refactor: remove MCP code-index dependency, replace with ripgrep/find

Replace all mcp__code-index__ calls with native ripgrep and find commands
across workflow and command files for better performance and portability.

Changes:
- Remove 41 mcp__code-index__ function calls from 12 files
- Replace with ripgrep (rg) for content search
- Replace with find for file discovery
- Remove index refresh dependencies (no longer needed)

Modified files:
- workflow/tools: context-gather, test-context-gather, task-generate-agent,
  task-generate, test-task-generate (core workflow tools)
- workflow: review (security scanning)
- memory: load, update-related, docs (memory management)
- cli/mode: plan, bug-index, code-analysis (CLI modes)

Documentation updates:
- Simplify mcp-tool-strategy.md to only Exa usage (5 lines)
- Streamline context-search-strategy.md to 69 lines
- Standardize codebase-retrieval syntax per intelligent-tools-strategy.md

Benefits:
- Faster search with ripgrep (no index overhead)
- Better cross-platform compatibility
- Simpler configuration (fewer MCP dependencies)
- -232 lines of code removed

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

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

.claude/commands/cli/mode/bug-index.md

@@ -138,7 +138,7 @@ RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: token validation fail
 ```bash
 # 1. Find bug-related files
 rg "error_keyword" --files-with-matches
-mcp__code-index__search_code_advanced(pattern="error|exception", file_pattern="*.ts")
+rg "error|exception" -g "*.ts"
 
 # 2. Execute bug analysis with focused context (analysis only, no code changes)
 /cli:mode:bug-index --cd "src/module" "specific error description"

.claude/commands/cli/mode/code-analysis.md

@@ -141,7 +141,7 @@ RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on security
 ```bash
 # 1. Find entry points and related files
 rg "function.*authenticate|class.*AuthService" --files-with-matches
-mcp__code-index__search_code_advanced(pattern="authenticate|login", file_pattern="*.ts")
+rg "authenticate|login" -g "*.ts"
 
 # 2. Build call graph understanding
 # entry → middleware → service → repository

.claude/commands/cli/mode/plan.md

@@ -139,7 +139,7 @@ RULES: $(cat ~/.claude/prompt-templates/plan.md) | Maintain backward compatibili
 ```bash
 # 1. Discover project structure
 ~/.claude/scripts/get_modules_by_depth.sh
-mcp__code-index__find_files(pattern="*.ts")
+find . -name "*.ts" -type f
 
 # 2. Gather existing architecture info
 rg "architecture|design" --files-with-matches

.claude/commands/memory/docs.md

@@ -658,7 +658,7 @@ bash(
     "pre_analysis": [
       {
         "step": "discover_api_endpoints",
-        "command": "mcp__code-index__search_code_advanced(pattern='router\\.|@(Get|Post)', file_pattern='*.{ts,js}')",
+        "command": "bash(rg 'router\\.| @(Get|Post)' -g '*.{ts,js}')",
         "output_to": "endpoint_discovery"
       },
       {

.claude/commands/memory/load.md

@@ -121,14 +121,14 @@ Task(
 ### Step 2: Keyword Extraction & File Discovery
 
 1. Extract core keywords from task description
-2. Discover relevant files using MCP code-index or rg:
+2. Discover relevant files using ripgrep and find:
-   \`\`\`javascript
+   \`\`\`bash
-   // Prefer MCP tools
+   # Find files by name
-   mcp__code-index__find_files(pattern="*{keyword}*")
+   find . -name "*{keyword}*" -type f
-   mcp__code-index__search_code_advanced(pattern="{keyword}", context_lines=2)
 
-   // Fallback: use rg
+   # Search content with ripgrep
-   bash(rg -l "{keyword}" --type ts --type md)
+   rg "{keyword}" --type ts --type md -C 2
+   rg -l "{keyword}" --type ts --type md  # List files only
    \`\`\`
 
 ### Step 3: Deep Analysis via CLI

.claude/commands/memory/update-related.md

@@ -40,10 +40,7 @@ Orchestrates context-aware CLAUDE.md updates for changed modules using batched a
 ## Phase 1: Change Detection & Analysis
 
 ```bash
-# Refresh code index
+# Detect changed modules (no index refresh needed)
-bash(mcp__code-index__refresh_index)
-
-# Detect changed modules
 bash(~/.claude/scripts/detect_changed_modules.sh list)
 
