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 pr-descriptiongit 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/pr-description)<a href="https://agentmods.dev/skills/s977043/river-review/pr-description"><img src="https://agentmods.dev/badge/skills/s977043/river-review/pr-description/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/pr-description"><img src="https://agentmods.dev/badge/skills/s977043/river-review/pr-description.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 | $0.00029 | $0.00903 |
| Opus 5.5 | $0.00012 | $0.00361 |
| Sonnet 5.5 | $0.00006 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
PR Description Review 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 1mo 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: PR 本文の品質と差分整合をレビューする。PR 本文が無い場合は実行不要。
Goal / 目的
- PR 本文が「レビュー可能な状態」かを確認する（Why/What、影響範囲、テスト方針、関連リンク）。
- 本文の説明と差分の不整合（説明にあるが差分に無い／差分にあるが説明に無い）を検出する。
Non-goals / 扱わないこと
- コード品質・命名・型の指摘（他の midstream skill が担当）。
- 差分に存在しないコードへの推測。
- PR 本文の文体・体裁の好みの指摘。
Pre-execution Gate / 実行前ゲート
このスキルは以下が満たされない限り NO_REVIEW を返す。
- inputContext に
prDescriptionが含まれている（PR 本文が利用可能） - inputContext に
diffが含まれている
ゲート不成立時の出力: NO_REVIEW: pr-description — PR 本文が利用できないため評価対象なし
Guidance
- Why（変更理由）と What（変更内容）が PR 本文に明記されているか確認する。
- 本文の説明が差分と一致しているか確認する（記載と実装の乖離を指摘）。
- 影響範囲・破壊的変更の有無が書かれているか確認する。
- テスト方針 / 動作確認方法が書かれているか確認する。
- 関連 Issue / 仕様 / 設計へのリンクがあるか確認する。
Closes #N/Fixes #Nについて、リンク先 Issue の完了条件（受入条件・チェックリスト）が入力から読み取れる場合のみ diff と突合する。未達の条件があればRefsへの変更または残課題の明記を提案する。完了条件が入力から読み取れない場合、この突合は reviewee 側（/prcommand）の責務として指摘しない。- ja/en 対訳ファイル（
*.mdと*.en.md、pages/配下の対）の片側のみが diff に含まれ、本文にその理由が無い場合は指摘する。 - 本文の宣言（「〜は変更しない」等の変更対象外の宣言、件数・列挙）が実 diff と矛盾していないか確認する。
- PR 本文に関する指摘は対象を
PR-DESCRIPTION:0として出力する。
False-positive guards / 抑制条件
- 軽微な変更（タイポ修正等）で本文が簡潔な場合は過剰に要求しない。
- テンプレート未記入のセクションが明らかに不要な場合は黙る。
Output / 出力例
findings:
- severity: minor
file: PR-DESCRIPTION:0
issue: PR 本文に変更理由(Why)が書かれておらず、レビュアーが意図を判断できない
suggestion: 「なぜこの変更が必要か」を1〜2文で本文冒頭に追記する
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.
- 1mo ago First seen · 76 lines · 29 tokens per session scan A 0c80ed2b1097
PR Description Review is a skill published in the GitHub repository s977043/river-review (7 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 903 once invoked, about $0.0001 per session on Opus 5.5. 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
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.
shipyard-writing-plans
Breaks a spec, requirements, or design into an implementation plan with file paths and verification commands. Use for any multi-step task before touching code. Also use when the user says "plan this", "break this down", "create tasks", or "decompose this feature", when a task needs more than 2-3 steps, or when tasks…
shipyard-handoff
Captures session context into .shipyard/HANDOFF.md so the next session can resume without losing progress. Use when the user says "handoff", "save context", or "I'm done for now", or when a long session ends and its state should be recorded.
revert
Git-aware revert that understands Draft tracks, phases, and tasks. Safely undo work at task, phase, or track level. Use when the user asks to 'revert this track', 'undo a phase', 'revert task X', or says 'roll back the last task', 'undo this work'.
integrations
Canonical integrations parent command. Handles external system exports and syncs. Routes intent to jira-preview or jira-create based on context.
using-shipyard
Explains how to find and use Shipyard skills and commands, and requires a Skill tool call before any response, including clarifying questions. Use at the start of any conversation, or when the user asks "what should I do", "help me", "how do I use shipyard", or "where do I start". Also use when it is unclear which…