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-criteria-integritygit 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-criteria-integrity)<a href="https://agentmods.dev/skills/s977043/river-review/review-criteria-integrity"><img src="https://agentmods.dev/badge/skills/s977043/river-review/review-criteria-integrity/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-criteria-integrity"><img src="https://agentmods.dev/badge/skills/s977043/river-review/review-criteria-integrity.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 | $0.00320 | $0.05030 |
| Opus 5 | $0.00160 | $0.02515 |
| Sonnet 5 | $0.00064 | $0.01006 |
| Haiku 4.5 | $0.00032 | $0.00503 |
Grade A, and why
Review Criteria Integrity レビュー基準・品質ゲートの自己弱体化検出 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.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Origin / 由来
inspired by https://zenn.dev/nnku/articles/f6c7a62b78a47e
上記はレビュー基準の出所を固定する設計の紹介であり、本文の転載や著者による endorsement を含まない(nominative fair use)。
取り込むのは 「差分が自分のレビュー基準を弱めている」ことをレビュー観点として指摘する という一点に限る。記事が提示する仕組み(二層 Definition・blob SHA 記録・fallback 規則)は移植しない。それらは config schema と run record の変更を伴う別スライスであり、docs/adr/005-review-learning-loop-incremental-extension.md の「外部記事の自動化度をそのまま持ち込まない」前例に従って設計から分離する。
命名は skills/README.md Naming Q0–Q5 に従う。Q0 で「概念の再実装」に分類されるためリネームが既定となり、Q1 では原語 Review Definition が本リポジトリの既存語彙(.river/rules.md / rules / policy)と衝突する。Q2 で役割が変わる(記事は基準解決アルゴリズムの設計、本 skill はレビュー観点)ため、Q2 でリネーム確定とし、既存の *-integrity 命名ファミリ(fix-scope-integrity / plangate-plan-integrity)に揃えた review-criteria-integrity を付与した。原語は tags の review-definition に残す。
Pattern declaration
Primary pattern: Reviewer Secondary patterns: Inversion Why: 基準の弱体化はパターンとして拾えるが、「弱体化かどうか」と「正当な緩和か」の判定は意味的であり、比較基準(弱体化前の基準・宣言された意図)が discover できない差分では実行を止めるゲートが必要である。
Goal / 目的
レビュー基準・品質ゲートは被レビューエージェントの書込権限内にあり、PR 内で .river/rules.md を弱めた変更は、その PR 自身のレビュー基準に即時反映される(pages/explanation/security-model.md §「レビュー基準の出所」)。この信頼境界を diff-time の観点として可視化する。
次の 5 Check のいずれかに該当する変更が、機能変更と同一 PR に混在し、かつ意図の宣言が無い場合に指摘する。
- Check 1(レビュールール):
.river/rules.md/.river/rules.d/*の基準の削除・条件の弱体化。 - Check 2(実行時コンフィグの閾値・ゲート):
.river-review.{json,yaml,yml}のreview.severity引き下げ(strict→normal/relaxed)、exclude.filesの拡大、exclude.prLabelsToIgnoreの追加、memory.suppressionEnabled: false、selection.skills.excludeへの追加、selection.packsからの削除。 - Check 3(suppression entry): suppression entry の新規追加(
river suppression add相当の登録差分)。 - Check 4(lint・静的解析設定): lint / 型チェック設定からのルール削除・無効化(ESLint rule の
off化や削除、tsconfigのstrict系フラグの無効化、textlint / markdownlint のルール削除)。 - Check 5(branch protection・required check): branch protection / required status check の緩和(required check の削除、
strictの無効化、必須レビュー人数の引き下げ)。
report-only(ADR-005)。finding / question のみを出力し、自動修正・自動マージはしない。
What ships with it
4 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.
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 · 188 lines · 320 tokens per session scan A 64b7c20fd237
Review Criteria Integrity レビュー基準・品質ゲートの自己弱体化検出 is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed yesterday), licensed MIT. It adds 320 tokens to every session and 5,030 once invoked, about $0.0016 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
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…
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…