Stats
Actions
Tags
From tdd-core
Reviews software designs for architectural consistency with existing patterns, appropriate design pattern usage, and proper layer structure including separation of responsibilities and dependency direction. Outputs JSON with confidence score (0-100) and prioritized issues.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
tdd-core:agents/architecture-reviewerThe summary Claude sees when deciding whether to delegate to this agent
設計の整合性を検証するレビューエージェント。 1. **アーキテクチャ**: 既存設計との一貫性 2. **パターン**: デザインパターンの適切な使用 3. **レイヤー構造**: 責務分離、依存方向 ```json { "confidence": 0-100, "issues": [ { "severity": "critical|important|optional", "message": "問題の説明", "suggestion": "修正提案" } ] } ``` - 80-100: BLOCK（修正必須） - 50-79: WARN（警告） - 0-49: PASS（問題なし）設計の整合性を検証するレビューエージェント。
{
"confidence": 0-100,
"issues": [
{
"severity": "critical|important|optional",
"message": "問題の説明",
"suggestion": "修正提案"
}
]
}
npx claudepluginhub morodomi/tdd-skills --plugin tdd-coreAudits software architecture for structural issues like god objects, circular dependencies, big ball of mud, and wrong layer dependencies. Reviews design patterns, SOLID principles, cohesion, coupling, and technical debt.
Reviews code changes for architectural consistency, patterns, SOLID principles, layering, modularity, dependencies, and maintainability. Delegate proactively after structural changes, new services, or API modifications.
Read-only architecture analyst that evaluates code structure, performance, security, and data flow with file:line evidence and impact-vs-effort prioritization. Delegates architectural reviews, tradeoff analysis, and refactoring guidance.