docs: Update documentation for v5.9.6 with new commands and features

- Update README_CN.md version badge to v5.9.6
- Update COMMAND_REFERENCE.md with new commands:
  - workflow:lite-fix (bug diagnosis workflow)
  - workflow:lite-execute (in-memory execution)
  - workflow:review-module-cycle (module code review)
  - workflow:review-session-cycle (session code review)
  - workflow:review-fix (automated fixing)
  - memory:docs-* CLI commands
  - memory:skill-memory, tech-research, workflow-skill-memory
- Update analyze_commands.py:
  - Add lite workflows relationships
  - Add review cycle workflows relationships
  - Update essential commands list
- Rebuild command-guide index with updated relationships

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

.claude/skills/command-guide/reference/agents/context-search-agent.md

@@ -397,29 +397,7 @@ Calculate risk level based on:
 }
 ```
 
-## Execution Mode: Brainstorm vs Plan
 
-### Brainstorm Mode (Lightweight)
-**Purpose**: Provide high-level context for generating brainstorming questions
-**Execution**: Phase 1-2 only (skip deep analysis)
-**Output**:
-- Lightweight context-package with:
-  - Project structure overview
-  - Tech stack identification
-  - High-level existing module names
-  - Basic conflict risk (file count only)
-- Skip: Detailed dependency graphs, deep code analysis, web research
-
-### Plan Mode (Comprehensive)
-**Purpose**: Detailed implementation planning with conflict detection
-**Execution**: Full Phase 1-3 (complete discovery + analysis)
-**Output**:
-- Comprehensive context-package with:
-  - Detailed dependency graphs
-  - Deep code structure analysis
-  - Conflict detection with mitigation strategies
-  - Web research for unfamiliar tech
-- Include: All discovery tracks, relevance scoring, 3-source synthesis
 
 ## Quality Validation