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-downstreamgit 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-downstream)<a href="https://agentmods.dev/skills/s977043/river-review/review-policy-standard-downstream"><img src="https://agentmods.dev/badge/skills/s977043/river-review/review-policy-standard-downstream/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-downstream"><img src="https://agentmods.dev/badge/skills/s977043/river-review/review-policy-standard-downstream.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 | $0.00024 | $0.01030 |
| Opus 5 | $0.00012 | $0.00515 |
| Sonnet 5 | $0.00005 | $0.00206 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
Standard Review Policy for Downstream 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 12d 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
- テスト/QA フェーズの差分に対して、テスト不足・失敗系の抜け・フレークのリスクを短く指摘する。
Non-goals / 扱わないこと
- 変更と無関係な “テストを増やすべき” の一般論を言わない。
- プロジェクトのテスト方針（E2E/Unit 比率など）を断定して押し付けない。
False-positive guards / 抑制条件
- 変更がテストの整形/リネームのみで、意味的な変更がない場合は深入りしない。
- テスト観点が不確実な場合は、欠陥ではなく質問として提示する。
Rule / ルール
- 指摘は差分に紐づける（根拠は
<file>:<line>）。 - 優先する観点は「失敗系」「境界」「クリティカルパス」（例: 認証、課金、データ整合性、権限）。
- 可能なら最小の追加テスト案を 1 つ添える（大改造ではなく追加 1 ケース）。
Evidence / 根拠
- 追加/変更された分岐や例外パスに対して、対応するテスト差分がない点を根拠として示す。
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）
- 新規/変更された分岐に対するテストが増えていない
- 例外/エラー戻りのアサーションがない（メッセージ、ステータス、code など）
- 時刻/乱数/外部依存でフレークしやすい構造になっている（固定化/モック不足）
- セットアップが重複し、テスト意図が読み取りにくい
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）
- テスト / QA レビューでも完璧を求めず、「このテスト追加 / 修正が回帰検出と保守性を改善するか」を判断軸にする (
google/eng-practicesの "Improve the overall code health" 原則)。 - テスト観点では「意味のある assertion」「flaky 回避」「適切な scope (unit / integration / e2e)」を最優先する。命名やフォーマットは nit 扱い。
- nit / 好み相当の指摘は
severity: minor以下に留める。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.
- 12d ago First seen · 90 lines · 24 tokens per session scan A 7379a364e44f
Standard Review Policy for Downstream is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,030 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 2026-08-31.
Other skills, from other repositories
daa-review
Use when reviewing existing test code for DAA compliance, identifying anti-patterns, or suggesting improvements to automation test architecture.
spike-consumer-adversarial
OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIALID and data path.
code-standards
Apply a disciplined engineering workflow to any code change. Use whenever implementing a feature, fixing a bug, or refactoring — before writing code, not after. Walks orient → baseline → smallest change → test → verify → self-review, and enforces language-agnostic hard gates (don't mass-reformat, keep the linter and…
e2e-reviewer
Use when reviewing Playwright or Cypress E2E specs, Page Objects (POM), PRs, pull requests, patches, diffs, or changed test files — asked to review tests, audit test quality, or find weak, flaky, or silently-passing tests; when tests pass CI but prove nothing or miss bugs; when auditing missing awaits, vacuous or…
cypress-debugger
Use when a Cypress end-to-end test has already run and failed and the user wants the root cause and a concrete fix. Trigger on a failing Cypress spec, Timed-out-retrying command, unresolved selector, cy.intercept alias or request race, suite-breaking hook, retry-only flake, hydration or timing race, or a…
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.