Refactor CLI command usage from ccw cli exec to ccw cli -p for improved prompt handling

- Updated command patterns across documentation and templates to reflect the new CLI syntax.
- Enhanced CLI tool implementation to support reading prompts from files and multi-line inputs.
- Modified core components and views to ensure compatibility with the new command structure.
- Adjusted help messages and internationalization strings to align with the updated command format.
- Improved error handling and user notifications in the CLI execution flow.

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

@@ -470,14 +470,14 @@ function computeCliStrategy(task, allTasks) {
   // Pattern: Gemini CLI deep analysis
   {
     "step": "gemini_analyze_[aspect]",
-    "command": "ccw cli exec 'PURPOSE: [goal]\\nTASK: [tasks]\\nMODE: analysis\\nCONTEXT: @[paths]\\nEXPECTED: [output]\\nRULES: $(cat [template]) | [constraints] | analysis=READ-ONLY' --tool gemini --mode analysis --cd [path]",
+    "command": "ccw cli -p 'PURPOSE: [goal]\\nTASK: [tasks]\\nMODE: analysis\\nCONTEXT: @[paths]\\nEXPECTED: [output]\\nRULES: $(cat [template]) | [constraints] | analysis=READ-ONLY' --tool gemini --mode analysis --cd [path]",
     "output_to": "analysis_result"
   },
 
   // Pattern: Qwen CLI analysis (fallback/alternative)
   {
     "step": "qwen_analyze_[aspect]",
-    "command": "ccw cli exec '[similar to gemini pattern]' --tool qwen --mode analysis --cd [path]",
+    "command": "ccw cli -p '[similar to gemini pattern]' --tool qwen --mode analysis --cd [path]",
     "output_to": "analysis_result"
   },
 
@@ -518,7 +518,7 @@ The examples above demonstrate **patterns**, not fixed requirements. Agent MUST:
 4. **Command Composition Patterns**:
    - **Single command**: `bash([simple_search])`
    - **Multiple commands**: `["bash([cmd1])", "bash([cmd2])"]`
-   - **CLI analysis**: `ccw cli exec '[prompt]' --tool gemini --mode analysis --cd [path]`
+   - **CLI analysis**: `ccw cli -p '[prompt]' --tool gemini --mode analysis --cd [path]`
    - **MCP integration**: `mcp__[tool]__[function]([params])`
 
 **Key Principle**: Examples show **structure patterns**, not specific implementations. Agent must create task-appropriate steps dynamically.
@@ -542,9 +542,9 @@ The `implementation_approach` supports **two execution modes** based on the pres
    - **Use for**: Large-scale features, complex refactoring, or when user explicitly requests CLI tool usage
    - **Required fields**: Same as default mode **PLUS** `command`, `resume_from` (optional)
    - **Command patterns** (with resume support):
-     - `ccw cli exec '[prompt]' --tool codex --mode write --cd [path]`
+     - `ccw cli -p '[prompt]' --tool codex --mode write --cd [path]`
-     - `ccw cli exec '[prompt]' --resume ${previousCliId} --tool codex --mode write` (resume from previous)
+     - `ccw cli -p '[prompt]' --resume ${previousCliId} --tool codex --mode write` (resume from previous)
-     - `ccw cli exec '[prompt]' --tool gemini --mode write --cd [path]` (write mode)
+     - `ccw cli -p '[prompt]' --tool gemini --mode write --cd [path]` (write mode)
    - **Resume mechanism**: When step depends on previous CLI execution, include `--resume` with previous execution ID
 
 **Semantic CLI Tool Selection**:
@@ -621,7 +621,7 @@ Agent determines CLI tool usage per-step based on user semantics and task nature
     "step": 3,
     "title": "Execute implementation using CLI tool",
     "description": "Use Codex/Gemini for complex autonomous execution",
-    "command": "ccw cli exec '[prompt]' --tool codex --mode write --cd [path]",
+    "command": "ccw cli -p '[prompt]' --tool codex --mode write --cd [path]",
     "modification_points": ["[Same as default mode]"],
     "logic_flow": ["[Same as default mode]"],
     "depends_on": [1, 2],
@@ -634,7 +634,7 @@ Agent determines CLI tool usage per-step based on user semantics and task nature
     "step": 4,
     "title": "Continue implementation with context",
     "description": "Resume from previous step with accumulated context",
-    "command": "ccw cli exec '[continuation prompt]' --resume ${step3_cli_id} --tool codex --mode write",
+    "command": "ccw cli -p '[continuation prompt]' --resume ${step3_cli_id} --tool codex --mode write",
     "resume_from": "step3_cli_id",  // Reference previous step's CLI ID
     "modification_points": ["[Continue from step 3]"],
     "logic_flow": ["[Build on previous output]"],

