feat: add implementation completeness assurance rules

docs/rules-en/ai-development-guide.md

@@ -210,4 +210,50 @@ npm run lint:fix      # Lint fixes
 
 - **Humility**: Perfect code doesn't exist, welcome feedback
 - **Courage**: Execute necessary refactoring boldly
-- **Transparency**: Clearly document technical decision reasoning
+- **Transparency**: Clearly document technical decision reasoning
+
+## Implementation Completeness Assurance
+
+### Required Procedure for Impact Analysis
+
+**Completion Criteria**: Complete all 3 stages
+
+#### 1. Discovery
+```bash
+Grep -n "TargetClass\|TargetMethod" -o content
+Grep -n "DependencyClass" -o content
+Grep -n "targetData\|SetData\|UpdateData" -o content
+```
+
+#### 2. Understanding
+**Mandatory**: Read all discovered files and include necessary parts in context:
+- Caller's purpose and context
+- Dependency direction
+- Data flow: generation → modification → reference
+
+#### 3. Identification
+Structured impact report (mandatory):
+```
+## Impact Analysis
+### Direct Impact: ClassA, ClassB (with reasons)
+### Indirect Impact: SystemX, PrefabY (with integration paths)
+### Processing Flow: Input → Process1 → Process2 → Output
+```
+
+**Important**: Do not stop at search; execute all 3 stages
+
+### Unused Code Deletion Rule
+
+When unused code is detected → Will it be used?
+- Yes → Implement immediately (no deferral allowed)
+- No → Delete immediately (remains in Git history)
+
+Target: Code, documentation, configuration files
+
+### Existing Code Deletion Decision Flow
+
+```
+In use? No → Delete immediately (remains in Git history)
+       Yes → Working? No → Delete + Reimplement
+                     Yes → Fix
+```

docs/rules-en/rules-index.yaml

@@ -50,8 +50,8 @@ rules:
 
   ai-development-guide:
     file: "ai-development-guide.md"
-    tags: [anti-patterns, technical-judgment, debugging, quality-commands, rule-of-three, implementation, type-safety, refactoring, code-reading, best-practices]
-    typical-use: "Technical decision criteria, anti-pattern detection, debugging techniques, quality check commands, implementation best practices"
+    tags: [anti-patterns, technical-judgment, debugging, quality-commands, rule-of-three, implementation, type-safety, refactoring, code-reading, best-practices, impact-analysis, unused-code, code-deletion]
+    typical-use: "Technical decision criteria, anti-pattern detection, debugging techniques, quality check commands, implementation best practices, impact analysis, unused code deletion"
     size: medium
     key-references:
       - "Rule of Three - Martin Fowler"
@@ -69,6 +69,7 @@ rules:
       - "Quality Check Command Reference"
       - "Situations Requiring Technical Decisions"
       - "Continuous Improvement Mindset"
+      - "Implementation Completeness Assurance"
 
   technical-spec:
     file: "technical-spec.md"

docs/rules-ja/ai-development-guide.md

@@ -211,4 +211,50 @@ npm run lint:fix      # Lint修正
 
 - **謙虚**: 完璧なコードは存在しない、フィードバック歓迎
 - **勇気**: 必要なリファクタリングは大胆に実行
-- **透明性**: 技術的な判断理由を明確に記録
+- **透明性**: 技術的な判断理由を明確に記録
+
+## 実装作業の完全性担保
+
+### 影響範囲調査の必須手順
+
+**完了定義**: 以下3段階すべての完了
+
+#### 1. 検索（Discovery）
+```bash
+Grep -n "TargetClass\|TargetMethod" -o content
+Grep -n "DependencyClass" -o content
+Grep -n "targetData\|SetData\|UpdateData" -o content
+```
+
+#### 2. 読解（Understanding）
+**必須**: 発見した全ファイルを読み込み、作業に必要な部分をコンテキストに含める：
+- 呼び出し元の目的と文脈
+- 依存関係の方向
+- データフロー: 生成→変更→参照
+
+#### 3. 特定（Identification）
+影響範囲の構造化報告（必須）：
+```
+## 影響範囲分析
+### 直接影響: ClassA、ClassB（理由明記）
+### 間接影響: SystemX、PrefabY（連携経路明記）
+### 処理フロー: 入力→処理1→処理2→出力
+```
+
+**重要**: 検索のみで完了とせず、3段階すべてを実行すること
+
+### 未使用コード削除ルール
+
+未使用コード検出時 → 使用予定？
+- Yes → 即実装（保留禁止）
+- No → 即削除（Git履歴に残る）
+
+対象: コード・ドキュメント・設定ファイル
+
+### 既存コード削除判断フロー
+
+```
+使用中？ No → 即削除（Git履歴に残る）
+      Yes → 動作？ No → 削除+再実装
+                  Yes → 修正
+```

docs/rules-ja/rules-index.yaml

@@ -50,8 +50,8 @@ rules:
 
   ai-development-guide:
     file: "ai-development-guide.md"
-    tags: [anti-patterns, technical-judgment, debugging, quality-commands, rule-of-three, implementation, type-safety, refactoring, code-reading, best-practices]
-    typical-use: "技術的判断基準、アンチパターン検出、デバッグ手法、品質チェックコマンド、実装時のベストプラクティス"
+    tags: [anti-patterns, technical-judgment, debugging, quality-commands, rule-of-three, implementation, type-safety, refactoring, code-reading, best-practices, impact-analysis, unused-code, code-deletion]
+    typical-use: "技術的判断基準、アンチパターン検出、デバッグ手法、品質チェックコマンド、実装時のベストプラクティス、影響範囲調査、未使用コード削除"
     size: medium
     key-references:
       - "Rule of Three - Martin Fowler"
@@ -69,6 +69,7 @@ rules:
       - "品質チェックコマンドリファレンス"
       - "技術的判断が必要な場面"
       - "継続的改善のマインドセット"
+      - "実装作業の完全性担保"
 
   technical-spec:
     file: "technical-spec.md"

package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-coding-project-boilerplate",
-  "version": "1.7.15",
+  "version": "1.7.16",
   "description": "TypeScript project boilerplate optimized for Claude Code development with comprehensive development rules, architecture patterns, and quality assurance tools",
   "main": "dist/index.js",
   "keywords": [