 # Cache git changes

.claude/commands/workflow/review.md

@@ -92,10 +92,10 @@ After bash validation, the model takes control to:
 2. **Perform Specialized Review**: Based on `review_type`
 
    **Security Review** (`--type=security`):
-   - Use MCP code search for security patterns:
+   - Use ripgrep for security patterns:
      ```bash
-     mcp__code-index__search_code_advanced(pattern="password|token|secret|auth", file_pattern="*.{ts,js,py}")
+     rg "password|token|secret|auth" -g "*.{ts,js,py}"
-     mcp__code-index__search_code_advanced(pattern="eval|exec|innerHTML|dangerouslySetInnerHTML", file_pattern="*.{ts,js,tsx}")
+     rg "eval|exec|innerHTML|dangerouslySetInnerHTML" -g "*.{ts,js,tsx}"
      ```
    - Use Gemini for security analysis:
      ```bash

.claude/commands/workflow/tools/context-gather.md

@@ -17,7 +17,7 @@ Agent-driven intelligent context collector that gathers relevant information fro
 - **Agent-Driven**: Delegate execution to universal-executor agent for autonomous operation
 - **Two-Phase Flow**: Discovery (context loading) → Execution (context gathering and packaging)
 - **Memory-First**: Reuse loaded documents from conversation memory
-- **MCP-Enhanced**: Use MCP tools for advanced code analysis and file discovery
+- **Ripgrep-Enhanced**: Use ripgrep and native tools for code analysis and file discovery
 - **Intelligent Collection**: Auto-identify relevant resources based on keyword analysis
 - **Comprehensive Coverage**: Collect code, documentation, configurations, and dependencies
 - **Standardized Output**: Generate unified format context-package.json
@@ -36,9 +36,10 @@ Agent-driven intelligent context collector that gathers relevant information fro
     // If in memory: use cached content
     // Else: Load from .workflow/{session-id}/workflow-session.json
   },
-  "mcp_capabilities": {
+  "search_tools": {
-    // Agent will use these tools to discover project context
+    // Agent will use these native tools to discover project context
-    "code_index": true,
+    "ripgrep": true,
+    "find": true,
     "exa_code": true,
     "exa_web": true
   }
@@ -76,8 +77,9 @@ Task(
 ### Session Metadata
 {session_metadata_content}
 
-### MCP Capabilities
+### Search Tools
-- code-index: Available for file discovery and code search
+- ripgrep: Available for content search and pattern matching
+- find: Available for file discovery
 - exa-code: Available for external research
 - exa-web: Available for web search
 
@@ -87,7 +89,7 @@ Task(
 1. **Project Structure Analysis**: Execute get_modules_by_depth.sh for architecture overview
 2. **Documentation Loading**: Load CLAUDE.md, README.md and relevant documentation
 3. **Keyword Extraction**: Extract core keywords from task description
-4. **Smart File Discovery**: Use MCP code-index tools to locate relevant files
+4. **Smart File Discovery**: Use ripgrep and find to locate relevant files
 5. **Code Structure Analysis**: Analyze project structure to identify relevant modules
 6. **Dependency Discovery**: Identify tech stack and dependency relationships
 7. **Context Packaging**: Generate standardized JSON context package
@@ -120,22 +122,18 @@ Task(
    - Identify potentially involved modules and components
    - Set file type filters
 
-#### Step 2: MCP-Enhanced File Discovery
+#### Step 2: File Discovery with Native Tools
 1. **Code File Location**
-   Use MCP code-index tools:
+   Use ripgrep and find commands:
-   \`\`\`javascript
+   \`\`\`bash
-   // Find files by pattern
+   # Find files by pattern
-   mcp__code-index__find_files(pattern="*{keyword}*")
+   find . -name "*{keyword}*" -type f
 
-   // Search code content
+   # Search code content with ripgrep
-   mcp__code-index__search_code_advanced(
+   rg "{keyword_patterns}" --type-add 'custom:*.{ts,js,py,go,md}' -t custom -C 3
-     pattern="{keyword_patterns}",
-     file_pattern="*.{ts,js,py,go,md}",
-     context_lines=3
-   )
 
