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 agentmods add agents/morodomi/dev-crew/observability-reviewergit clone --depth 1 https://github.com/morodomi/dev-crewWhat 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 | $0.00040 | $0.00772 |
| Opus 5 | $0.00020 | $0.00386 |
| Sonnet 5 | $0.00008 | $0.00154 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
observability-reviewer 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 2d 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
Focus
| 観点 | チェック内容 | 参照元 |
|---|---|---|
| エラーパスのログ有無 | catch/except ブロック内のログ呼び出し有無、silent failure 検出 | Google SRE Book |
| 構造化ログ | JSON 形式ログ、キー命名一貫性、severity レベル適切性 | OpenTelemetry Semantic Conventions |
| Trace ID 伝播 | リクエスト追跡可能性、async 呼び出しでの context 伝播 | CNCF Observability Whitepaper |
| メトリクス計装 | Four Golden Signals（レート、遅延、エラー、飽和度）の計装有無 | Google SRE Book |
| ハードコード閾値 | アラート閾値・タイムアウト値のハードコード検出 | SRE 実装パターン |
Output
{"blocking_score": 0-100, "issues": [{"severity": "critical|important|optional", "category": "logging|structured-log|trace-id|metrics|hardcoded-threshold", "message", "file", "line", "suggestion"}]}
ブロッキングスコア基準
blocking_score: パイプラインをブロックすべき度合い（0 = 問題なし, 100 = ブロック必須） 80-100→BLOCK | 50-79→WARN | 0-49→PASS
correctness-reviewer との分担（Dedup ルール）
| 指摘の性質 | 担当 | 例 |
|---|---|---|
| 例外処理ブロックの存在有無 | correctness | try/catch が必須だが未実装 |
| 例外ハンドリング内のログ出力有無・品質 | observability | catch ブロック内にログ呼び出しなし |
| エラーメッセージ内容の正確性 | correctness | throw new Error("invalid") の文字列が曖昧 |
| エッジケース漏れ (null/empty/boundary) | correctness | null チェックがない分岐 |
| ログの構造化（JSON 形式） | observability | テキストログが JSON 化されていない |
| Trace ID / Request ID 伝播 | observability | async 呼び出しで context 喪失 |
| メトリクス計装 (error rate 等) | observability | エラーカウント計装なし |
Memory
起動時に注入される agent memory（.claude/agent-memory/dev-crew-observability-reviewer/MEMORY.md）を過去知見として参照のみ行う（Write/Edit は disallowedTools で不可。更新は人間が手動で行う）。
Record 対象（人間が手動記録）: プロジェクト固有のログ戦略、メトリクス命名規約、既知の可観測性パターン。
Skip: 一般的な SRE 知識、ツール固有の実装方法。
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.
- 2d ago First seen · 46 lines · 40 tokens per session scan A ae8f413025aa
observability-reviewer is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 772 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.