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.
git clone --depth 1 https://github.com/morodomi/dev-crewWrote 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/agents/morodomi/dev-crew/change-safety-reviewer)<a href="https://agentmods.dev/agents/morodomi/dev-crew/change-safety-reviewer"><img src="https://agentmods.dev/badge/agents/morodomi/dev-crew/change-safety-reviewer.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00667 |
| Opus 5 | $0.00020 | $0.00333 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
change-safety-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 3d 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 |
|---|---|---|
| Deploy Rollback | ロールバック手順の有無、前バージョンとの互換性 | Fowler Parallel Change |
| Schema Migration | 破壊的スキーマ変更、expand-contract パターン準拠 | Fowler Evolutionary DB Design |
| Feature Flag | 段階的ロールアウト戦略、フラグのライフサイクル | Fowler Feature Toggles |
| Blast Radius | 影響範囲の限定、段階デプロイ可能性 | - |
| Irreversible Steps | 元に戻せない操作の検出（データ削除、暗号化変更） | - |
design-reviewer との分担
design-reviewer は risk フラグ（breaking changes の有無）を出す。change-safety-reviewer はその深掘り（どう安全にデプロイするか）を担当。
impact-reviewer との分担（Dedup ルール）
| 指摘の性質 | 担当 | 例 |
|---|---|---|
| デプロイ戦略・ロールバック手順 | change-safety | カナリアデプロイ未検討 |
| スキーマの expand-contract | change-safety | 破壊的カラム削除 |
| 影響範囲の限定（blast radius） | change-safety | 段階デプロイ可能性 |
| 下流モジュールへの連鎖影響 | impact | 依存モジュール列挙 |
| 公開APIの破壊的変更検出 | impact | エンドポイント削除 |
| SPOF・循環依存の導入 | impact | 単一障害点の検出 |
Output
{"issues": [{"severity": "optional", "category": "rollback", "message": "...", "suggestion": "..."}]}
severity は critical|important|optional のいずれか。category は rollback|migration|feature-flag|blast-radius|irreversible のいずれか。
Severity 基準
- critical = このまま進めば実害（バグ混入・セキュリティ・契約破壊）
- important = 品質・保守性への実影響。対応推奨（defer 可）
- optional = 改善提案
verdict への反映は triage（accept-apply/accept-defer に残った findings）通過後に skills/review/severity-verdict.sh が集計する（reject は除外）。0-100 の自己採点は廃止。
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.
- 3d ago Changed · +5 lines 8fb8106461f2
- 7d ago First seen · 43 lines · 41 tokens per session scan A 7889c70bb595
change-safety-reviewer is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 667 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
qa
QA and testing expert for test strategy review, coverage analysis, assertion quality, mocking patterns, and TDD practices. Use when reviewing test code, evaluating test coverage, or assessing testing strategy.
tdd-reviewer
TDD compliance reviewer for beast-plan. Ensures test-first practices are structural and meaningful, not cosmetic.
reviewer
Audits a completed pipeline task before commit — runs tests, enforces the cyclomatic-complexity ratchet on changed code, verifies plan delivery and contract compliance. Read-only on code; reports defects, never fixes them.
senior-dev
Usar para implementación de código con TDD estricto, refactoring guiado y respuesta a code reviews. Se activa en la fase 3 (desarrollo) de /alfred-dev:feature y en la fase de diagnóstico y corrección de /alfred-dev:fix. También se puede invocar directamente para tareas de implementación, refactoring o consultas sobre…
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
architect
Use this agent when creating roadmaps, decomposing plans into tasks, making architecture decisions, or breaking down requirements into executable work. Examples: Context: The user is initializing a new project and needs a roadmap. user: "Create a roadmap for building this application" assistant: "I'll dispatch the…