LDE(Law-Driven Engineering)の相互拘束(Mutual Constraint)を検証するエージェント。 Law↔Termの相互参照関係を検証し、孤立の検出と影響分析を行う。 使用タイミング: (1) PR作成前、(2) 「Link Mapをチェックして」「孤立を検出して」、 (3) Law/Term追加後の整合性確認、(4) 変更影響分析時
Detects orphaned Law/Term cards and analyzes change impacts in your LDE knowledge base. Use before PRs, after adding Law/Term cards, or when checking link integrity to maintain mutual constraints between laws and terms.
/plugin marketplace add CAPHTECH/claude-marketplace/plugin install caphtech-plugin@caphtech-marketplaceLDEの相互拘束(Mutual Constraint)を検証し、Law↔Termの整合性を維持する。
┌─────────────────────────────────────────────────────┐
│ 相互拘束(Mutual Constraint) │
├─────────────────────────────────────────────────────┤
│ Law → Term: すべてのLawはTermsを最低1つ参照 │
│ Term → Law: S0/S1 TermはRelated Lawsを最低1つ持つ │
└─────────────────────────────────────────────────────┘
docs/lde/link-map.md から Law→Term, Term→Law を取得
orphan_check:
type: orphan_law
law_id: LAW-xxx
issue: "Terms欄が空です"
action: "参照するTermを最低1つ追加してください"
orphan_check:
type: orphan_term
term_id: TERM-xxx
importance: S1
issue: "Related Lawsが空です"
action: "関連Lawを追加するか重要度を見直してください"
pattern_detection:
type: noun_inflation
indicator: "Termが5件以上追加されたがLawが0件"
recommendation: "追加したTermに関連するLawを検討してください"
pattern_detection:
type: relation_soup
indicator: "Lawが5件以上追加されたがTermが1件以下"
recommendation: "Lawが参照する語彙をTermカード化してください"
impact_analysis:
changed: TERM-inventory-available
change_type: definition | type | constraint
affected_laws:
- LAW-inv-available-balance
- LAW-pre-order-quantity
action_required:
- "各Lawの整合性を確認"
- "テストを更新"
impact_analysis:
changed: LAW-inv-available-balance
change_type: statement | constraint | exception
affected_terms:
- TERM-inventory-available
- TERM-inventory-total
action_required:
- "各Termの意味と整合性を確認"
- "境界検証ロジックを更新"
# Mutual Constraint Check Report
## Summary
- Total Laws: 25
- Total Terms: 18
- 孤立Law: 1件
- 孤立Term: 1件
## Status: WARN
### 孤立Law
- LAW-policy-discount: Terms欄が空
- Action: 参照するTermを追加
### 孤立Term
- TERM-customer-tier (S1): Related Lawsが空
- Action: 関連Lawを追加
### パターン検出
- 名辞インフレ: なし
- 関係スープ: なし
## 影響分析(変更があった場合)
- 変更: TERM-xxx
- 影響Law: LAW-a, LAW-b
- 推奨アクション: ...
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>