docs: rename general-purpose agent to universal-executor and update documentation

Major updates in this release:

1. Agent Renaming (13 files, 21 references):
   - Renamed general-purpose → universal-executor to avoid naming conflicts
   - Updated all references in commands and workflows
   - Maintained backward compatibility in documentation

2. README Updates (4 files):
   - Removed /workflow:session:start step (auto-created by /workflow:plan)
   - Simplified workflow from 4 steps to 3 steps
   - Updated version to v4.6.2
   - Added CLI tool usage guidelines

3. GETTING_STARTED Enhancements (2 files):
   - Added Design Philosophy section explaining multi-model CLI integration
   - Added comprehensive CLI tool usage guide with common workflows
   - Reorganized quick start to emphasize automatic session creation
   - Added examples for bug fixes and feature development

Files modified:
- Agent config: .claude/agents/general-purpose.md
- Commands: 7 files in .claude/commands/
- Workflows: 5 files in .claude/workflows/
- Documentation: README.md, README_CN.md, GETTING_STARTED.md, GETTING_STARTED_CN.md

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

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

.claude/agents/general-purpose.md

@@ -1,5 +1,5 @@
 ---
-name: general-purpose
+name: universal-executor
 description: |
   Versatile execution agent for implementing any task efficiently. Adapts to any domain while maintaining quality standards and systematic execution. Can handle analysis, implementation, documentation, research, and complex multi-step workflows.
 

.claude/commands/memory/load.md

@@ -12,10 +12,10 @@ examples:
 
 ## 1. Overview
 
-The `memory:load` command **delegates to a general-purpose agent** to analyze the project and return a structured "Core Content Pack". This pack is loaded into the main thread's memory, providing essential context for subsequent agent operations while minimizing token consumption.
+The `memory:load` command **delegates to a universal-executor agent** to analyze the project and return a structured "Core Content Pack". This pack is loaded into the main thread's memory, providing essential context for subsequent agent operations while minimizing token consumption.
 
 **Core Philosophy**:
-- **Agent-Driven**: Fully delegates execution to general-purpose agent
+- **Agent-Driven**: Fully delegates execution to universal-executor agent
 - **Read-Only Analysis**: Does not modify code, only extracts context
 - **Structured Output**: Returns standardized JSON content package
 - **Memory Optimization**: Package loaded directly into main thread memory
@@ -34,7 +34,7 @@ The `memory:load` command **delegates to a general-purpose agent** to analyze th
 
 ## 3. Agent-Driven Execution Flow
 
-The command fully delegates to **general-purpose agent**, which autonomously:
+The command fully delegates to **universal-executor agent**, which autonomously:
 
 1. **Analyzes Project Structure**: Executes `get_modules_by_depth.sh` to understand architecture
 2. **Loads Documentation**: Reads CLAUDE.md, README.md and other key docs
@@ -94,7 +94,7 @@ The command fully delegates to **general-purpose agent**, which autonomously:
 
 ```javascript
 Task(
-  subagent_type="general-purpose",
+  subagent_type="universal-executor",
   description="Load project memory: ${task_description}",
   prompt=`
 ## Mission: Load Project Memory Context

.claude/commands/task/breakdown.md

@@ -99,7 +99,7 @@ Files updated: .task/IMPL-1.json + 2 subtask files + TODO_LIST.md
 - **Implementation** → `@code-developer`
 - **Testing** → `@code-developer` (type: "test-gen")
 - **Test Validation** → `@test-fix-agent` (type: "test-fix")
-- **Review** → `@general-purpose` (optional)
+- **Review** → `@universal-executor` (optional)
 
 ### Context Inheritance
 - Subtasks inherit parent requirements

.claude/commands/task/create.md

@@ -104,7 +104,7 @@ Based on task type and title keywords:
 - **Design/Plan** → @planning-agent
 - **Test Generation** → @code-developer (type: "test-gen")
 - **Test Execution/Fix** → @test-fix-agent (type: "test-fix")
-- **Review/Audit** → @general-purpose (optional, only when explicitly requested)
+- **Review/Audit** → @universal-executor (optional, only when explicitly requested)
 
 ## Validation Rules
 

.claude/commands/task/execute.md

@@ -19,7 +19,7 @@ argument-hint: "task-id"
     -   Executes step-by-step, requiring user confirmation at each checkpoint.
     -   Allows for dynamic adjustments and manual review during the process.
 -   **review**
-    -   Optional manual review using `@general-purpose`.
+    -   Optional manual review using `@universal-executor`.
     -   Used only when explicitly requested by user.
 
 ### 🤖 **Agent Selection Logic**
@@ -45,7 +45,7 @@ FUNCTION select_agent(task, agent_override):
             WHEN CONTAINS "Execute tests", "Fix tests", "Validate":
                 RETURN "@test-fix-agent" // type: test-fix
             WHEN CONTAINS "Review code":
-                RETURN "@general-purpose" // Optional manual review
+                RETURN "@universal-executor" // Optional manual review
             DEFAULT:
                 RETURN "@code-developer" // Default agent
         END CASE
@@ -236,7 +236,7 @@ Different agents receive context tailored to their function, including implement
 - Error conditions to validate from implementation.context_notes.error_handling
 - Performance requirements from implementation.context_notes.performance_considerations
 
-**`@general-purpose`**:
+**`@universal-executor`**:
 - Used for optional manual reviews when explicitly requested
 - Code quality standards and implementation patterns
 - Security considerations from implementation.context_notes.risks

.claude/commands/workflow/execute.md

@@ -466,7 +466,7 @@ Task(subagent_type="{meta.agent}",
   "status": "pending|active|completed|blocked",
   "meta": {
     "type": "feature|bugfix|refactor|test-gen|test-fix|docs",
-    "agent": "@code-developer|@test-fix-agent|@general-purpose"
+    "agent": "@code-developer|@test-fix-agent|@universal-executor"
   },
   "context": {
     "requirements": ["req1", "req2"],
@@ -552,7 +552,7 @@ meta.agent missing → Infer from meta.type:
   - "feature" → @code-developer
   - "test-gen" → @code-developer
   - "test-fix" → @test-fix-agent
-  - "review" → @general-purpose
+  - "review" → @universal-executor
   - "docs" → @doc-generator
 ```
 

