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 review-policy-standard-midstreamgit 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/review-policy-standard-midstream)<a href="https://agentmods.dev/skills/s977043/river-review/review-policy-standard-midstream"><img src="https://agentmods.dev/badge/skills/s977043/river-review/review-policy-standard-midstream/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/review-policy-standard-midstream"><img src="https://agentmods.dev/badge/skills/s977043/river-review/review-policy-standard-midstream.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 | $0.00023 | $0.01095 |
| Opus 5 | $0.00012 | $0.00548 |
| Sonnet 5 | $0.00005 | $0.00219 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
Standard Review Policy for Midstream 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.
What it actually says
Goal / 目的
- 実装フェーズの差分に対して、バグ・安全性・保守性のリスクを短く指摘する。
Non-goals / 扱わないこと
- 差分にないコードや仕様を断定しない（推測は “可能性” として扱う）。
- 重要度の低い “nit” を濫発しない（本質的なリスクを優先する）。
- プロジェクトの前提が不明なまま大規模リファクタを押し付けない。
False-positive guards / 抑制条件
- 変更がコメント・フォーマットのみで、挙動変更が見当たらない場合は深入りしない。
- リスクが不確実で根拠が薄い場合は、断定ではなく質問として扱う。
Rule / ルール
- 差分に紐づく指摘だけを出す（根拠は
<file>:<line>）。 - 優先度は「壊れる/漏れる/回復できない」ものから（例: 入力検証不足、例外握りつぶし、認可漏れ、型安全性の破壊）。
- 可能なら “次の一手” を最小で添える（過剰な提案は避ける）。
Evidence / 根拠
- 指摘は必ず
<file>:<line>で追える形にする。 - 差分外の推測に依存する場合は、その旨を明示する。
Output / 出力
- 各指摘を 1 行で出力する:
<file>:<line>: <message> <message>は日本語で簡潔に（目安: 200 文字以内）。- PR の本文（説明）と PR コメント（レビューコメント）は日本語で書く。
- 最大 8 件。指摘がなければ
NO_ISSUESのみ。
Heuristics / 判定の手がかり（例）
- I/O・外部 API のエラー処理不足（タイムアウト、例外伝播、再試行の意図が不明）
- 入力バリデーション不足（URL/ボディ/環境変数/外部レスポンスのノーチェック使用）
- 例外の握りつぶし（ログ無し、戻り値で隠蔽、cause が失われる）
- 競合・リソースリーク（接続/ファイルハンドルの close 忘れ、共有状態の競合）
- ハードコード値の増加（環境差異で壊れる設定値）
評価指標（Evaluation）
- 合格基準: 指摘が差分に紐づき、根拠と次アクションが説明されている。
- 不合格基準: 差分と無関係な指摘、根拠のない断定、抑制条件の無視。
人間に返す条件（Human Handoff）
- 仕様や意図が不明確で解釈が分かれる場合は質問として返す。
- 影響範囲が広い設計判断やトレードオフは人間レビューへ返す。
レビュー姿勢（Standard of Code Review）
- 完璧なコードを求めず、「PR を入れることでコードベース全体の健全性が改善するか」を判断軸にする (
google/eng-practicesの "Improve the overall code health" 原則)。 - 完璧主義的な書き直し要求や、好みベースの reformat 要求はしない。
- nit / 好み相当の指摘は
severity: minor以下に留め、major/criticalは実害ベースの指摘に限定する。詳しい対応表はdocs/development/google-eng-practices-mapping.mdを参照する。
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 · 91 lines · 23 tokens per session scan A 321561ded181
Standard Review Policy for Midstream is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 1,095 once invoked, about $0.0001 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…
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…
deep-review
Multi-angle code review that adapts to what is being reviewed — a mid-flight worktree increment, a full PR before production, a merge-window integration sweep, or a security-only pass. Findings are scored, adversarially refuted, widened to the same defect elsewhere in the codebase, and reported to the native review…
review-loop
Run a bounded cross-model peer review and fix loop, or report findings in read-only mode.
harness
Plan or execute complex tasks through the harness checkpoint, evaluation, and retro workflow.
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…