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 adr-decision-qualitygit 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/adr-decision-quality)<a href="https://agentmods.dev/skills/s977043/river-review/adr-decision-quality"><img src="https://agentmods.dev/badge/skills/s977043/river-review/adr-decision-quality/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/adr-decision-quality"><img src="https://agentmods.dev/badge/skills/s977043/river-review/adr-decision-quality.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 | $0.00028 | $0.01209 |
| Opus 5 | $0.00014 | $0.00605 |
| Sonnet 5 | $0.00006 | $0.00242 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
ADR Decision Quality 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 7d 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
Pattern declaration
Primary pattern: Reviewer Secondary patterns: Inversion Why: ADRの記録品質を多面的チェックリストで検証し、不足を指摘して将来の設計ドリフトを防ぐ。
Goal / 目的
- ADR（設計意思決定記録）の差分から、将来の設計ドリフト/再議論/運用事故につながる “記録不足” を減らす。
Non-goals / 扱わないこと
- 技術選定の正解を断定しない（代替案とトレードオフの “記録の質” を見て指摘する）。
- ADR の書式統一や文章校正を主目的にしない（重要論点の不足を優先）。
Pre-execution Gate / 実行前ゲート
このスキルは以下の条件がすべて満たされない限りNO_REVIEWを返す。
- 差分にADR関連ファイル（
docs/adr/,adr/,*.adr,*adr*.md）が含まれている - 差分がADRの意思決定内容（Context / Decision / Alternatives / Follow-ups）に実質的な変更を含んでいる
- inputContextにdiffが含まれている
ゲート不成立時の出力: NO_REVIEW: adr-decision-quality — ADR関連ファイルの実質的変更なし
False-positive guards / 抑制条件
- 既に別 ADR で合意済みの内容を単に参照しているだけなら、重複指摘しない（参照先が明確な場合）。
Rule / ルール
- まず「何を決めた ADR か / 何が未決か」を 1 行で要約する。
- 指摘は最大 8 件まで。将来の混乱コストが大きいもの（互換性・移行・運用・セキュリティ）を優先。
- 不明点は “質問” で出すが、可能なら “追記テンプレ” を添える。
Checklist / 観点チェックリスト
- Context
- なぜ今この意思決定が必要か（背景/課題/制約）があるか。
- 影響範囲（利用者/システム/データ/運用）が明示されているか。
- Decision
- 決定事項が 1〜3 行で明確か（何を採用し、何をしないか）。
- 成功条件/受け入れ条件（どの状態なら “成功” か）があるか。
- Alternatives & Tradeoffs
- 代替案が最低 1 つ、却下理由とトレードオフがあるか。
- 既存との互換性（API/データ/運用）の扱いがあるか。
- Follow-ups
- 未決事項/TODO/期限/決める人が書かれているか。
- 関連ドキュメント/実装/運用手順へのリンクがあるか。
Output / 出力フォーマット
すべて日本語。<file>:<line>: <message> 形式で出力する。
- 先頭に要約を 1 行:
(summary):1: <ADRの決定事項/未決の要点> - 以降は指摘（最大 8 件）:
<message>に[severity=critical|major|minor|info]を含める。- 可能なら “追記テンプレ” を付ける（短文で貼れる形）。
追記テンプレ例:
背景/制約: <何が課題で何が制約か>代替案: A=<案>, B=<案> / 却下理由=<理由> / トレードオフ=<何を犠牲に何を得るか>成功条件: <可観測な条件（メトリクス/ログ/運用上の状態）>
評価指標（Evaluation）
- 合格基準: 記録不足による将来の混乱を防ぐ指摘が、差分に紐づき、追記案（テンプレ）付きで出ている。
- 不合格基準: 技術的主張の押し付け、差分と無関係な理想論、指摘過多。
人間に返す条件（Human Handoff）
- トレードオフが組織/予算/法務に跨る場合、または意思決定者の明確化が必要な場合は人間レビューへ返す。
What ships with it
2 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.
- 7d ago First seen · 94 lines · 28 tokens per session scan A b5940ed99af8
ADR Decision Quality is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,209 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
punchcard
Architecture-level design review of a code change: module boundaries, dependency direction, data model, error paths, cost of the next change — never naming, formatting, or anything a linter catches. Use when the user invokes /punchcard, says 'punchcard review', or asks for any design, architecture, or structural…
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…
deep-plan
Creates detailed, sectionized, TDD-oriented implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
audit
Audit a documentation-led repo against its own conventions — contiguous ADR numbering, INDEX sync, plan/ coverage, required sections, status validity, cross-reference resolution, language mandate, ADR-privacy leaks into user-visible code, cross-worktree collisions (duplicate numbers, duplicate plan ownership, same ADR…
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.