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

@@ -148,7 +148,7 @@ discuss → multi (gemini + codex parallel)
 
 **Gemini/Qwen (Analysis)**:
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: {goal}
 TASK: {task}
 MODE: analysis
@@ -162,17 +162,17 @@ RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)
 
 **Gemini/Qwen (Write)**:
 ```bash
-ccw cli exec "..." --tool gemini --mode write --cd {dir}
+ccw cli -p "..." --tool gemini --mode write --cd {dir}
 ```
 
 **Codex (Write)**:
 ```bash
-ccw cli exec "..." --tool codex --mode write --cd {dir}
+ccw cli -p "..." --tool codex --mode write --cd {dir}
 ```
 
 **Cross-Directory** (Gemini/Qwen):
 ```bash
-ccw cli exec "CONTEXT: @**/* @../shared/**/*" --tool gemini --mode analysis --cd src/auth --includeDirs ../shared
+ccw cli -p "CONTEXT: @**/* @../shared/**/*" --tool gemini --mode analysis --cd src/auth --includeDirs ../shared
 ```
 
 **Directory Scope**:

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

@@ -78,7 +78,7 @@ rg "^import .* from " -n | head -30
 ### Gemini Semantic Analysis (deep-scan, dependency-map)
 
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: {from prompt}
 TASK: {from prompt}
 MODE: analysis

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

@@ -78,7 +78,7 @@ Phase 4: planObject Generation
 ## CLI Command Template
 
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Generate plan for {task_description}
 TASK:
 • Analyze task/bug description and context

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

@@ -107,7 +107,7 @@ Phase 3: Task JSON Generation
 
 **Template-Based Command Construction with Test Layer Awareness**:
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Analyze {test_type} test failures and generate fix strategy for iteration {iteration}
 TASK:
 • Review {failed_tests.length} {test_type} test failures: [{test_names}]
@@ -527,7 +527,7 @@ See: `.process/iteration-{iteration}-cli-output.txt`
 1. **Detect test_type**: "integration" → Apply integration-specific diagnosis
 2. **Execute CLI**:
    ```bash
-   ccw cli exec "PURPOSE: Analyze integration test failure...
+   ccw cli -p "PURPOSE: Analyze integration test failure...
    TASK: Examine component interactions, data flow, interface contracts...
    RULES: Analyze full call stack and data flow across components" --tool gemini --mode analysis
    ```

.claude/agents/code-developer.md

@@ -123,7 +123,7 @@ When task JSON contains `flow_control.implementation_approach` array:
 
 **CLI Command Execution (CLI Execute Mode)**:
 When step contains `command` field with Codex CLI, execute via CCW CLI. For Codex resume:
-- First task (`depends_on: []`): `ccw cli exec "..." --tool codex --mode write --cd [path]`
+- First task (`depends_on: []`): `ccw cli -p "..." --tool codex --mode write --cd [path]`
 - Subsequent tasks (has `depends_on`): Use CCW CLI with resume context to maintain session
 
 **Test-Driven Development**:

.claude/agents/doc-generator.md

@@ -63,7 +63,7 @@ The agent supports **two execution modes** based on task JSON's `meta.cli_execut
    - Agent substitutes [target_folders] into command
    - Agent executes CLI command via CCW:
    ```bash
-   ccw cli exec "
+   ccw cli -p "
    PURPOSE: Generate module documentation
    TASK: Create API.md and README.md for each module
    MODE: write
@@ -216,7 +216,7 @@ Before completion, verify:
 {
   "step": "analyze_module_structure",
   "action": "Deep analysis of module structure and API",
-  "command": "ccw cli exec \"PURPOSE: Document module comprehensively\nTASK: Extract module purpose, architecture, public API, dependencies\nMODE: analysis\nCONTEXT: @**/* System: [system_context]\nEXPECTED: Complete module analysis for documentation\nRULES: $(cat ~/.claude/workflows/cli-templates/prompts/documentation/module-documentation.txt)\" --tool gemini --mode analysis --cd src/auth",
+  "command": "ccw cli -p \"PURPOSE: Document module comprehensively\nTASK: Extract module purpose, architecture, public API, dependencies\nMODE: analysis\nCONTEXT: @**/* System: [system_context]\nEXPECTED: Complete module analysis for documentation\nRULES: $(cat ~/.claude/workflows/cli-templates/prompts/documentation/module-documentation.txt)\" --tool gemini --mode analysis --cd src/auth",
   "output_to": "module_analysis",
   "on_error": "fail"
 }

