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.
git 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/commands/s977043/river-review/review-team)<a href="https://agentmods.dev/commands/s977043/river-review/review-team"><img src="https://agentmods.dev/badge/commands/s977043/river-review/review-team/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/commands/s977043/river-review/review-team"><img src="https://agentmods.dev/badge/commands/s977043/river-review/review-team.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 | $0.00016 | $0.00996 |
| Opus 5 | $0.00008 | $0.00498 |
| Sonnet 5 | $0.00003 | $0.00199 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
review-team 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.
What it actually says
スキル定義: skills/agent-skills/review-team/SKILL.md
Context
- Status:
git status - Diff:
git diff - Recent commits:
git log --oneline -10
差分がない場合は「差分がありません」と伝えて終了する。
Task
review-team スキルの手順に従い、現在の差分をレビュー・チームで検査する。
Step 1: ロールを決定する
引数でロールが指定された場合はそれを使う。なければ auto(差分から自動選択)。
Step 2: レビューを実行する
River Review は npm 未公開のため npx river-review は使えない。エージェントがこのスキルの手順を直接実行する(CLI 不要)。上記 Step 1 で決めたロールを並列に走らせ、Union-Find で finding を統合し、consensusLevel と teamLeadReport を生成する。
リポジトリ内で作業していて river CLI をアクセラレータとして使える場合のみ、次を利用してよい(任意)。コスト確認が必要なら先に --dry-run。
# auto モード(推奨)
npm run river -- run . --reviewers auto --output json
# ロール明示指定
npm run river -- run . --reviewers <role1,role2,...> --output json
CLI が存在しない、または失敗した場合は、スキル駆動のレビューで継続する。
Step 3: 結果を報告する
用語(skills/agent-skills/review-team/SKILL.md の「Output Interpretation / 結果の読み方」が出典):
scope: 指摘が本 PR の追加行に由来するかを示す finding のメタデータ。値はin-diff/pre-existingの 2 つin-diff: 本 PR が追加行で持ち込んだ問題。既定値であり fail-safe でもあるため、値が無い finding もこの扱いになるpre-existing: 変更ファイル内だが追加行の外にある既存コードへの指摘。文脈参考として扱い、本 PR のスコープを超えた修正を招かないようにするconsensusLevel: 同じ finding を挙げたロール数のバケット。consensus(3 以上)/multi(2)/single(1 以下)- 並び順のキーは
consensusLevel→severity→scopeである。consensusLevelがseverityに優先し、severityは同値のときだけ次のキーへ進む
JSON 出力(teamLeadReport / issues)をもとに以下の形式で報告する。
## レビュー・チーム 結果
### 実行ロール
<reviewerRole の一覧>
### 優先確認の指摘(top3)
<consensusLevel → severity → scope 順の上位3件。multi は ★★、consensus は ★★★ を付ける。scope は上位2キーが同値のときだけ in-diff を先に置く。pre-existing の finding には file:line の直後に `_(pre-existing)_` を付ける>
### 全指摘(severity 降順)
<critical → major → minor → info の順。scope が pre-existing の finding には file:line の直後に `_(pre-existing)_` を付ける。in-diff(本 PR の追加行由来)は既定値なので印を付けず、pre-existing(変更ファイル内だが追加行の外)だけを示す>
### 見落とし可能性
<blindSpots の label。空なら「なし(全ロールを実行済み)」>
### コンセンサス集計
consensus: N件 / multi: N件 / single: N件
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 · 75 lines · 16 tokens per session scan A b2de7ac7f1cc
review-team is a command published in the GitHub repository s977043/river-review (3 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 996 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 commands, from other repositories
consensus-review
Consensus code review (Opus arbiter + codex, optional pi advisor) across 4 dimensions (architecture/quality/impact/tests) for a PR or uncommitted changes; P0–P2 findings; strict sceptic by default; every flag also accepted with a leading -.
architecture-audit
One-shot architecture audit — layers, slices, contracts, paradigms, complexity.
logic-diff
Check two code versions for semantic equivalence — use after a refactor or rewrite.
logic-review
Review code for logic bugs — use when you suspect something is wrong but have no failing test yet.
arch-review
Architectural impact review of a change (diff-scoped) via the arch-reviewer agent.
impact-review
Review of a change and its impact on adjacent parts via the impact-reviewer agent.