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 plangate-verification-auditgit 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/plangate-verification-audit)<a href="https://agentmods.dev/skills/s977043/river-review/plangate-verification-audit"><img src="https://agentmods.dev/badge/skills/s977043/river-review/plangate-verification-audit/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/plangate-verification-audit"><img src="https://agentmods.dev/badge/skills/s977043/river-review/plangate-verification-audit.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 | $0.00061 | $0.03717 |
| Opus 5 | $0.00030 | $0.01858 |
| Sonnet 5 | $0.00012 | $0.00743 |
| Haiku 4.5 | $0.00006 | $0.00372 |
Grade A, and why
PlanGate 検証監査 (W チェック) 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern declaration
Primary pattern: Reviewer
Secondary patterns: Inversion
Why: 既存レビュー（review-self / review-external）を artifact として読み込み、差分および上流 artifact と突き合わせて「レビューに対するレビュー（META finding）」を返す再照合型の skill。入力となるレビューが揃わない場合は実行を止めるゲート（Inversion）として機能する。
Goal / 目的
- 既に生成されたレビュー（
review-self/review-external）を W チェック（二重レビュー）し、漏れ・誤検知・ハルシネーション・根拠欠落・過剰指摘を検出する。 - 元コードに対する直接指摘ではなく、レビューそのものの品質を対象とする META finding を返し、後続の人間判断や Riverbed Memory に再評価材料を提供する。
river review verifyCLI（pages/reference/cli-review-verify-spec.md）から呼び出される verify 系 skill として、verify ファミリー制限に適合した単一責務の監査を行う。
Non-goals / 扱わないこと
- 実装コード自体の品質レビュー（midstream / downstream skill の責務）。
- 計画アーティファクト（
plan/pbi-input/todo/test-cases）の内部整合性チェック（姉妹 skillplangate-plan-integrityの責務）。 - 差分が plan と整合しているかの検査（姉妹 skill
plangate-exec-conformanceの責務）。 - 既存レビューの severity 再マッピング全般（本 skill は「過剰指摘」観点のみに限定し、妥当な severity の再評価は行わない）。
- レビューアーの意図や主観の推定。書かれた内容から客観的に判断できる範囲のみを扱う。
Pre-execution Gate / 実行前ゲート
このスキルは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
review-selfまたはreview-externalのいずれか1つ以上が解決できている（pages/reference/artifact-input-contract.mdの ID に準拠） -
diffartifact が解決できている（未指定時はgit diff <mergeBase>..HEADによる fallback を許容）
ゲート不成立時の出力: NO_REVIEW: plangate-verification-audit — レビュー入力 (review-self / review-external) または diff が不足
Gate と抑制条件の違い:
- Gate = 監査対象となるレビューまたは差分が揃わなければ W チェックは成立しない。
- 抑制条件 = 実行した上で個別の META finding を抑える。
False-positive guards / 抑制条件
- 既存レビューが「info」や「参考」として明示的に弱い推奨にとどめている項目を、漏れ・過剰指摘として指摘しない。
- 既存レビューが「推測」「要確認」「後続 Issue に回す」と明示的に不確実性を宣言している項目は、根拠欠落として扱わない。
- diff の fallback 取得で
mergeBaseが曖昧（浅い clone 等）な場合、差分に該当行が見つからない指摘を即ハルシネーションと断定しない。[q]として質問に回す。 plan/test-casesが未提供の場合、受け入れ条件カバレッジに関する漏れ検出は抑制し、infoレベルの補足通知にとどめる。- 既存レビューが自動生成コメント（依存更新、フォーマット）に向けた定型的な観察のみで構成される場合、過剰指摘として扱わない。
Rule / ルール
既存レビューを以下の観点で再点検する。1 観点=1 指摘を原則とし、最大 8 件まで。
1. 漏れ検出 (omissions)
pbi-input/planの主要な受け入れ条件や明示された重大リスクが、既存レビューで一切カバーされていないか。- diff に含まれる明らかな懸念点（エラー処理欠落、破壊的変更、テスト不足）が既存レビューで触れられていないか。
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.
- 7d ago First seen · 160 lines · 61 tokens per session scan A e133140ec544
PlanGate 検証監査 (W チェック) is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 3,717 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
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…
tsq-audit
A code-audit skill that reviews changed files and runs relevant verification checks. It produces a report grouped by severity across security, type safety, error handling, API compatibility, tests, and performance.
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.
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…