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 trust-boundaries-authzgit 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/trust-boundaries-authz)<a href="https://agentmods.dev/skills/s977043/river-review/trust-boundaries-authz"><img src="https://agentmods.dev/badge/skills/s977043/river-review/trust-boundaries-authz/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/trust-boundaries-authz"><img src="https://agentmods.dev/badge/skills/s977043/river-review/trust-boundaries-authz.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 | $0.01353 |
| Opus 5 | $0.00014 | $0.00677 |
| Sonnet 5 | $0.00006 | $0.00271 |
| Haiku 4.5 | $0.00003 | $0.00135 |
Grade A, and why
Trust Boundaries & Authorization Architecture 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: 信頼境界・認可設計はチェックリスト型評価が主だが、セキュリティ設計無関係の差分では実行を止めるゲートが必要
Goal / 目的
- 設計差分から、信頼境界（trust boundary）と認証/認可（authn/authz）の責務が曖昧なまま実装に入るリスクを減らす。
Non-goals / 扱わないこと
- 具体プロダクトやクラウドの “正解構成” の押し付け。
- 実装コードの脆弱性レビュー（設計上の責務/契約のレビューに限定）。
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。
- 差分にセキュリティ設計・認証/認可・信頼境界に関連するドキュメント変更が含まれている
- 誤字・リンク更新のみの変更ではない
- inputContextにdiffが含まれている
ゲート不成立時の出力: NO_REVIEW: trust-boundaries-authz — 信頼境界・認可設計に関連する変更が検出されない
False-positive guards / 抑制条件
- 参照先（セキュリティ設計書/権限仕様）ですでに明確で、差分が参照更新のみの場合は重複指摘しない。
Rule / ルール
- 先頭に要約を 1 行出す（新規/変更された境界、主体、権限の要点）。
- 指摘は最大 8 件まで。
[severity=critical]は “権限漏れ/越境の温床” に限定する。 - 質問だけで終わらせず、可能なら “追記案（貼れる形）” を付ける。
Checklist / 観点チェックリスト
- Trust boundary
- どこが信頼境界か（外部→内部、サービス間、ネットワーク境界）が明示されているか。
- 境界を跨ぐときに “何を信頼できる/できない” かが書かれているか。
- Authn/Authz の責務
- 認証（authn）と認可（authz）を “どこで” 判定するかが明示されているか。
- Gateway/BFF/各サービスの責務分担（中央集約か分散か）が明記されているか。
- Identity/Claims の伝播
- ユーザーID/tenantId/role/scope などの claims をどの形で伝播するか（token/headers/mtls 等）があるか。
- 伝播情報の検証（署名/改ざん防止）と、サービス側での再検証の方針があるか。
- 監査と特権操作
- 管理操作やデータ閲覧など、監査対象の操作が明示されているか。
- 誰がいつ何をしたか（監査ログの最低要件）があるか。
- 認可の粒度
- 代表的なユースケースの権限マトリクス（役割×操作×リソース）があるか。
- マルチテナントなら tenant 境界（越境防止）の前提があるか。
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: <信頼境界/権限境界の要点> - 以降は指摘（最大 8 件）:
<message>に[severity=critical|major|minor|info]を含める。- 可能なら “追記案” を 1 行付ける。
追記案例:
権限マトリクス: role={Admin,User}, action={read,write,delete}, resource={X} を表に追記境界: 外部→Gateway→ServiceA の trust boundary と、token 検証責務を明記
評価指標（Evaluation）
- 合格基準: 差分に紐づく信頼境界/認可責務の曖昧さが、優先度付きで指摘され、追記案がある。
- 不合格基準: 根拠のない断定、差分と無関係な一般論、指摘過多。
人間に返す条件（Human Handoff）
- 権限設計が規制/契約/組織ポリシーに跨る場合は人間（セキュリティ/法務）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 · 101 lines · 28 tokens per session scan A 918ce9f615c6
Trust Boundaries & Authorization Architecture is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,353 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…
application-patterns
Architecture pattern selection, folder structures, coding conventions, error handling, testing strategies, and platform-specific patterns for structuring application code.
python-services
Python patterns for CLI tools, async parallelism, and backend services. Use when building CLI apps, async/parallel Python, FastAPI services, background jobs, or configuring Python project tooling (uv, ruff, ty).
nodejs-backend
Node.js backend patterns: framework selection, layered architecture, TypeScript, validation, error handling, security, production deployment. Use when building REST APIs, Express/Fastify servers, microservices, or server-side TypeScript.
backend-clean-architecture
Use this skill when the user asks 'where does this code go', 'what layer', 'clean architecture', 'hexagonal', 'ports and adapters', 'domain layer', 'application layer', 'infrastructure layer', 'should this be in service or repository', or when designing or reviewing backend code organization. This skill enforces…
php-laravel
Modern PHP 8.2+ and Laravel patterns: architecture, Eloquent, queues, Pest testing. Use when asked to "write PHP", "build a Laravel app", "fix Eloquent query", "add a queue job", "write a Pest test", or mentions PHP, Laravel, Eloquent, Blade, artisan, or migrations.