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 cross-file-leakagegit 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/cross-file-leakage)<a href="https://agentmods.dev/skills/s977043/river-review/cross-file-leakage"><img src="https://agentmods.dev/badge/skills/s977043/river-review/cross-file-leakage/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/cross-file-leakage"><img src="https://agentmods.dev/badge/skills/s977043/river-review/cross-file-leakage.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 | $0.00079 | $0.01757 |
| Opus 5 | $0.00039 | $0.00879 |
| Sonnet 5 | $0.00016 | $0.00351 |
| Haiku 4.5 | $0.00008 | $0.00176 |
Grade A, and why
Cross-File Leakage リファクタ後の caller 側残骸検出 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.
How it starts
The opening of the file, as written. The whole thing — 129 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: 構造変更に対する caller 走査は grep による決定論的突合が主だが、構造変更を含まない変更では実行を止めるゲートが必要
Goal / 目的
- スキル/モジュールを構造変更したとき、当該ファイルは更新したが caller 側 N 箇所が古い構造を参照したまま 残るパターンを検出する。
- 「変更元は直したが、参照元を直し忘れた」ドリフトを、変更の波及範囲を grep で追って可視化する。
Non-goals / 扱わないこと
- 構造変更そのものの良し悪しの判断。
- 静的型エラーの検出（型システムが捕捉できる drift はコンパイラ/tsc の役割）。
- 当該ファイル内の整合性（それは
self-contradictionの領域）。
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。
- 差分に構造変更（記号の再採番、シンボル名変更、シグネチャ変更、セクション番号の振り直し、ファイル分割・移動）が含まれている
- inputContext に diff が含まれている
ゲート不成立時の出力: NO_REVIEW: cross-file-leakage — 構造変更が検出されない
False-positive guards / 抑制条件
- 旧構造への参照を grep しても caller 側に残骸が見つからない場合は指摘しない。
- 残骸が意図的（旧 API の互換 shim、移行期間中の dual-reference）で差分内に明記がある場合は抑制。
- 参照が文字列として同一でも別シンボル/別スコープを指す場合は抑制。
Rule / ルール
検出ロジック
- 構造変更の特定: 差分から「何がどう変わったか」を抽出する（旧シンボル→新シンボル、
§2.1→新採番、foo(a)→foo(a, b)、ファイル A→分割後）。 - caller の列挙: 旧構造の識別子（旧シンボル名・旧参照形式・旧パス）を repo 全体に grep し、参照している全箇所を列挙する。
- 残骸の判定: 列挙した参照のうち、今回の差分で更新されていないものを残骸として特定する。
- 波及の報告: 残骸を
<file>:<line>と検索語で示し、更新漏れの caller を網羅的に挙げる。
制約
- 検出は最大 5 件（同一原因の残骸はまとめて1件とし、影響ファイルを列挙）。
- 各指摘には「構造変更」「旧構造の検索語」「未更新の caller 位置」を必ず含める。
- caller の列挙は grep で再現可能にし、「N 箇所」と件数を明示する。
Evidence / 根拠の取り方
- 残骸は必ず
<file>:<line>と grep 検索語を示し、推測で件数を述べない。 - 「構造がどう変わったか」を旧→新で具体的に示し、なぜ caller が壊れる/古いかを説明する。
Output / 出力フォーマット
すべて日本語。
(cross-file-leakage):1: [要約] 最も影響の大きい未更新 caller は〈1文〉
<file>:<line>: [caller 残骸1] <タイトル>
構造変更: <旧構造> → <新構造>(変更元: <file>:<line>)
検索語: `<grep pattern>`
未更新の caller: <N>箇所 — <file:line>, <file:line>, ...
影響: <古い参照が引き起こす不整合/破壊>
Fix: <caller 側 N 箇所を新構造に更新する>
<file>:<line>: [caller 残骸2] ...
Good / Bad Examples
Good
review-output/SKILL.md:1: [caller 残骸] §再採番後に caller 9ファイルが旧セクション番号を参照
構造変更: review-output SKILL.md を §1-§6 構成に再採番(review-output/SKILL.md:1)
検索語: `§(2\.1|4\.4|3-R)`
未更新の caller: 9箇所 — a/SKILL.md:12, b/SKILL.md:30, scripts/build.py:88, ...
影響: caller が存在しない旧セクション番号を指し、参照が解決不能
Fix: caller 9ファイルの §2.1/§4.4/§3-R を新採番に更新
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 · 129 lines · 79 tokens per session scan A bcb807b500ed
Cross-File Leakage リファクタ後の caller 側残骸検出 is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,757 once invoked, about $0.0004 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
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
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…
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.
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.
omnicreate-github
Use when creating a GitHub pull request (OmniForge). Auto-populates title and description from commits, supports draft PRs, labels, assignees, reviewers, and issue linking.
omnifix-github
Use when fixing review findings on a GitHub PR, resolving inline review threads, applying code review suggestions, or when asked to fix issues from an OmniForge report.