.claude/commands/memory/docs.md

@@ -238,9 +238,9 @@ api_id=$((group_count + 3))
 | **CLI** | true | implementation_approach | write | --mode write | Execute CLI commands, validate output |
 
 **Command Patterns**:
-- Gemini/Qwen: `ccw cli exec "..." --tool gemini --mode analysis --cd dir`
+- Gemini/Qwen: `ccw cli -p "..." --tool gemini --mode analysis --cd dir`
-- CLI Mode: `ccw cli exec "..." --tool gemini --mode write --cd dir`
+- CLI Mode: `ccw cli -p "..." --tool gemini --mode write --cd dir`
-- Codex: `ccw cli exec "..." --tool codex --mode write --cd dir`
+- Codex: `ccw cli -p "..." --tool codex --mode write --cd dir`
 
 **Generation Process**:
 1. Read configuration values (tool, cli_execute, mode) from workflow-session.json
@@ -331,7 +331,7 @@ api_id=$((group_count + 3))
 {
   "step": 2,
   "title": "Batch generate documentation via CLI",
-  "command": "ccw cli exec 'PURPOSE: Generate module docs\\nTASK: Create documentation\\nMODE: write\\nCONTEXT: @**/* [phase2_context]\\nEXPECTED: API.md and README.md\\nRULES: Mirror structure' --tool gemini --mode write --cd ${dirs_from_group}",
+  "command": "ccw cli -p 'PURPOSE: Generate module docs\\nTASK: Create documentation\\nMODE: write\\nCONTEXT: @**/* [phase2_context]\\nEXPECTED: API.md and README.md\\nRULES: Mirror structure' --tool gemini --mode write --cd ${dirs_from_group}",
   "depends_on": [1],
   "output": "generated_docs"
 }
@@ -363,7 +363,7 @@ api_id=$((group_count + 3))
       },
       {
         "step": "analyze_project",
-        "command": "bash(ccw cli exec \"PURPOSE: Analyze project structure\\nTASK: Extract overview from modules\\nMODE: analysis\\nCONTEXT: [all_module_docs]\\nEXPECTED: Project outline\" --tool gemini --mode analysis)",
+        "command": "bash(ccw cli -p \"PURPOSE: Analyze project structure\\nTASK: Extract overview from modules\\nMODE: analysis\\nCONTEXT: [all_module_docs]\\nEXPECTED: Project outline\" --tool gemini --mode analysis)",
         "output_to": "project_outline"
       }
     ],
@@ -403,7 +403,7 @@ api_id=$((group_count + 3))
     "pre_analysis": [
       {"step": "load_existing_docs", "command": "bash(cat .workflow/docs/${project_name}/{ARCHITECTURE,EXAMPLES}.md 2>/dev/null || echo 'No existing docs')", "output_to": "existing_arch_examples"},
       {"step": "load_all_docs", "command": "bash(cat .workflow/docs/${project_name}/README.md && find .workflow/docs/${project_name} -type f -name '*.md' ! -path '*/README.md' ! -path '*/ARCHITECTURE.md' ! -path '*/EXAMPLES.md' ! -path '*/api/*' | xargs cat)", "output_to": "all_docs"},
-      {"step": "analyze_architecture", "command": "bash(ccw cli exec \"PURPOSE: Analyze system architecture\\nTASK: Synthesize architectural overview and examples\\nMODE: analysis\\nCONTEXT: [all_docs]\\nEXPECTED: Architecture + Examples outline\" --tool gemini --mode analysis)", "output_to": "arch_examples_outline"}
+      {"step": "analyze_architecture", "command": "bash(ccw cli -p \"PURPOSE: Analyze system architecture\\nTASK: Synthesize architectural overview and examples\\nMODE: analysis\\nCONTEXT: [all_docs]\\nEXPECTED: Architecture + Examples outline\" --tool gemini --mode analysis)", "output_to": "arch_examples_outline"}
     ],
     "implementation_approach": [
       {
@@ -440,7 +440,7 @@ api_id=$((group_count + 3))
     "pre_analysis": [
       {"step": "discover_api", "command": "bash(rg 'router\\.| @(Get|Post)' -g '*.{ts,js}')", "output_to": "endpoint_discovery"},
       {"step": "load_existing_api", "command": "bash(cat .workflow/docs/${project_name}/api/README.md 2>/dev/null || echo 'No existing API docs')", "output_to": "existing_api_docs"},
-      {"step": "analyze_api", "command": "bash(ccw cli exec \"PURPOSE: Document HTTP API\\nTASK: Analyze endpoints\\nMODE: analysis\\nCONTEXT: @src/api/**/* [endpoint_discovery]\\nEXPECTED: API outline\" --tool gemini --mode analysis)", "output_to": "api_outline"}
+      {"step": "analyze_api", "command": "bash(ccw cli -p \"PURPOSE: Document HTTP API\\nTASK: Analyze endpoints\\nMODE: analysis\\nCONTEXT: @src/api/**/* [endpoint_discovery]\\nEXPECTED: API outline\" --tool gemini --mode analysis)", "output_to": "api_outline"}
     ],
     "implementation_approach": [
       {

