pr → [PR 作成] → review-poll（builtin workflow では exec step として起動）→ (PASS=close / RETRY=pr-fix / BACK_FALLBACK=review fallback)
入力（harness が env として注入）
| env 変数 | 必須 | 説明 |
|---|---|---|
KAJI_ISSUE_ID |
✅ | PR 解決の検索キー |
KAJI_PROVIDER_TYPE |
✅ | github 以外は ABORT |
KAJI_GIT_REMOTE |
✅ | owner/repo 解決 (git remote get-url) |
KAJI_WORKTREE_DIR |
✅ | git remote get-url 実行 cwd |
KAJI_PR_ID |
任意 | harness 側で解決済みの場合のみ。未設定なら kaji pr list で取得 |
KAJI_VERDICT_PATH |
PASS には必須 | runner が注入する verdict.yaml の絶対パス。承認証跡の保存先 <dirname>/review-poll-evidence.json の導出に使う。未設定のまま PASS 条件が成立すると ABORT（evidence unavailable） |
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.
- 9d ago Changed · -2 lines d985813b0874
- 11d ago Changed · -1 lines 15dfd858e27d
- 12d ago Changed · +37 lines 109c3fd081a8
- 26d ago Changed · +38 lines · +24 tokens per session 1b0b6171aed7
- 1mo ago First seen · 98 lines · 48 tokens per session scan A a1cf747e2ea9
review-poll is a skill published in the GitHub repository apokamo/kaji (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 72 tokens to every session and 3,784 once invoked, about $0.0003 per session on Opus 5.5. 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.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.