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.
npx skills add s977043/river-review --skill plan-review-gategit clone --depth 1 https://github.com/s977043/river-reviewWrote 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/river-review/plan-review-gate)<a href="https://agentmods.dev/skills/s977043/river-review/plan-review-gate"><img src="https://agentmods.dev/badge/skills/s977043/river-review/plan-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/river-review/plan-review-gate"><img src="https://agentmods.dev/badge/skills/s977043/river-review/plan-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 | $0.00063 | $0.03196 |
| Opus 5 | $0.00032 | $0.01598 |
| Sonnet 5 | $0.00013 | $0.00639 |
| Haiku 4.5 | $0.00006 | $0.00320 |
Grade C, and why
実装計画レビューゲート 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 6d 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.
- 破壊的コマンド（`rm -rf`, `DROP TABLE`, `kubectl delete` 等） How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern declaration
Primary pattern: Reviewer Secondary patterns: Gate Why: 実装計画アーティファクトを読み込み、AI が自律実行すべきでない危険操作・スコープ外操作・人間承認必須条件を検出する。問題あり時は実行を止めるゲートとして機能する。
Goal / 目的
- 実装計画（
plan.md/pbi-input.md）に記載された作業が、AI エージェントが単独で実行してよい範囲に収まっているかを判定する。 - 危険操作、触れてはならないスコープ（Do Not Touch）、人間承認が必要な条件（
human_approval: required）を早期に検出し、下流フェーズへの誤進入を防ぐ。 - 過実装（over-implementation）および設計書との矛盾を検出し、計画段階での修正機会を提供する。
Non-goals / 扱わないこと
- 計画アーティファクト間の整合性チェック（
plangate-plan-integrityの責務）。 - 実装コードそのものの品質レビュー（midstream skill の責務）。
- テストコードの実装妥当性（downstream skill の責務）。
- ビジネス価値や優先度の妥当性判断（人間の責務）。
責務分界 / plangate-plan-integrity との違い
| 観点 | plangate-plan-integrity | plan-review-gate（本スキル） |
|---|---|---|
| 主目的 | PBI / plan / todo / test-cases 間の整合性 | 危険操作・スコープ外・承認必須の検出 |
| 検出対象 | アーティファクト間の矛盾・欠落 | 安全性・権限・影響範囲のリスク |
| ゲート条件 | plan + 関連 artifact 1 件以上 | plan または pbi-input が存在すれば起動 |
| 人間への引き渡し | 再計画が必要な場合 | 人間承認必須トリガーを検出した場合 |
Pre-execution Gate / 実行前ゲート
以下の条件がすべて満たされない限り NO_REVIEW を返す。
- 入力 artifact に
plan.mdまたはpbi-input.mdが存在する - diff または fullFile のいずれかの inputContext が利用可能である
ゲート不成立時の出力:
NO_REVIEW: plan-review-gate — plan.md または pbi-input.md が見つからない
Rule / ルール
1. 危険操作の検出（Stop-work トリガー）
以下のいずれかを計画が含む場合、human_approval: required として即座に Stop-work を返す。
- 破壊的コマンド（
rm -rf,DROP TABLE,kubectl delete等） - 認証情報・シークレットの書き込み・上書き（
credential,secret,tokenの作成・変更） - 設定ファイルの上書き（
config overwrite,overwrite settings） - 外部サービスへのポスト・通知（
external posting,Slack 送信,メール送信） - 本番環境デプロイ（
deployment,本番 deploy,production release） - cron / スケジューラ登録（
cron,scheduled task） - エージェントメモリへの書き込み（
memory write） - 課金・請求操作（
billing） - プロバイダ変更（
provider change,クラウド移行） - 認証フロー変更（
auth,SSO,OAuthの変更） - 権限変更（
permission change,IAM,RBACの変更） - ユーザーデータの処理（
user data,PII,個人情報）
What ships with it
11 files 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.
- fixtures/01-adversarial-euphemism-cleanup.md 721 B
- fixtures/02-adversarial-euphemism-secrets.md 537 B
- fixtures/03-adversarial-euphemism-live-env.md 535 B
- fixtures/04-adversarial-low-confidence-only.md 614 B
- fixtures/05-benign-refactor.md 565 B
- fixtures/06-heldout-zero-width-bypass.md 625 B
- fixtures/07-heldout-newline-split.md 606 B
- fixtures/08-heldout-word-order-variant.md 575 B
- fixtures/09-benign-verification.md 768 B
- fixtures/10-benign-refactor.md 756 B
- fixtures/11-heldout-poisoned-exclusion.md 667 B
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.
- 6d ago First seen · 181 lines · 63 tokens per session scan C c17a361b6dff
実装計画レビューゲート is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 3,196 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…
logic-diff
Compare two code versions for semantic equivalence via semi-formal tracing of both versions side-by-side. Trigger when the user shares a refactor, rewrite, migration, or A/B implementation and wants to confirm behavior is unchanged — "did I break anything", "is this equivalent", "are these equivalent", "semantically…
omnicheck-gitlab
Use when checking if MR review findings have been applied — verifies both OmniForge-generated and human reviewer comments against the current diff, posts nudge replies on unaddressed threads.
omnicheck-github
Use when checking if PR review findings have been applied — verifies both OmniForge-generated and human reviewer comments against the current diff, posts nudge replies on unaddressed threads.
omnicreate-gitlab
Use when creating a GitLab merge request (OmniForge). Auto-populates title and description from commits, supports draft MRs, labels, assignees, reviewers, and issue linking.