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 adversarial-reviewgit 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/adversarial-review)<a href="https://agentmods.dev/skills/s977043/river-review/adversarial-review"><img src="https://agentmods.dev/badge/skills/s977043/river-review/adversarial-review/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/adversarial-review"><img src="https://agentmods.dev/badge/skills/s977043/river-review/adversarial-review.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 | $0.00141 | $0.02080 |
| Opus 5 | $0.00071 | $0.01040 |
| Sonnet 5 | $0.00028 | $0.00416 |
| Haiku 4.5 | $0.00014 | $0.00208 |
Grade A, and why
adversarial-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 11d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Review（敵対的レビュー）
通常のコードレビューは「正しさの確認」に集中する。 敵対的レビューは 「どう壊れるか」「どう攻撃されるか」「どこが論理的に弱いか」 に集中する。
背景 / Background
AIをレビューに使う最大の価値は、情報の整理ではなく 思考の死角を映す鏡 としての活用にある。 このスキルは、2系統の敵対的手法を体系化し、レビューの質を根本的に引き上げる。
認知バイアス対策（思考の死角）
| 手法 | 対策するバイアス | 核心の問い |
|---|---|---|
| Pre-mortem | 生存バイアス・楽観バイアス | 「失敗したとして、なぜ？」 |
| War Game | 自己中心バイアス | 「敵の立場から、どう攻撃する？」 |
| Logic Torturing | 確証バイアス | 「この論理の穴を潰して」 |
claim-vs-actual 検出（宣言・主張と実態の乖離）
| 手法 | 対象とするズレ | 核心の問い |
|---|---|---|
| Self-Contradiction | 宣言と同一ファイルの実装 | 「規則 X を宣言した本人が破っていない？」 |
| Refactor-Claim Audit | 完了主張と残骸 | 「『全部やった』を grep で反証できる？」 |
| Cross-File Leakage | 構造変更と caller 側 | 「直したのは変更元だけ、参照元は？」 |
When to Use / いつ使うか
- 設計判断やアーキテクチャ変更を含むPRのレビュー時
- セキュリティに影響する変更のレビュー時
- 重要な技術選択の妥当性を検証したいとき
- 「本当にこれで大丈夫か？」という不安があるとき
Routing / ルーティング
入力に応じて、適切な手法へルーティングする。複数手法の併用も可能。
| キーワード | 手法 | スキルID |
|---|---|---|
| 失敗, リスク, 負債, インシデント, pre-mortem | Pre-mortem | pre-mortem |
| 攻撃, セキュリティ, 悪用, 脆弱性, war-game | War Game | war-game |
| 論理, 判断, 根拠, なぜ, 代替案, logic | Logic Torturing | logic-torturing |
| 自己矛盾, contradiction, 宣言と実装, declared but | Self-Contradiction | self-contradiction |
| 削減, 完了, 全て置換, all replaced, -N%, リファクタ | Refactor-Claim Audit | refactor-claim-audit |
| caller, 残骸, 参照漏れ, 再採番, leakage | Cross-File Leakage | cross-file-leakage |
| 敵対的, adversarial, 全部, フル | 全手法実行 | 上記6つすべて |
What ships with it
1 file 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.
- 11d ago First seen · 155 lines · 141 tokens per session scan A 9eb9f3421fad
adversarial-review is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed today), licensed MIT. It adds 141 tokens to every session and 2,080 once invoked, about $0.0007 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 skills, from other repositories
code-gauntlet
Prefer this skill for code review requests — it runs a multi-agent pipeline with blind challenge verification for high-confidence results. Trigger for ANY of these situations: (1) user says "review" in the context of code, PRs, MRs, branches, diffs, or changes, (2) user references a PR/MR number and wants feedback or…
evjs
Develop, migrate, review, document, or debug evjs applications and framework code involving file-based pages, ev.config.ts, server functions, API routes, rendering, plugins, development, builds, and deployment.
build-review-md
Use this skill when the user wants to create or set up a REVIEW.md configuration file for their repository. Trigger for ANY of these: (1) user says "create REVIEW.md", "set up REVIEW.md", or "configure review rules", (2) code-gauntlet Phase 2d detects no REVIEW.md and suggests creating one, (3) user wants to customize…
challenge
Adversarial review — Fable 5 stress-tests reasoning, Gemini checks knowledge. Use before plan or architecture decisions.
ttb-skill-audit
Code audits for TTBaseUIKit apps: performance, accessibility, localization. FCR compliance scoring.
code-review-adversarial
Deep code review via a committee of specialized reviewers with PR-type-aware playbooks and convergence. Feature PRs → evaluate better alternatives; bugfix PRs → verify fix correctness + regression; design-heavy PRs (proto/contract only) → AIP/compatibility audit. Dispatches 2-4 reviewers from distinct stances…