.claude/commands/memory/load.md

@@ -136,7 +136,7 @@ Task(
 Execute Gemini/Qwen CLI for deep analysis (saves main thread tokens):
 
 \`\`\`bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Extract project core context for task: ${task_description}
 TASK: Analyze project architecture, tech stack, key patterns, relevant files
 MODE: analysis

.claude/commands/memory/workflow-skill-memory.md

@@ -187,7 +187,7 @@ Objectives:
 
 3. Use Gemini for aggregation (optional):
    Command pattern:
-   ccw cli exec "
+   ccw cli -p "
    PURPOSE: Extract lessons and conflicts from workflow session
    TASK:
    • Analyze IMPL_PLAN and lessons from manifest
@@ -334,7 +334,7 @@ Objectives:
    - Sort sessions by date
 
 2. Use Gemini for final aggregation:
-   ccw cli exec "
+   ccw cli -p "
    PURPOSE: Aggregate lessons and conflicts from all workflow sessions
    TASK:
    • Group successes by functional domain

.claude/commands/workflow/lite-execute.md

@@ -474,7 +474,7 @@ Detailed plan: ${executionContext.session.artifacts.plan}`)
   return prompt
 }
 
-ccw cli exec "${buildCLIPrompt(batch)}" --tool codex --mode write
+ccw cli -p "${buildCLIPrompt(batch)}" --tool codex --mode write
 ```
 
 **Execution with fixed IDs** (predictable ID pattern):
@@ -497,8 +497,8 @@ const previousCliId = batch.resumeFromCliId || null
 
 // Build command with fixed ID (and optional resume for continuation)
 const cli_command = previousCliId
-  ? `ccw cli exec "${buildCLIPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId} --resume ${previousCliId}`
+  ? `ccw cli -p "${buildCLIPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId} --resume ${previousCliId}`
-  : `ccw cli exec "${buildCLIPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId}`
+  : `ccw cli -p "${buildCLIPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId}`
 
 bash_result = Bash(
   command=cli_command,
@@ -520,7 +520,7 @@ if (bash_result.status === 'failed' || bash_result.status === 'timeout') {
 ⚠️ Execution incomplete. Resume available:
    Fixed ID: ${fixedExecutionId}
    Lookup: ccw cli detail ${fixedExecutionId}
-   Resume: ccw cli exec "Continue tasks" --resume ${fixedExecutionId} --tool codex --mode write --id ${fixedExecutionId}-retry
+   Resume: ccw cli -p "Continue tasks" --resume ${fixedExecutionId} --tool codex --mode write --id ${fixedExecutionId}-retry
 `)
 
   // Store for potential retry in same session
@@ -575,15 +575,15 @@ RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/02-review-code-q
 # - Report findings directly
 
 # Method 2: Gemini Review (recommended)
-ccw cli exec "[Shared Prompt Template with artifacts]" --tool gemini --mode analysis
+ccw cli -p "[Shared Prompt Template with artifacts]" --tool gemini --mode analysis
 # CONTEXT includes: @**/* @${plan.json} [@${exploration.json}]
 
 # Method 3: Qwen Review (alternative)
-ccw cli exec "[Shared Prompt Template with artifacts]" --tool qwen --mode analysis
+ccw cli -p "[Shared Prompt Template with artifacts]" --tool qwen --mode analysis
 # Same prompt as Gemini, different execution engine
 
 # Method 4: Codex Review (autonomous)
-ccw cli exec "[Verify plan acceptance criteria at ${plan.json}]" --tool codex --mode write
+ccw cli -p "[Verify plan acceptance criteria at ${plan.json}]" --tool codex --mode write
 ```
 
