refactor: remove subagent references and update CLI tool usage across documentation

docs/agents/builtin.md

@@ -396,10 +396,10 @@ Task({
 
 **Capabilities**:
 - Orchestrates parallel CLAUDE.md updates
-- Uses ccw tool exec update_module_claude
+- Uses MCP tools directly for module documentation
 - Processes every module path
 
-**Tools**: `Bash`, `ccw tool exec`, `TodoWrite`
+**Tools**: `Bash`, `mcp__ccw-tools__*`, `TodoWrite`
 
 ```javascript
 Task({
@@ -511,7 +511,7 @@ Specialized agents use: `mcp__ace-tool__search_context`, `mcp__ccw-tools__smart_
 
 ### CLI Tools
 
-CLI-capable agents use: `ccw cli`, `ccw tool exec`
+CLI-capable agents use: `ccw cli`, MCP tools directly
 
 ### Workflow Tools
 

docs/features/codexlens.md

@@ -41,21 +41,17 @@
 
 ## Usage
 
-### Indexing Project
+### Via MCP Tool (Recommended)
 
-```bash
-ccw index
-ccw index --watch  # Continuous indexing
+```typescript
+// ACE semantic search
+mcp__ace-tool__search_context({
+  project_root_path: "/path/to/project",
+  query: "authentication logic"
+})
 ```
 
-### Searching
-
-```bash
-ccw search "authentication logic"
-ccw search "where is user validation" --top 10
-```
-
-### Via MCP Tool
+> **Note**: The CLI commands `ccw index` and `ccw search` are deprecated. Use MCP tools directly for semantic search.
 
 ```typescript
 // ACE semantic search

docs/guide/ch01-what-is-claude-dms3.md

@@ -37,13 +37,13 @@
 
 | Concept | Description | Location/Command |
 |---------|-------------|------------------|
-| **CodexLens** | Semantic code indexing and search engine | `ccw search` |
+| **CodexLens** | Semantic code indexing and search engine | `mcp__ace-tool__search_context(project_root_path="...", query="...")` |
 | **CCW** | Unified CLI tool invocation framework | `ccw cli` |
-| **Memory** | Cross-session knowledge persistence | `ccw memory` |
+| **Memory** | Cross-session knowledge persistence | `mcp__ccw-tools__core_memory(operation="list")` |
 | **Spec** | Project specification and constraint system | `.workflow/specs/` |
 | **Hook** | Auto-triggered context injection scripts | `.claude/hooks/` |
 | **Agent** | Specialized AI subprocess for specific roles | `.claude/agents/` |
-| **Skill** | Reusable AI capability modules | `.claude/skills/` |
+| **Skill** | Reusable AI capability modules | `Skill(skill="<name>")` |
 | **Workflow** | Multi-phase development orchestration | `/workflow:*` |
 
 ---

docs/guide/ch02-getting-started.md

@@ -164,16 +164,16 @@ Multi-perspective brainstorming for diverse viewpoints:
 
 ### 2.5.1 View Project Memory
 
-```bash
-ccw memory list
+```typescript
+mcp__ccw-tools__core_memory(operation="list")
 ```
 
 Display all project memories, including learnings, decisions, conventions, and issues.
 
 ### 2.5.2 Search Related Memory
 
-```bash
-ccw memory search "authentication"
+```typescript
+mcp__ccw-tools__core_memory(operation="search", query="authentication")
 ```
 
 Semantic search for memories related to "authentication".
@@ -192,20 +192,16 @@ Interactively capture important knowledge points from the current session.
 
 ### 2.6.1 Semantic Search
 
-Use CodexLens search in VS Code:
+Use ACE semantic search via MCP tool:
 
-```bash
-# Search via CodexLens MCP endpoint
-ccw search "user login logic"
+```typescript
+mcp__ace-tool__search_context(
+  project_root_path="/path/to/project",
+  query="user login logic"
+)
 ```
 
-### 2.6.2 Call Chain Tracing
-
-Search function definitions and all call locations:
-
-```bash
-ccw search --trace "authenticateUser"
-```
+> **Note**: The CLI commands `ccw search` and `ccw memory` are deprecated. Use MCP tools directly.
 