-   // Get file summaries
+   # Get file summaries (find function/class definitions)
-   mcp__code-index__get_file_summary(file_path="relevant/file.ts")
+   rg "^(class|function|export|def|interface)" relevant/file.ts
    \`\`\`
 
 2. **Configuration Files Discovery**
@@ -321,34 +319,27 @@ Before completion, verify:
 - File count limit: Maximum 50 files per type
 - Size filtering: Skip oversized files (>10MB)
 - Depth limit: Maximum search depth of 3 levels
-- Use MCP tools for efficient discovery
+- Use ripgrep for efficient discovery
 
-**MCP Tools Integration**:
+**Native Tools Integration**:
-Agent should use MCP code-index tools when available:
+Agent should use ripgrep and find commands:
-\`\`\`javascript
+\`\`\`bash
-// Set project path
+# Find files by pattern
-mcp__code-index__set_project_path(path="{current_project_path}")
+find . -name "*{keyword}*" -type f
 
-// Refresh index
+# Search code content with ripgrep
-mcp__code-index__refresh_index()
+rg "{keyword_patterns}" --type ts --type js --type py --type go --type md -C 3
 
-// Find files by pattern
+# Alternative: use glob patterns
-mcp__code-index__find_files(pattern="*{keyword}*")
+rg "{keyword_patterns}" -g "*.{ts,js,py,go,md}" -C 3
 
-// Search code content
+# Count matches
-mcp__code-index__search_code_advanced(
+rg "{keyword_patterns}" -c
-  pattern="{keyword_patterns}",
+
-  file_pattern="*.{ts,js,py,go,md}",
+# List files with matches
-  context_lines=3
+rg "{keyword_patterns}" --files-with-matches
-)
 \`\`\`
 
-**Fallback Strategy**:
-When MCP tools unavailable, agent should use traditional commands:
-- \`find\` for file discovery
-- \`rg\` or \`grep\` for content search
-- Bash commands from project structure analysis
-
 ## Output
 
 Generate context-package.json and report completion:
@@ -391,9 +382,10 @@ const agentContext = {
     ? memory.get("workflow-session.json")
     : Read(.workflow/WFS-[id]/workflow-session.json),
 
-  // MCP capabilities - agent will use these tools
+  // Search tools - agent will use these native tools
-  mcp_capabilities: {
+  search_tools: {
-    code_index: true,
+    ripgrep: true,
+    find: true,
     exa_code: true,
     exa_web: true
   }

.claude/commands/workflow/tools/task-generate-agent.md

@@ -93,14 +93,11 @@ Autonomous task JSON and IMPL_PLAN.md generation using action-planning-agent wit
    }
    ```
 
-5. **MCP Code Analysis** (optional - enhance understanding)
+5. **Code Analysis with Native Tools** (optional - enhance understanding)
-   ```javascript
+   ```bash
-   // Find relevant files for task context
+   # Find relevant files for task context
-   mcp__code-index__find_files(pattern="*auth*")
+   find . -name "*auth*" -type f
-   mcp__code-index__search_code_advanced(
+   rg "authentication|oauth" -g "*.ts"
-     pattern="authentication|oauth",
-     file_pattern="*.ts"
-   )
    ```
 
 6. **MCP External Research** (optional - gather best practices)
@@ -274,18 +271,13 @@ $(cat ~/.claude/workflows/cli-templates/prompts/workflow/impl-plan-template.txt)
 **Code Index Usage**:
 \`\`\`javascript
 // Discover authentication-related files
-mcp__code-index__find_files(pattern="*auth*")
+bash(find . -name "*auth*" -type f)
 
 // Search for OAuth patterns
-mcp__code-index__search_code_advanced(
+bash(rg "oauth|jwt|authentication" -g "*.{ts,js}")
-  pattern="oauth|jwt|authentication",
-  file_pattern="*.{ts,js}"
-)
 
 // Get file summary for key components
-mcp__code-index__get_file_summary(
+bash(rg "^(class|function|export|interface)" src/auth/index.ts)
-  file_path="src/auth/index.ts"
-)
 \`\`\`
 
