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 failure-modes-observabilitygit 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/failure-modes-observability)<a href="https://agentmods.dev/skills/s977043/river-review/failure-modes-observability"><img src="https://agentmods.dev/badge/skills/s977043/river-review/failure-modes-observability/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/failure-modes-observability"><img src="https://agentmods.dev/badge/skills/s977043/river-review/failure-modes-observability.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 | $0.00027 | $0.01097 |
| Opus 5.5 | $0.00011 | $0.00439 |
| Sonnet 5.5 | $0.00005 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
Failure Modes & Observability in Design 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: 設計の差分から失敗モード・エラー契約・観測性の抜けをレビューし、障害シナリオを逆照射してクリティカルフローの堅牢性を検証する。
Rule / ルール
- クリティカルフロー（認証、課金、データ保存など）の失敗モード（タイムアウト、リトライ、フォールバック、外部障害、権限不備）を明示する。
- エラー応答（ステータス、エラーコード、message/detail）の契約を一貫させ、クライアントが判断できる形にする。
- SLO/監視、ログ、メトリクス、トレースなどの観測性を設計に含める。
Heuristics / 判定の手がかり
- 外部依存（DB/HTTP/Queue）の失敗時に「何が起きるか」が仕様に無い（例: リトライ方針、タイムアウト、冪等性）。
- 4xx/5xx の使い分け、エラー構造がエンドポイントごとに不揃い。
- Rate limit / backoff / circuit breaker の前提があるのに、設計/ADR で触れられていない。
- 障害時の切り分けに必要なログ（相関ID、requestId、重要な属性）やメトリクスの設計が無い。
Questions / 確認質問（不明な場合は質問として出す）
- 代表的な失敗モード（タイムアウト、外部 5xx、バリデーション、権限、競合）はどれですか？
- 冪等性キーやリトライ可否の判断はどこで担保しますか？
- 監視対象（SLO、エラーバジェット、アラート条件）はありますか？
Actions / 改善案
- タイムアウト値、リトライ回数、バックオフ、フォールバックを ADR/設計に追記する。
- エラー応答の共通スキーマ（code/message/detail/requestId など）を定義し、例を載せる。
- クリティカルフローに相関IDを付与し、ログ/トレースのキーを設計に含める。
Non-goals / 扱わないこと
- 実際の監視基盤やアラート運用の構築。
- 既存プロダクション障害の原因究明。
- 実装詳細（ログライブラリ選定など）の決定。
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API定義・ルート定義・設計ドキュメントのいずれかが含まれている
- inputContextにdiffが含まれている
ゲート不成立時の出力: NO_REVIEW: failure-modes-observability — 失敗モード/観測性に関連する設計差分がない
False-positive guards / 抑制条件
- 失敗モード/観測性が別 ADR で既に合意され、差分が参照更新のみ。
- 影響範囲がローカルな試験コードで、運用対象外と明記されている。
評価指標（Evaluation）
- 合格基準: 指摘が差分に紐づき、根拠と次アクションが説明されている。
- 不合格基準: 差分と無関係な指摘、根拠のない断定、抑制条件の無視。
人間に返す条件（Human Handoff）
- 仕様や意図が不明確で解釈が分かれる場合は質問として返す。
- 影響範囲が広い設計判断やトレードオフは人間レビューへ返す。
What ships with it
4 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.
- 1mo ago First seen · 81 lines · 27 tokens per session scan A 98d0b00d7e4c
Failure Modes & Observability in Design is a skill published in the GitHub repository s977043/river-review (7 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,097 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
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.
spine-design
Produce a system design doc — components, data flow, decisions made, tradeoffs, failure modes. Not a list of options. An actual design with calls made. Use when asked for "system design for", "architect this", "how should we build", or "design the backend".
vigil-instrument
Instrument a service with OpenTelemetry — RED metrics, structured logs, distributed tracing, and health checks. Outputs actual code and config, not a plan. Use when asked to "add monitoring", "instrument this", "add logging", "set up tracing", or "observability".
spine-review
API and backend code review — REST conventions, auth, validation, error handling, pagination, rate limiting, test coverage. Use when asked to "review this API", "code review", "review backend", or "pre-launch backend check".
vigil-incident
Incident response — diagnose production issues, find root cause, propose fix with rollback. Use when asked about "something is broken", "production issue", "why is this down", "incident", or "debug production".
spine-perf
Find and fix performance bottlenecks — N+1 queries, missing indexes, sync bottlenecks, caching gaps. Use when asked "why is this slow", "performance issue", "optimize this endpoint", or "N+1 queries".