Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/s977043/plangate/review-gate)<a href="https://agentmods.dev/skills/s977043/plangate/review-gate"><img src="https://agentmods.dev/badge/skills/s977043/plangate/review-gate/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/s977043/plangate/review-gate"><img src="https://agentmods.dev/badge/skills/s977043/plangate/review-gate.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 | $0.00116 | $0.07466 |
| Opus 5 | $0.00058 | $0.03733 |
| Sonnet 5 | $0.00023 | $0.01493 |
| Haiku 4.5 | $0.00012 | $0.00747 |
Grade A, and why
review-gate 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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Gate
実装後に 6 観点でレビューを行い、critical finding を Completion Gate に伝達する。
Iron Law
NO MERGE WITHOUT TWO-STAGE REVIEW
severity=critical の finding がある場合、fix なしに Completion Gate を通過させない。
Common Rationalizations
| こう思ったら | 現実 |
|---|---|
| 「テストが通ったからレビュー不要」 | テスト通過はロジック正確性の一部に過ぎない。セキュリティ・仕様準拠は別途確認が必要 |
| 「小さな変更だから critical は出ない」 | 規模に関わらず 6 観点でチェックせよ。1 行の変更でも脆弱性は混入する |
| 「外部レビューを受けたから大丈夫」 | review type の EvidenceItem として記録せよ。記録なき承認は存在しない |
手順
ステップ 1: レビュー対象の差分を取得して finding を収集する
/pg-checkは存在しない（TASK-0124 /2645848, 2026-06-02 の plugin 初回同期適用でplugin/plangate/commands/pg-check.mdが削除され、後継コマンドは無い）。 本節はその代替として、コマンドに依存しない手順を定義する。severity 付き finding を 起こす責務は本 Skill（ステップ 2〜3）が引き継ぐ。旧コマンドを前提とした自動化を 組んでいる場合は、以下の手順に置き換えること。
対象差分を取得する（上から順に該当するものを使う）:
git status # 対象ブランチと未コミット変更を確認
gh pr diff <PR番号> # PR がある場合
git diff origin/main...HEAD # PR 前のブランチを見る場合
git diff && git diff --cached # 未コミット変更を見る場合
git diff --stat # 変更ファイルの概要
取得した差分を精読し、ステップ 2 の 6 観点ごとに finding を起こす。この段階では
severity を付けず、事実（ファイル・行・観察された挙動）だけを列挙する。severity は
ステップ 2 で review-principles.md §3 の定義に従って付与する。
コミット・PR 前のセルフ検査は
diff-auditSkill を使う（本 Skill の代わりにはならない）。diff-auditは「変更を作った本人が PR 前に自分で潰す」段階、本 Skill は「実装完了後の ゲート判定」段階であり、diff-audit§review-gate との役割分界 のとおり別段階である。diff-auditの出力を本ステップの入力として持ち込むのは有効だが、それだけで本ステップを 満たしたとは扱わない。
ステップ 2: 6 観点で finding を分類・severity を付与する
ステップ 1 で収集した finding を以下の 6 観点に分類する:
| # | 観点 | チェック内容 |
|---|---|---|
| 1 | 仕様準拠 | 受入基準・設計書との一致 |
| 2 | コード品質 | 可読性・命名・構造の明確さ |
| 3 | セキュリティ | 入力バリデーション・認証・認可・機密情報 |
| 4 | パフォーマンス | N+1 クエリ・ループ内 I/O・不要データ取得 |
| 5 | テスト不足 | カバレッジ・エッジケース・重要パスの未テスト |
| 6 | 破壊的変更 | 後方互換性・API 変更・スキーマ変更 |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 332 lines · 116 tokens per session scan A 699f93ec62cb
review-gate is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 7,466 once invoked, about $0.0006 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.
Other skills, from other repositories
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…
01-sdlc
Autonomously orchestrates a request from framing to a draft pull request, isolating implementation, independent review, and final outcome challenge. Use when the user wants to deliver a change end to end. Not for running one development step.
00-async-dev
Drive the async-dev pipeline from one entry point, whether setup, run, or review. Use when the user wants to install async dev, run a ready issue, or address PR review comments, or on a webhook trigger. Not for plain status checks.
vue-best-practices
A review checklist for Vue 2 and Vue 3 components, covering component names, prop declarations, TypeScript casts, API styles and complex template expressions.
agents-consilium
Run external coding agents (Codex, Claude Code, OpenCode, native Grok Build, Gemini) as independent reviewers, stateful repository researchers, or single-agent implementers. Use for multi-model opinions and code review, steerable Grok research, full-access delegation, long-running work, or reattaching to delegated…