 **Exa Research Usage**:

.claude/commands/workflow/tools/task-generate.md

@@ -249,9 +249,9 @@ This enhanced 5-field schema embeds all necessary context, artifacts, and execut
         }
       },
       {
-        "step": "mcp_codebase_exploration",
+        "step": "codebase_exploration",
-        "action": "Explore codebase using MCP tools",
+        "action": "Explore codebase using native tools",
-        "command": "mcp__code-index__find_files(pattern=\"[patterns]\") && mcp__code-index__search_code_advanced(pattern=\"[patterns]\")",
+        "command": "bash(find . -name \"[patterns]\" -type f && rg \"[patterns]\")",
         "output_to": "codebase_structure"
       },
       {

.claude/commands/workflow/tools/test-context-gather.md

@@ -17,11 +17,11 @@ Specialized context collector for test generation workflows that analyzes test c
 - **Gap Identification**: Locate implementation files without corresponding tests
 - **Source Context Loading**: Import implementation summaries from source session
 - **Framework Detection**: Auto-detect test framework and patterns
-- **MCP-Powered**: Leverage code-index tools for precise analysis
+- **Ripgrep-Powered**: Leverage ripgrep and native tools for precise analysis
 
 ## Core Responsibilities
 - Load source session implementation context
-- Analyze current test coverage using MCP tools
+- Analyze current test coverage using ripgrep
 - Identify files requiring test generation
 - Detect test framework and conventions
 - Package test context for analysis phase
@@ -41,21 +41,17 @@ Specialized context collector for test generation workflows that analyzes test c
    - Extract changed files and implementation scope
    - Identify implementation patterns and tech stack
 
-### Phase 2: Test Coverage Analysis (MCP Tools)
+### Phase 2: Test Coverage Analysis (Ripgrep)
 
 1. **Existing Test Discovery**
    ```bash
    # Find all test files
-   mcp__code-index__find_files(pattern="*.test.*")
+   find . -name "*.test.*" -type f
-   mcp__code-index__find_files(pattern="*.spec.*")
+   find . -name "*.spec.*" -type f
-   mcp__code-index__find_files(pattern="*test_*.py")
+   find . -name "*test_*.py" -type f
 
    # Search for test patterns
-   mcp__code-index__search_code_advanced(
+   rg "describe|it|test|@Test" -g "*.test.*"
-     pattern="describe|it|test|@Test",
-     file_pattern="*.test.*",
-     context_lines=0
-   )
    ```
 
 2. **Coverage Gap Analysis**
@@ -80,18 +76,10 @@ Specialized context collector for test generation workflows that analyzes test c
 1. **Framework Identification**
    ```bash
    # Check package.json or requirements.txt
-   mcp__code-index__search_code_advanced(
+   rg "jest|mocha|jasmine|pytest|unittest|rspec" -g "package.json" -g "requirements.txt" -g "Gemfile" -C 2
-     pattern="jest|mocha|jasmine|pytest|unittest|rspec",
-     file_pattern="package.json|requirements.txt|Gemfile",
-     context_lines=2
-   )
 
    # Analyze existing test patterns
-   mcp__code-index__search_code_advanced(
+   rg "describe\(|it\(|test\(|def test_" -g "*.test.*" -C 3
-     pattern="describe\\(|it\\(|test\\(|def test_",
-     file_pattern="*.test.*",
-     context_lines=3
-   )
    ```
 
 2. **Convention Analysis**
@@ -207,33 +195,26 @@ Generate `test-context-package.json`:
 .workflow/{test_session_id}/.process/test-context-package.json
 ```
 
-## MCP Tools Usage
+## Native Tools Usage
 
 ### File Discovery
 ```bash
 # Test files
-mcp__code-index__find_files(pattern="*.test.*")
+find . -name "*.test.*" -type f
-mcp__code-index__find_files(pattern="*.spec.*")
+find . -name "*.spec.*" -type f
 
 # Implementation files
-mcp__code-index__find_files(pattern="*.ts")
+find . -name "*.ts" -type f
-mcp__code-index__find_files(pattern="*.js")
+find . -name "*.js" -type f
 ```
 
 ### Content Search
 ```bash
 # Test framework detection
-mcp__code-index__search_code_advanced(
+rg "jest|mocha|pytest" -g "package.json" -g "requirements.txt"
-  pattern="jest|mocha|pytest",
-  file_pattern="package.json|requirements.txt"
-)
 