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

@@ -1,6 +1,6 @@
 ---
 name: gather
-description: Intelligently collect project context using general-purpose agent based on task description and package into standardized JSON
+description: Intelligently collect project context using universal-executor agent based on task description and package into standardized JSON
 argument-hint: "--session WFS-session-id \"task description\""
 examples:
   - /workflow:tools:context-gather --session WFS-user-auth "Implement user authentication system"
@@ -14,7 +14,7 @@ examples:
 Agent-driven intelligent context collector that gathers relevant information from project codebase, documentation, and dependencies based on task descriptions, generating standardized context packages.
 
 ## Core Philosophy
-- **Agent-Driven**: Delegate execution to general-purpose agent for autonomous operation
+- **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
@@ -62,7 +62,7 @@ Agent-driven intelligent context collector that gathers relevant information fro
 **Agent Invocation**:
 ```javascript
 Task(
-  subagent_type="general-purpose",
+  subagent_type="universal-executor",
   description="Gather project context and generate context package",
   prompt=`
 ## Execution Context

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

@@ -174,7 +174,7 @@ This enhanced 5-field schema embeds all necessary context, artifacts, and execut
   "status": "pending|active|completed|blocked|container",
   "meta": {
     "type": "feature|bugfix|refactor|test-gen|test-fix|docs",
-    "agent": "@code-developer|@test-fix-agent|@general-purpose",
+    "agent": "@code-developer|@test-fix-agent|@universal-executor",
     "execution_group": "group-id|null",
     "context_signature": "hash-of-focus_paths-and-artifacts"
   },

.claude/workflows/cli-templates/prompts/workflow/task-json-agent-mode.txt

@@ -9,7 +9,7 @@ Task JSON Schema - Agent Mode (No Command Field)
   "status": "pending",
   "meta": {
     "type": "feature|bugfix|refactor|test|docs",
-    "agent": "@code-developer|@test-fix-agent|@general-purpose"
+    "agent": "@code-developer|@test-fix-agent|@universal-executor"
   },
   "context": {
     "requirements": ["extracted from analysis"],

.claude/workflows/cli-templates/prompts/workflow/task-json-cli-mode.txt

@@ -9,7 +9,7 @@ Task JSON Schema - CLI Execute Mode (With Command Field)
   "status": "pending",
   "meta": {
     "type": "feature|bugfix|refactor|test|docs",
-    "agent": "@code-developer|@test-fix-agent|@general-purpose"
+    "agent": "@code-developer|@test-fix-agent|@universal-executor"
   },
   "context": {
     "requirements": ["extracted from analysis"],

.claude/workflows/task-core.md

@@ -14,7 +14,7 @@ All task files use this simplified 5-field schema (aligned with workflow-archite
 
   "meta": {
     "type": "feature|bugfix|refactor|test-gen|test-fix|docs",
-    "agent": "@code-developer|@action-planning-agent|@test-fix-agent|@general-purpose"
+    "agent": "@code-developer|@action-planning-agent|@test-fix-agent|@universal-executor"
   },
 
   "context": {
@@ -155,14 +155,14 @@ Tasks inherit from:
 - **@code-developer**: Implementation tasks, coding, test writing
 - **@action-planning-agent**: Design, architecture planning
 - **@test-fix-agent**: Test execution, failure diagnosis, code fixing
-- **@general-purpose**: Optional manual review (only when explicitly requested)
+- **@universal-executor**: Optional manual review (only when explicitly requested)
 
 ### Agent Context Filtering
 Each agent receives tailored context:
 - **@code-developer**: Complete implementation details, test requirements
 - **@action-planning-agent**: High-level requirements, risks, architecture
 - **@test-fix-agent**: Test execution, failure diagnosis, code fixing
-- **@general-purpose**: Quality standards, security considerations (when requested)
+- **@universal-executor**: Quality standards, security considerations (when requested)
 
 ## Deprecated Fields
 

.claude/workflows/workflow-architecture.md

@@ -114,7 +114,7 @@ All task files use this unified 5-field schema with optional artifacts enhanceme
 
   "meta": {
     "type": "feature|bugfix|refactor|test-gen|test-fix|docs",
-    "agent": "@code-developer|@action-planning-agent|@test-fix-agent|@general-purpose"
+    "agent": "@code-developer|@action-planning-agent|@test-fix-agent|@universal-executor"
   },
 
   "context": {
@@ -912,7 +912,7 @@ Based on task type and title keywords:
 - **Planning tasks** → @action-planning-agent
 - **Implementation** → @code-developer (code + tests)
 - **Test execution/fixing** → @test-fix-agent
-- **Review** → @general-purpose (optional, only when explicitly requested)
+- **Review** → @universal-executor (optional, only when explicitly requested)
 
 ### Execution Context
 Agents receive complete task JSON plus workflow context: