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 independent-review-synthesisgit 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/independent-review-synthesis)<a href="https://agentmods.dev/skills/s977043/river-review/independent-review-synthesis"><img src="https://agentmods.dev/badge/skills/s977043/river-review/independent-review-synthesis/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/independent-review-synthesis"><img src="https://agentmods.dev/badge/skills/s977043/river-review/independent-review-synthesis.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 | $0.00052 | $0.02278 |
| Opus 5 | $0.00026 | $0.01139 |
| Sonnet 5 | $0.00010 | $0.00456 |
| Haiku 4.5 | $0.00005 | $0.00228 |
Grade A, and why
Independent Review Synthesis 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 9d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal / 目的
複数 reviewer の指摘をそのまま採用せず、差分・周辺コード・テスト・既存レビュー結果に照らして検証し、merge 判断に資する形に統合する。
入力チャネル (artifact contract 参照: pages/reference/artifact-input-contract.md):
diff— 当該 PR の差分review-self— 実装者のセルフレビュー (Markdown)review-external— 外部レビュー結果 (AI / 人間、Markdown)findings-pool— 複数 Review Artifact から集約した findings 履歴 (JSON)fullFile(任意) — 該当ファイルの完全な内容
既定 CI レビューでは自動発火しない（/challenge 等の明示呼び出し向け）。
外部実証: 「実装したAIにレビューさせない——Claude Codeの3パス独立レビューと機械判定」（ピヨ助, 2026-08-03）は、実装時の会話に設計理由や試行錯誤の経緯が残る点を指摘します。そのため実装した AI が同じ変更のレビューも担う場合、自分の実装を追認する方向へ寄りやすくなります。同記事では、仕様を渡されていないレビュアーがコメントの前提と実際の処理内容との食い違いに気づき、Android 実機でのみ発生する重大な欠陥を発見しました。同じ箇所は、仕様を持つレビュアーには「設計どおり」に見えていたと述べられています。この事例は、reviewer / sourceKind といった出典の独立性を保ったまま統合するという本スキルの前提を裏付ける一次データとして参照できます。
外部実証（続報）: 「ループエンジニアリング実践ガイド (3/3) AI レビューの限界と本番化の境界」（タカシ, 2026-08-26）は、役割を割り当てた 9 名の並列レビューについて報告します。1 名を除く全員が同じモデルファミリで、違いは役割の指示だけでした。著者は「学習コーパスを共有するモデルは誤りが相関し、多数決の前提が崩れます」と述べ、役割の多様性がモデル多様性の代わりにならなかったと結論しています。単体では正しいものの並列時に矛盾する箇所へ気づいたレビュアーは、9 名中 1 名のみでした。この観測は、多数決で finding の採否を決めないという本スキルの Non-goals と、reviewer の出典独立性を保つ前提を裏付ける一次データとして参照できます。
Non-goals / 扱わないこと
- 新しいレビュー観点の追加 (security / a11y / performance などは個別 skill の責務)。
- 多数決で finding の採否を決めること。
- reviewer 固有のツール固定 (Claude / Codex / Cursor などの名前を skill body に直書きしない)。
- 推測ベースで critical / major に上げること (evidence 必須)。
False-positive guards / 抑制条件
- 入力 artifact (review-self / review-external / findings-pool) がすべて空 → 出力は
actions: []と "no reviewer inputs" 1 行で終了。silent skip にはしない。 findings-poolが schema 不一致でパース不能 → loud-fail (例外を投げる)。silent skip にしない。- 入力 reviewer が 1 つのみ → degraded mode で実行。出力に
agreement: []を明記、summary に "single-reviewer mode" を含める。
Rule / ルール
1. Collect — reviewer ごとに finding を収集
各 reviewer 出力から finding を抽出し、provenance (reviewer, sourceKind) を付与。
What ships with it
8 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.
- 9d ago First seen · 144 lines · 52 tokens per session scan A aa713b2d8a99
Independent Review Synthesis is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 2,278 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
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.
8eyes
Multi-agent adversarial code review via eight-eyes enforcement kernel.
pr-lifecycle
Full PR lifecycle management: list, analyze, validate, and merge pull requests. Auto-detects validation gates per package and integrates a code-review pass for code analysis. Use when: managing PRs, checking PR status, reviewing open PRs, merging PRs, triaging PRs, cleaning up stale PRs, validating PR readiness, or…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.