 ---
 
@@ -297,7 +293,7 @@ npm install
 | `/workflow-plan` | Planning workflow |
 | `/brainstorm` | Brainstorming |
 | `/review-code` | Code review |
-| `ccw memory list` | View Memory |
+| `mcp__ccw-tools__core_memory(operation="list")` | View Memory |
 | `ccw cli -p "..."` | CLI invocation |
 
 ---

docs/guide/ch03-core-concepts.md

@@ -185,7 +185,7 @@ graph LR
 | **Prompt** | Codex prompt templates | `.codex/prompts/` |
 | **Workflow** | Team collaboration process | `/workflow:*` |
 | **Session** | Session context management | `/workflow:session:*` |
-| **Memory** | Cross-session knowledge persistence | `ccw memory` |
+| **Memory** | Cross-session knowledge persistence | `mcp__ccw-tools__core_memory(operation="list")` |
 | **Spec** | Project specification constraints | `.workflow/specs/` |
 | **CodexLens** | Semantic code indexing | `.codex-lens/` |
 | **CCW** | CLI invocation framework | `ccw` directory |

docs/guide/ch05-advanced-tips.md

@@ -192,7 +192,7 @@ Configure in `.claude/hooks.json`:
     {
       "name": "save-decisions",
       "description": "Save important decisions",
-      "command": "ccw memory import \"{content}\""
+      "command": "mcp__ccw-tools__core_memory(operation=\"import\", text=\"{content}\")"
     }
   ]
 }

docs/guide/ch06-best-practices.md

@@ -301,12 +301,14 @@ graph LR
 
 ### Memory Maintenance
 
-| Operation | Command |
+| Operation | MCP Tool |
 | --- | --- |
-| List memories | `ccw memory list` |
-| Search memories | `ccw memory search "..."` |
-| Import memory | `ccw memory import "..."` |
-| Export memory | `ccw memory export <id>` |
+| List memories | `mcp__ccw-tools__core_memory(operation="list")` |
+| Search memories | `mcp__ccw-tools__core_memory(operation="search", query="...")` |
+| Import memory | `mcp__ccw-tools__core_memory(operation="import", text="...")` |
+| Export memory | `mcp__ccw-tools__core_memory(operation="export", id="...")` |
+
+> **Note**: The CLI commands `ccw memory *` are deprecated. Use MCP tools directly.
 
 ---
 

docs/guide/workflows.md

@@ -50,8 +50,8 @@ The workflow executes automatically:
 
 After a checkpoint, resume the workflow:
 
-```bash
-ccw workflow resume
+```javascript
+Skill(skill="workflow-execute", args="--resume")
 ```
 
 ## Workflow Tasks
@@ -163,21 +163,21 @@ Always review checkpoints:
 
 Provide feedback during workflow:
 
-```bash
-# Add feedback during review
-ccw workflow feedback --task REVIEW-001 --message "Tests need more edge cases"
+```javascript
+// Add feedback during review
+Skill(skill="workflow-execute", args="--feedback --task REVIEW-001")
 ```
 
 ### 4. Monitor Progress
 
 Track workflow status:
 
-```bash
-# Check workflow status
-ccw workflow status
+```javascript
+// Check workflow status
+Skill(skill="workflow-execute", args="--status")
 
-# View task details
-ccw workflow task IMPL-001
+// View task details
+Skill(skill="workflow-execute", args="--task IMPL-001")
 ```
 
 ## Troubleshooting
@@ -186,21 +186,21 @@ ccw workflow task IMPL-001
 
 If a workflow stalls:
 
-```bash
-# Check for blocked tasks
-ccw workflow status --blocked
+```javascript
+// Check for blocked tasks
+Skill(skill="workflow-execute", args="--status --blocked")
 
-# Reset stuck tasks
-ccw workflow reset --task IMPL-001
+// Reset stuck tasks
+Skill(skill="workflow-execute", args="--reset --task IMPL-001")
 ```
 
 ### Failed Tasks
 
 Retry failed tasks:
 