 # Test pattern analysis
-mcp__code-index__search_code_advanced(
+rg "describe|it|test" -g "*.test.*" -C 2
-  pattern="describe|it|test",
-  file_pattern="*.test.*",
-  context_lines=2
-)
 ```
 
 ### Coverage Analysis
@@ -249,7 +230,7 @@ test_file_patterns=(
 
 # Search for test file
 for pattern in "${test_file_patterns[@]}"; do
-  if mcp__code-index__find_files(pattern="$pattern") | grep -q .; then
+  if [ -f "$pattern" ]; then
     echo "✅ Test exists: $pattern"
     break
   fi
@@ -262,10 +243,9 @@ done
 |-------|-------|------------|
 | Source session not found | Invalid source_session reference | Verify test session metadata |
 | No implementation summaries | Source session incomplete | Complete source session first |
-| MCP tools unavailable | MCP not configured | Fallback to bash find/grep |
 | No test framework detected | Missing test dependencies | Request user to specify framework |
 
-## Fallback Strategy (No MCP)
+## Native Tools Implementation
 
 ```bash
 # File discovery
@@ -287,8 +267,8 @@ done
 - `/workflow:test-gen` (Phase 3: Context Gathering)
 
 ### Calls
-- MCP code-index tools for analysis
+- Ripgrep and find for file analysis
-- Bash file operations for fallback
+- Bash file operations for coverage analysis
 
 ### Followed By
 - `/workflow:tools:test-concept-enhanced` - Analyzes context and plans test generation
@@ -296,7 +276,7 @@ done
 ## Success Criteria
 
 - ✅ Source session context loaded successfully
-- ✅ Test coverage gaps identified with MCP tools
+- ✅ Test coverage gaps identified with ripgrep
 - ✅ Test framework detected and documented
 - ✅ Valid test-context-package.json generated
 - ✅ All missing tests catalogued with priority

.claude/commands/workflow/tools/test-task-generate.md

@@ -146,9 +146,9 @@ Generate **TWO task JSON files**:
         "step": "load_existing_test_patterns",
         "action": "Study existing tests for pattern reference",
         "commands": [
-          "mcp__code-index__find_files(pattern=\"*.test.*\")",
+          "bash(find . -name \"*.test.*\" -type f)",
           "bash(# Read first 2 existing test files as examples)",
-          "bash(test_files=$(mcp__code-index__find_files(pattern=\"*.test.*\") | head -2))",
+          "bash(test_files=$(find . -name \"*.test.*\" -type f | head -2))",
           "bash(for f in $test_files; do echo \"=== $f ===\"&& cat \"$f\"; done)"
         ],
         "output_to": "existing_test_patterns",
@@ -282,11 +282,11 @@ Generate **TWO task JSON files**:
         "step": "analyze_test_coverage",
         "action": "Analyze test coverage and identify missing tests",
         "commands": [
-          "mcp__code-index__find_files(pattern=\"*.test.*\")",
+          "bash(find . -name \"*.test.*\" -type f)",
-          "mcp__code-index__search_code_advanced(pattern=\"test|describe|it|def test_\", file_pattern=\"*.test.*\")",
+          "bash(rg \"test|describe|it|def test_\" -g \"*.test.*\")",
           "bash(# Count implementation files vs test files)",
           "bash(impl_count=$(find [changed_files_dirs] -type f \\( -name '*.ts' -o -name '*.js' -o -name '*.py' \\) ! -name '*.test.*' 2>/dev/null | wc -l))",
-          "bash(test_count=$(mcp__code-index__find_files(pattern=\"*.test.*\") | wc -l))",
+          "bash(test_count=$(find . -name \"*.test.*\" -type f | wc -l))",
           "bash(echo \"Implementation files: $impl_count, Test files: $test_count\")"
         ],
         "output_to": "test_coverage_analysis",

.claude/workflows/context-search-strategy.md

@@ -8,89 +8,61 @@ type: search-guideline
 
 ## ⚡ Execution Environment
 
-**CRITICAL**: All commands execute in **Bash environment** (Git Bash on Windows, Bash on Linux/macOS)
+**CRITICAL**: All commands execute in **Bash environment** (Git Bash on Windows)
 
-**❌ Forbidden**: Windows-specific commands (`findstr`, `dir`, `where`, `type`, `copy`, `del`) - Use Bash equivalents (`grep`, `find`, `which`, `cat`, `cp`, `rm`)
+**❌ Forbidden**: Windows commands (`findstr`, `dir`, `where`) - Use Bash (`grep`, `find`, `cat`)
 