 **Multi-Round Review with Fixed IDs**:
@@ -592,12 +592,12 @@ ccw cli exec "[Verify plan acceptance criteria at ${plan.json}]" --tool codex --
 const reviewId = `${sessionId}-review`
 
 // First review pass with fixed ID
-const reviewResult = Bash(`ccw cli exec "[Review prompt]" --tool gemini --mode analysis --id ${reviewId}`)
+const reviewResult = Bash(`ccw cli -p "[Review prompt]" --tool gemini --mode analysis --id ${reviewId}`)
 
 // If issues found, continue review dialog with fixed ID chain
 if (hasUnresolvedIssues(reviewResult)) {
   // Resume with follow-up questions
-  Bash(`ccw cli exec "Clarify the security concerns you mentioned" --resume ${reviewId} --tool gemini --mode analysis --id ${reviewId}-followup`)
+  Bash(`ccw cli -p "Clarify the security concerns you mentioned" --resume ${reviewId} --tool gemini --mode analysis --id ${reviewId}-followup`)
 }
 ```
 
@@ -672,7 +672,7 @@ console.log(`✓ Development index: [${category}] ${entry.title}`)
 | Empty file | File exists but no content | Error: "File is empty: {path}. Provide task description." |
 | Invalid Enhanced Task JSON | JSON missing required fields | Warning: "Missing required fields. Treating as plain text." |
 | Malformed JSON | JSON parsing fails | Treat as plain text (expected for non-JSON files) |
-| Execution failure | Agent/Codex crashes | Display error, use fixed ID `${sessionId}-${groupId}` for resume: `ccw cli exec "Continue" --resume <fixed-id> --id <fixed-id>-retry` |
+| Execution failure | Agent/Codex crashes | Display error, use fixed ID `${sessionId}-${groupId}` for resume: `ccw cli -p "Continue" --resume <fixed-id> --id <fixed-id>-retry` |
 | Execution timeout | CLI exceeded timeout | Use fixed ID for resume with extended timeout |
 | Codex unavailable | Codex not installed | Show installation instructions, offer Agent execution |
 | Fixed ID not found | Custom ID lookup failed | Check `ccw cli history`, verify date directories |
@@ -745,5 +745,5 @@ Appended to `previousExecutionResults` array for context continuity in multi-exe
 ccw cli detail ${fixedCliId}
 
 # Resume with new fixed ID for retry
-ccw cli exec "Continue from where we left off" --resume ${fixedCliId} --tool codex --mode write --id ${fixedCliId}-retry
+ccw cli -p "Continue from where we left off" --resume ${fixedCliId} --tool codex --mode write --id ${fixedCliId}-retry
 ```

.claude/commands/workflow/review.md

@@ -136,7 +136,7 @@ After bash validation, the model takes control to:
      ```
    - Use Gemini for security analysis:
      ```bash
-     ccw cli exec "
+     ccw cli -p "
      PURPOSE: Security audit of completed implementation
      TASK: Review code for security vulnerabilities, insecure patterns, auth/authz issues
      CONTEXT: @.summaries/IMPL-*.md,../.. @../../CLAUDE.md
@@ -148,7 +148,7 @@ After bash validation, the model takes control to:
    **Architecture Review** (`--type=architecture`):
    - Use Qwen for architecture analysis:
      ```bash
-     ccw cli exec "
+     ccw cli -p "
      PURPOSE: Architecture compliance review
      TASK: Evaluate adherence to architectural patterns, identify technical debt, review design decisions
      CONTEXT: @.summaries/IMPL-*.md,../.. @../../CLAUDE.md
@@ -160,7 +160,7 @@ After bash validation, the model takes control to:
    **Quality Review** (`--type=quality`):
    - Use Gemini for code quality:
      ```bash
-     ccw cli exec "
+     ccw cli -p "
      PURPOSE: Code quality and best practices review
      TASK: Assess code readability, maintainability, adherence to best practices
      CONTEXT: @.summaries/IMPL-*.md,../.. @../../CLAUDE.md
@@ -182,7 +182,7 @@ After bash validation, the model takes control to:
      done
 