-```bash
-# Retry with new prompt
-ccw workflow retry --task IMPL-001 --prompt "Fix the TypeScript errors"
+```javascript
+// Retry with new prompt
+Skill(skill="workflow-execute", args="--retry --task IMPL-001")
 ```
 
 ::: info See Also

docs/skills/custom.md

@@ -257,13 +257,15 @@ describe('my-skill', () => {
 
 ## Debugging
 
-Enable debug logging:
+Enable debug logging and invoke skill directly:
 
 ```bash
 export CCW_DEBUG=1
-ccw skill run my-skill "test input"
+Skill(skill="my-skill", args="test input")
 ```
 
+> **Note**: The CLI command `ccw skill run` is deprecated. Use `Skill()` tool directly.
+
 ::: info See Also
 - [Core Skills](./core-skills.md) - Built-in skill reference
 - [Skills Library](./index.md) - All available skills

docs/skills/index.md

@@ -246,8 +246,8 @@ Skill(skill="team-roadmap-dev", args="--epic ts-migration")
 **Scenario**: Generate API documentation
 
 ```bash
-# Step 1: Capture existing patterns
-ccw memory:capture "API patterns: REST, versioning, error handling"
+# Step 1: Capture existing patterns via memory skill
+Skill(skill="memory-capture", args="API patterns: REST, versioning, error handling")
 
 # Step 2: Generate docs
 ccw software-manual --output ./docs/api/

docs/workflows/examples.md

@@ -51,9 +51,9 @@ This is an output from `workflow-lite-planex` command.
 
 ### Execution Steps
 
-```shell
-# Execute the plan
-ccw workflow-execute --session WFS-001
+```javascript
+// Execute the plan
+Skill(skill="workflow-execute", args="--session WFS-001")
 ```
 
 ---
@@ -388,7 +388,7 @@ To use these examples in your own projects:
 1. **Copy the structure** that matches your needs
 2. **Modify fields** to fit your requirements
 3. **Remove sensitive information**
-4. **Test the output** with `ccw workflow-execute`
+4. **Test the output** with `Skill(skill="workflow-execute")`
 
 ::: tip
 These examples are generated by CCW workflow tools. Run relevant commands to generate similar outputs for your projects.

docs/zh/skills/custom.md

@@ -261,7 +261,7 @@ describe('my-skill', () => {
 
 ```bash
 export CCW_DEBUG=1
-ccw skill run my-skill "test input"
+Skill(skill="my-skill", args="\"test input\"")
 ```
 
 ::: info 参见

docs/zh/skills/index.md

@@ -219,11 +219,11 @@ Skill(skill="review-code")
 ccw cli -p "Analyze /api/users endpoint for N+1 query issues" --tool gemini --mode analysis
 
 # 步骤 2：深度调查（如需要）
-ccw workflow:debug-with-file
+Skill(skill="workflow:debug-with-file")
 # 创建假设、植入代码、分析日志
 
 # 步骤 3：应用修复
-ccw workflow-execute --task "Fix N+1 query in user endpoint"
+Skill(skill="workflow-execute", args="--task \"Fix N+1 query in user endpoint\"")
 ```
 
 ### 示例 3：代码迁移
@@ -247,10 +247,10 @@ Skill(skill="team-roadmap-dev", args="--epic ts-migration")
 
 ```bash
 # 步骤 1：捕获现有模式
-ccw memory:capture "API patterns: REST, versioning, error handling"
+Skill(skill="memory-capture", args="\"API patterns: REST, versioning, error handling\"")
 
 # 步骤 2：生成文档
-ccw software-manual --output ./docs/api/
+Skill(skill="software-manual", args="--output ./docs/api/")
 ```
 
 ### 示例 5：代码审查流水线
@@ -259,10 +259,10 @@ ccw software-manual --output ./docs/api/
 
 ```bash
 # 全面审查
-ccw review-code --focus security,performance
+Skill(skill="review-code", args="--focus security,performance")
 
 # 或使用循环自动修复
-ccw review-cycle --max-iterations 3
+Skill(skill="review-cycle", args="--max-iterations 3")
 ```
 
 ### 最佳效果提示