 ## ⚡ Core Search Tools
 
 **codebase-retrieval**: Semantic file discovery via Gemini CLI with all files analysis
 **rg (ripgrep)**: Fast content search with regex support
 **find**: File/directory location by name patterns
-**grep**: Built-in pattern matching in files
+**grep**: Built-in pattern matching (fallback when rg unavailable)
-**get_modules_by_depth.sh**: Program architecture analysis and structural discovery
+**get_modules_by_depth.sh**: Program architecture analysis (MANDATORY before planning)
 
-### Decision Principles
+## 📋 Tool Selection Matrix
-- **Use codebase-retrieval for semantic discovery** - Intelligent file discovery based on task context
-- **Use rg for content** - Fastest for searching within files
-- **Use find for files** - Locate files/directories by name
-- **Use grep sparingly** - Only when rg unavailable
-- **Use get_modules_by_depth.sh first** - MANDATORY for program architecture analysis before planning
-- **Always use Bash commands** - NEVER use Windows cmd/PowerShell commands
-
-### Tool Selection Matrix
 
 | Need | Tool | Use Case |
 |------|------|----------|
-| **Semantic file discovery** | codebase-retrieval | Find files relevant to task/feature context |
+| **Semantic discovery** | codebase-retrieval | Find files relevant to task/feature context |
 | **Pattern matching** | rg | Search code content with regex |
 | **File name lookup** | find | Locate files by name patterns |
-| **Architecture analysis** | get_modules_by_depth.sh | Understand program structure |
+| **Architecture** | get_modules_by_depth.sh | Understand program structure |
+
+## 🔧 Quick Command Reference
 
-### Quick Command Reference
 ```bash
 # Semantic File Discovery (codebase-retrieval)
-gemini "CONTEXT: @**/* List all files relevant to: [task/feature description]"
+cd [directory] && gemini -p "
-bash(gemini "CONTEXT: @**/* List all files relevant to: [task/feature description]")
+PURPOSE: Discover files relevant to task/feature
+TASK: List all files related to [task/feature description]
+MODE: analysis
+CONTEXT: @**/*
+EXPECTED: Relevant file paths with relevance explanation
+RULES: Focus on direct relevance to task requirements
+"
 
-# Program Architecture Analysis (MANDATORY FIRST)
+# Program Architecture (MANDATORY FIRST)
-~/.claude/scripts/get_modules_by_depth.sh  # Discover program architecture
+~/.claude/scripts/get_modules_by_depth.sh
-bash(~/.claude/scripts/get_modules_by_depth.sh)  # Analyze structural hierarchy
 
 # Content Search (rg preferred)
-rg "pattern" --type js          # Search in JS files
+rg "pattern" --type js -n        # Search JS files with line numbers
-rg -i "case-insensitive"        # Ignore case
+rg -i "case-insensitive"         # Ignore case
-rg -n "show-line-numbers"       # Show line numbers
+rg -C 3 "context"                # Show 3 lines before/after
-rg -A 3 -B 3 "context-lines"    # Show 3 lines before/after
 
-# File Search (find)
+# File Search
-find . -name "*.ts" -type f     # Find TypeScript files
+find . -name "*.ts" -type f      # Find TypeScript files
 find . -path "*/node_modules" -prune -o -name "*.js" -print
 
-# Built-in alternatives
+# Workflow Examples
-grep -r "pattern" .             # Recursive search (slower)
+rg "IMPL-\d+" .workflow/ --type json                    # Find task IDs
-grep -n -i "pattern" file.txt   # Line numbers, case-insensitive
+find .workflow/ -name "*.json" -path "*/.task/*"        # Locate task files
+rg "status.*pending" .workflow/.task/                   # Find pending tasks
 ```
 
-### Workflow Integration Examples
+## ⚡ Performance Tips
-```bash
-# Semantic Discovery → Content Search → Analysis (Recommended Pattern)
-gemini "CONTEXT: @**/* List all files relevant to: [task/feature]"  # Get relevant files
-rg "[pattern]" --type [filetype]  # Then search within discovered files
 
-# Program Architecture Analysis (MANDATORY BEFORE PLANNING)
-~/.claude/scripts/get_modules_by_depth.sh  # Discover program architecture
-bash(~/.claude/scripts/get_modules_by_depth.sh)  # Analyze structural hierarchy
-
-# Search for task definitions
-rg "IMPL-\d+" .workflow/ --type json        # Find task IDs
-find .workflow/ -name "*.json" -path "*/.task/*"  # Locate task files
-
-# Analyze workflow structure
-rg "status.*pending" .workflow/.task/      # Find pending tasks
-rg "depends_on" .workflow/.task/ -A 2      # Show dependencies
-
-# Find workflow sessions
-find .workflow/ -name ".active-*"          # Active sessions
-rg "WFS-" .workflow/ --type json           # Session references
-
-# Content analysis for planning
-rg "flow_control" .workflow/ -B 2 -A 5     # Flow control patterns
-find . -name "IMPL_PLAN.md" -exec grep -l "requirements" {} \;
-```
-
-### Performance Tips
 - **rg > grep** for content search
 - **Use --type filters** to limit file types
-- **Exclude common dirs**: `--glob '!node_modules'`
+- **Exclude dirs**: `--glob '!node_modules'`
-- **Use -F for literal** strings (no regex)
+- **Use -F** for literal strings (no regex)

.claude/workflows/mcp-tool-strategy.md

@@ -1,176 +1,11 @@
-# MCP Tool Strategy: Triggers & Workflows
+# MCP Tool Strategy: Exa Usage
 
-## ⚡ Triggering Mechanisms
+## ⚡ Exa Triggering Mechanisms
 
-**Auto-Trigger Scenarios**:
+**Auto-Trigger**:
 - User mentions "exa-code" or code-related queries → `mcp__exa__get_code_context_exa`
 - Need current web information → `mcp__exa__web_search_exa`
-- Finding code patterns/files → `mcp__code-index__search_code_advanced`
-- Locating specific files → `mcp__code-index__find_files`
 
-**Manual Trigger Rules**:
+**Manual Trigger**:
 - Complex API research → Exa Code Context
-- Architecture pattern discovery → Exa Code Context + Gemini analysis
 - Real-time information needs → Exa Web Search
-- Codebase exploration → Code Index tools first, then Gemini analysis
-
-## 🎯 Available MCP Tools
-
-### Exa Code Context (mcp__exa__get_code_context_exa)
-**Purpose**: Search and get relevant context for programming tasks
-**Strengths**: Highest quality context for libraries, SDKs, and APIs
-**Best For**: Code examples, API patterns, learning frameworks
-
-**Usage**:
-```bash
-mcp__exa__get_code_context_exa(
-  query="React useState hook examples",
-  tokensNum="dynamic"  # or 1000-50000
-)
-```
-
-**Examples**: "React useState", "Python pandas filtering", "Express.js middleware"
-
-### Exa Web Search (mcp__exa__web_search_exa)
-**Purpose**: Real-time web searches with content scraping
-**Best For**: Current information, research, recent solutions
-
-**Usage**:
-```bash
-mcp__exa__web_search_exa(
-  query="latest React 18 features",
-  numResults=5  # default: 5
-)
-```
-
-
-### Code Index Tools (mcp__code-index__)
-**核心方法**: `search_code_advanced`, `find_files`, `refresh_index`
-
-**核心搜索**:
-```bash
-mcp__code-index__search_code_advanced(pattern="function.*auth", file_pattern="*.ts")
-mcp__code-index__find_files(pattern="*.test.js")
-mcp__code-index__refresh_index()  # git操作后刷新
-```
-
-**实用场景**:
-- **查找代码**: `search_code_advanced(pattern="old.*API")`
-- **定位文件**: `find_files(pattern="src/**/*.tsx")`
-- **更新索引**: `refresh_index()` (git操作后)
-
-**文件搜索测试结果**:
-- ✅ `find_files(pattern="*.md")` - 搜索所有 Markdown 文件
-- ✅ `find_files(pattern="*complete*")` - 通配符匹配文件名
-- ❌ `find_files(pattern="complete.md")` - 精确匹配可能失败
-- 📝 建议使用通配符模式获得更好的搜索结果
-
-## 📊 Tool Selection Matrix
-
-| Task | MCP Tool | Use Case | Integration |
-|------|----------|----------|-------------|
-| **Code Context** | Exa Code | API examples, patterns | → Gemini analysis |
-| **Research** | Exa Web | Current info, trends | → Planning phase |
-| **Code Search** | Code Index | Pattern discovery, file location | → Gemini analysis |
-| **Navigation** | Code Index | File exploration, structure | → Architecture phase |
-
-## 🚀 Integration Patterns
-
-### Standard Workflow
-```bash
-# 1. Explore codebase structure
-mcp__code-index__find_files(pattern="*async*")
-mcp__code-index__search_code_advanced(pattern="async.*function", file_pattern="*.ts")
-
-# 2. Get external context
-mcp__exa__get_code_context_exa(query="TypeScript async patterns", tokensNum="dynamic")
-
-# 3. Analyze with Gemini
-cd "src/async" && gemini "
-PURPOSE: Understand async patterns
-CONTEXT: Code index results + Exa context + @src/async/**/*
-EXPECTED: Pattern analysis
-RULES: Focus on TypeScript best practices
-"
-
-# 4. Implement with Codex
-codex -C src/async --full-auto exec "Apply modern async patterns" -s danger-full-access
-```
-
-### Enhanced Planning
-1. **Explore codebase** with Code Index tools
-2. **Research** with Exa Web Search
-3. **Get code context** with Exa Code Context
-4. **Analyze** with Gemini
-5. **Architect** with Qwen
-6. **Implement** with Codex
-
-## 🔧 Best Practices
-
-### Code Index
-- **Search first** - Use before external tools for codebase exploration
-- **Refresh after git ops** - Keep index synchronized
-- **Pattern specificity** - Use precise regex patterns for better results
-- **File patterns** - Combine with glob patterns for targeted search
-- **Glob pattern matching** - Use `*.md`, `*complete*` patterns for file discovery
-- **Exact vs wildcard** - Exact names may fail, use wildcards for better results
-
-### Exa Code Context
-- **Use "dynamic" tokens** for efficiency
-- **Be specific** - include technology stack
-- **MANDATORY** when user mentions exa-code or code queries
-
-### Exa Web Search
-- **Default 5 results** usually sufficient
-- **Use for current info** - supplement knowledge cutoff
-
-
-
-## 🎯 Common Scenarios
-
-### Learning New Technology
-```bash
-# Explore existing patterns + get examples + research + analyze
-mcp__code-index__search_code_advanced(pattern="router|routing", file_pattern="*.ts")
-mcp__exa__get_code_context_exa(query="Next.js 14 app router", tokensNum="dynamic")
-mcp__exa__web_search_exa(query="Next.js 14 best practices 2024", numResults=3)
-cd "src/app" && gemini "Learn Next.js patterns"
-```
-
-### Debugging
-```bash
-# Find similar patterns + solutions + fix
-mcp__code-index__search_code_advanced(pattern="similar.*error", file_pattern="*.ts")
-mcp__exa__get_code_context_exa(query="TypeScript generic constraints", tokensNum="dynamic")
-codex --full-auto exec "Fix TypeScript issues" -s danger-full-access
-```
-
-### Codebase Exploration
-```bash
-# Comprehensive codebase understanding workflow
-mcp__code-index__set_project_path(path="/current/project")  # 设置项目路径
-mcp__code-index__refresh_index()  # 刷新索引
-mcp__code-index__find_files(pattern="*auth*")  # Find auth-related files
-mcp__code-index__search_code_advanced(pattern="function.*auth", file_pattern="*.ts")  # Find auth functions
-mcp__code-index__get_file_summary(file_path="src/auth/index.ts")  # Understand structure
-cd "src/auth" && gemini "Analyze auth architecture"
-```
-
-### Project Setup Workflow
-```bash
-# 新项目初始化流程
-mcp__code-index__set_project_path(path="/path/to/new/project")
-mcp__code-index__get_settings_info()  # 确认设置
-mcp__code-index__refresh_index()  # 建立索引
-mcp__code-index__configure_file_watcher(enabled=true)  # 启用文件监控
-mcp__code-index__get_file_watcher_status()  # 确认监控状态
-```
-
-## ⚡ Performance Tips
-
-- **Code Index first** → explore codebase before external tools
-- **Use "dynamic" tokens** for Exa Code Context
-- **MCP first** → gather context before analysis
-- **Focus queries** - avoid overly broad searches
-- **Integrate selectively** - use relevant context only
-- **Refresh index** after major git operations