Logic Torturing 論理検証

Logic Torturing 論理検証 is a skill for Claude Code from s977043/river-review. It costs 57 tokens per session (1,799 once invoked), scanned A, original, MIT.

A review method for testing the reasoning behind design choices and implementation decisions in a code change.

In plain words
What is it for?
It questions non-mechanical changes such as new data structures, dependencies, algorithms, error strategies, and API designs.
Why use it?
It exposes weak assumptions, overlooked alternatives, boundary cases, conflicts with existing design, and decisions that are costly to reverse.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the river-review plugin — 138 skills, 18 commands, 5 agents, 3 hooks shipped together

Good fit It questions non-mechanical changes such as new data structures, dependencies, algorithms, error strategies, and API designs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/s977043/river-review/logic-torturing
Install

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.

Any agent
npx skills add s977043/river-review --skill logic-torturing
Clone the repo
git clone --depth 1 https://github.com/s977043/river-review

Made for: Claude Code.

Or install river-review, the plugin that ships this one along with the rest of its 138 skills, 18 commands, 5 agents, 3 hooks.

Wrote 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.

agentmods badge for Logic Torturing 論理検証

README.md
[![agentmods](https://agentmods.dev/badge/skills/s977043/river-review/logic-torturing/github.svg)](https://agentmods.dev/skills/s977043/river-review/logic-torturing)
Your own site
<a href="https://agentmods.dev/skills/s977043/river-review/logic-torturing"><img src="https://agentmods.dev/badge/skills/s977043/river-review/logic-torturing/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.

agentmods 80×15 button for Logic Torturing 論理検証

Your own site · 80×15
<a href="https://agentmods.dev/skills/s977043/river-review/logic-torturing"><img src="https://agentmods.dev/badge/skills/s977043/river-review/logic-torturing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,799 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01799
Opus 5 $0.00028 $0.00899
Sonnet 5 $0.00011 $0.00360
Haiku 4.5 $0.00006 $0.00180

Measured 5d ago against content hash e16045ca296f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Logic Torturing 論理検証 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 5d 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.

skills/midstream/logic-torturing/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pattern declaration

Primary pattern: Reviewer Secondary patterns: Inversion Why: 論理検証はチェックリスト型評価が主だが、判断を含まない変更では実行を止めるゲートが必要

Goal / 目的

  • 変更に含まれる設計判断・技術選択・実装方針の論理的な穴を徹底的に突き、確証バイアスを排除する。
  • 「なぜその選択なのか」「他の選択肢はなぜ棄却されたのか」「前提が変わっても成立するか」を問い続け、判断の耐久性を検証する。
  • 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)。

Non-goals / 扱わないこと

  • コードスタイルや命名規則の指摘。
  • 既知のバグパターンの検出(それは他のスキルの役割)。
  • 著者の判断を否定すること自体が目的ではない(より強固な判断にすることが目的)。

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。

  • 差分に設計判断・技術選択・実装方針の判断を含む変更がある
  • 変更が機械的なもの(リネーム、フォーマット、依存更新のみ)ではない
  • inputContextにdiffが含まれている

ゲート不成立時の出力: NO_REVIEW: logic-torturing — 論理検証の対象となる判断が検出されない

False-positive guards / 抑制条件

  • ADRや設計ドキュメントですでに代替案とトレードオフが十分に記述されている場合は重複指摘しない。
  • 些末な判断(変数名の選択、import順序など)には適用しない。

Rule / ルール

検証フレームワーク

変更内の判断を発見したら、以下の5つの問いを順に適用する:

  1. 前提の検証: 「この判断が依存している前提は何か?その前提は常に成立するか?」
  2. 代替案の検証: 「他にどんな選択肢があったか?なぜそれらは劣るのか?」
  3. 境界条件の検証: 「この判断が破綻する条件は何か?入力の極端値、負荷の増大、依存の変化」
  4. 整合性の検証: 「この判断は既存のアーキテクチャ/設計原則と矛盾しないか?」
  5. 可逆性の検証: 「この判断が間違いだとわかったとき、元に戻せるか?コストは?」

判断の検出基準

以下のシグナルから「判断」を検出する:

  • 新しいデータ構造・スキーマの導入
  • 依存ライブラリの追加・変更
  • アルゴリズムやデータフローの変更
  • エラーハンドリング戦略の選択
  • API設計(エンドポイント、レスポンス形式)の決定
  • 設計ドキュメントの「Decision」「選定理由」セクション

制約

  • 論理的な穴の指摘は最大 5 件。判断への影響が大きいものを優先。
  • 各指摘には必ず「問い」と「なぜこれが問題か」と「強化方法」を含める。
  • 反論のための反論はしない。建設的な問いに限定する。

Evidence / 根拠の取り方

  • 判断箇所を差分の具体的な行に紐づける(<file>:<line>)。
  • 問いの根拠を既存コード、設計原則、業界標準から引用する。
  • 「〜の可能性がある」と「〜である」を明確に区別する。

Output / 出力フォーマット

すべて日本語。

(logic-torturing):1: [要約] この変更で最も検証が必要な判断は〈1文〉

<file>:<line>: [論理検証1] <判断の要約>
  問い: <この判断の論理的な穴を突く質問>
  なぜ問題か: <この穴が放置された場合の具体的なリスク>
  強化方法: <判断をより強固にするためのアクション>

<file>:<line>: [論理検証2] ...

Good / Bad Examples

Good

src/core/skill-dispatcher.mjs:112: [論理検証] スキル選択でファイルパターンのみを基準にしている判断
  問い: ファイルパターンだけでスキルの適用可否を判断しているが、同じパスに設計変更とフォーマット変更が混在する場合、過剰なスキルが発火しないか?
  なぜ問題か: 不要なスキルの発火はレビューコスト増加と誤検知増加に直結する。差分の内容(セマンティクス)を考慮しないパターンマッチは、ファイル数の増加に比例して精度が劣化する。
  強化方法: パターンマッチ後に差分の変更種別(構造変更/スタイル変更/コメントのみ)を判定するフィルタを追加する。

Read the full file on GitHub · 134 lines

Changes

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.

  1. 5d ago First seen · 134 lines · 57 tokens per session scan A e16045ca296f

Subscribe to this mod's changes

Logic Torturing 論理検証 is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,799 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.

Related

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…

liatrio-labs/claude-code-gauntlet · 218 tokens

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…

hyhmrright/logic-lens · 180 tokens

logic-diff

Compare two code versions for semantic equivalence via semi-formal tracing of both versions side-by-side. Trigger when the user shares a refactor, rewrite, migration, or A/B implementation and wants to confirm behavior is unchanged — "did I break anything", "is this equivalent", "are these equivalent", "semantically…

hyhmrright/logic-lens · 192 tokens

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.

nexiouscaliver/OmniForge · 41 tokens

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.

nexiouscaliver/OmniForge · 40 tokens

omnicreate-gitlab

Use when creating a GitLab merge request (OmniForge). Auto-populates title and description from commits, supports draft MRs, labels, assignees, reviewers, and issue linking.

nexiouscaliver/OmniForge · 45 tokens