refactor: Replace CLI execution flags with semantic-driven tool selection

- Remove --cli-execute flag from plan.md, tdd-plan.md, task-generate-agent.md, task-generate-tdd.md
- Remove --use-codex flag from test-gen.md, test-fix-gen.md, test-task-generate.md
- Remove meta.use_codex from task JSON schema in action-planning-agent.md and cli-planning-agent.md
- Add "Semantic CLI Tool Selection" section to action-planning-agent.md
- Document explicit source: metadata.task_description from context-package.json
- Update test-fix-agent.md execution mode documentation
- Update action-plan-verify.md to remove use_codex validation
- Sync SKILL reference copies via analyze_commands.py

CLI tool usage now determined semantically from user's task description
(e.g., "use Codex for implementation") instead of explicit flags.

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

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

.claude/agents/action-planning-agent.md

@@ -43,7 +43,6 @@ You are a pure execution agent specialized in creating actionable implementation
   - `context_package_path`: Context package with brainstorming artifacts catalog
 - **Metadata**: Simple values
   - `session_id`: Workflow session identifier (WFS-[topic])
-  - `execution_mode`: agent-mode | cli-execute-mode
   - `mcp_capabilities`: Available MCP tools (exa_code, exa_web, code_index)
 
 **Legacy Support** (backward compatibility):
@@ -244,8 +243,7 @@ Generate individual `.task/IMPL-*.json` files with the following structure:
     "type": "test-gen|test-fix",
     "agent": "@code-developer|@test-fix-agent",
     "test_framework": "jest|vitest|pytest|junit|mocha",
-    "coverage_target": "80%",
-    "use_codex": true|false
+    "coverage_target": "80%"
   }
 }
 ```
@@ -253,7 +251,8 @@ Generate individual `.task/IMPL-*.json` files with the following structure:
 **Test-Specific Fields**:
 - `test_framework`: Existing test framework from project (required for test tasks)
 - `coverage_target`: Target code coverage percentage (optional)
-- `use_codex`: Whether to use Codex for automated fixes in test-fix tasks (optional, default: false)
+
+**Note**: CLI tool usage for test-fix tasks is now controlled via `flow_control.implementation_approach` steps with `command` fields, not via `meta.use_codex`.
 
 #### Context Object
 
@@ -485,15 +484,31 @@ The `implementation_approach` supports **two execution modes** based on the pres
      - `bash(codex --full-auto exec '[task]' resume --last --skip-git-repo-check -s danger-full-access)` (multi-step)
      - `bash(cd [path] && gemini -p '[prompt]' --approval-mode yolo)` (write mode)
 
-**Mode Selection Strategy**:
-- **Default to agent execution** for most tasks
-- **Use CLI mode** when:
-  - User explicitly requests CLI tool (codex/gemini/qwen)
-  - Task requires multi-step autonomous reasoning beyond agent capability
-  - Complex refactoring needs specialized tool analysis
-  - Building on previous CLI execution context (use `resume --last`)
+**Semantic CLI Tool Selection**:
 
-**Key Principle**: The `command` field is **optional**. Agent must decide based on task complexity and user preference.
+Agent determines CLI tool usage per-step based on user semantics and task nature.
+
+**Source**: Scan `metadata.task_description` from context-package.json for CLI tool preferences.
+
+**User Semantic Triggers** (patterns to detect in task_description):
+- "use Codex/codex" → Add `command` field with Codex CLI
+- "use Gemini/gemini" → Add `command` field with Gemini CLI
+- "use Qwen/qwen" → Add `command` field with Qwen CLI
+- "CLI execution" / "automated" → Infer appropriate CLI tool
+
+**Task-Based Selection** (when no explicit user preference):
+- **Implementation/coding**: Codex preferred for autonomous development
+- **Analysis/exploration**: Gemini preferred for large context analysis
+- **Documentation**: Gemini/Qwen with write mode (`--approval-mode yolo`)
+- **Testing**: Depends on complexity - simple=agent, complex=Codex
+
+**Default Behavior**: Agent always executes the workflow. CLI commands are embedded in `implementation_approach` steps:
+- Agent orchestrates task execution
+- When step has `command` field, agent executes it via Bash
+- When step has no `command` field, agent implements directly
+- This maintains agent control while leveraging CLI tool power
+
+**Key Principle**: The `command` field is **optional**. Agent decides based on user semantics and task complexity.
 
 **Examples**:
 

.claude/agents/cli-planning-agent.md

@@ -66,8 +66,7 @@ You are a specialized execution agent that bridges CLI analysis tools with task
   "task_config": {
     "agent": "@test-fix-agent",
     "type": "test-fix-iteration",
-    "max_iterations": 5,
-    "use_codex": false
+    "max_iterations": 5
   }
 }
 ```
@@ -263,7 +262,6 @@ function extractModificationPoints() {
     "analysis_report": ".process/iteration-{iteration}-analysis.md",
     "cli_output": ".process/iteration-{iteration}-cli-output.txt",
     "max_iterations": "{task_config.max_iterations}",
-    "use_codex": "{task_config.use_codex}",
     "parent_task": "{parent_task_id}",
     "created_by": "@cli-planning-agent",
     "created_at": "{timestamp}"

.claude/agents/code-developer.md

@@ -24,8 +24,6 @@ You are a code execution specialist focused on implementing high-quality, produc
 - **Context-driven** - Use provided context and existing code patterns
 - **Quality over speed** - Write boring, reliable code that works
 
-
-
 ## Execution Process
 
 ### 1. Context Assessment

.claude/agents/test-fix-agent.md

@@ -142,9 +142,9 @@ run_test_layer "L1-unit" "$UNIT_CMD"
 
 ### 3. Failure Diagnosis & Fixing Loop
 
-**Execution Modes**:
+**Execution Modes** (determined by `flow_control.implementation_approach`):
 
-**A. Manual Mode (Default, meta.use_codex=false)**:
+**A. Agent Mode (Default, no `command` field in steps)**:
 ```
 WHILE tests are failing AND iterations < max_iterations:
     1. Use Gemini to diagnose failure (bug-fix template)
@@ -155,17 +155,17 @@ WHILE tests are failing AND iterations < max_iterations:
 END WHILE
 ```
 
-**B. Codex Mode (meta.use_codex=true)**:
+**B. CLI Mode (`command` field present in implementation_approach steps)**:
 ```
 WHILE tests are failing AND iterations < max_iterations:
     1. Use Gemini to diagnose failure (bug-fix template)
-    2. Use Codex to apply fixes automatically with resume mechanism
+    2. Execute `command` field (e.g., Codex) to apply fixes automatically
     3. Re-run test suite
     4. Verify fix doesn't break other tests
 END WHILE
 ```
 
-**Codex Resume in Test-Fix Cycle** (when `meta.use_codex=true`):
+**Codex Resume in Test-Fix Cycle** (when step has `command` with Codex):
 - First iteration: Start new Codex session with full context
 - Subsequent iterations: Use `resume --last` to maintain fix history and apply consistent strategies