      # Check implementation summaries against requirements
-     ccw cli exec "
+     ccw cli -p "
      PURPOSE: Verify all requirements and acceptance criteria are met
      TASK: Cross-check implementation summaries against original requirements
      CONTEXT: @.task/IMPL-*.json,.summaries/IMPL-*.md,../.. @../../CLAUDE.md

.claude/commands/workflow/tdd-verify.md

@@ -141,7 +141,7 @@ done
 **Gemini analysis for comprehensive TDD compliance report**
 
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Generate TDD compliance report
 TASK: Analyze TDD workflow execution and generate quality report
 CONTEXT: @{.workflow/active/{sessionId}/.task/*.json,.workflow/active/{sessionId}/.summaries/*,.workflow/active/{sessionId}/.process/tdd-cycle-report.md}

.claude/commands/workflow/tools/conflict-resolution.md

@@ -133,7 +133,7 @@ Task(subagent_type="cli-execution-agent", run_in_background=false, prompt=`
   ### 2. Execute CLI Analysis (Enhanced with Exploration + Scenario Uniqueness)
 
   Primary (Gemini):
-  ccw cli exec "
+  ccw cli -p "
   PURPOSE: Detect conflicts between plan and codebase, using exploration insights
   TASK:
   • **Review pre-identified conflict_indicators from exploration results**

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

@@ -256,7 +256,7 @@ Based on userConfig.executionMethod:
 CLI Resume Support (MANDATORY for all CLI commands):
 - Use --resume parameter to continue from previous task execution
 - Read previous task's cliExecutionId from session state
-- Format: ccw cli exec "[prompt]" --resume ${previousCliId} --tool ${tool} --mode write
+- Format: ccw cli -p "[prompt]" --resume ${previousCliId} --tool ${tool} --mode write
 
 ## EXPLORATION CONTEXT (from context-package.exploration_results)
 - Load exploration_results from context-package.json
@@ -308,10 +308,10 @@ Each task JSON MUST include:
 4. **merge_fork**: Task has multiple parents - merges all parent contexts into new conversation
 
 **Execution Command Patterns**:
-- new: `ccw cli exec "[prompt]" --tool [tool] --mode write --id [cli_execution_id]`
+- new: `ccw cli -p "[prompt]" --tool [tool] --mode write --id [cli_execution_id]`
-- resume: `ccw cli exec "[prompt]" --resume [resume_from] --tool [tool] --mode write`
+- resume: `ccw cli -p "[prompt]" --resume [resume_from] --tool [tool] --mode write`
-- fork: `ccw cli exec "[prompt]" --resume [resume_from] --id [cli_execution_id] --tool [tool] --mode write`
+- fork: `ccw cli -p "[prompt]" --resume [resume_from] --id [cli_execution_id] --tool [tool] --mode write`
-- merge_fork: `ccw cli exec "[prompt]" --resume [merge_from.join(',')] --id [cli_execution_id] --tool [tool] --mode write`
+- merge_fork: `ccw cli -p "[prompt]" --resume [merge_from.join(',')] --id [cli_execution_id] --tool [tool] --mode write`
 
 ## QUALITY STANDARDS
 Hard Constraints:

.claude/commands/workflow/tools/test-concept-enhanced.md

@@ -90,7 +90,7 @@ Template: ~/.claude/workflows/cli-templates/prompts/test/test-concept-analysis.t
 
 ## EXECUTION STEPS
 1. Execute Gemini analysis:
-   ccw cli exec "$(cat ~/.claude/workflows/cli-templates/prompts/test/test-concept-analysis.txt)" --tool gemini --mode write --cd .workflow/active/{test_session_id}/.process
+   ccw cli -p "$(cat ~/.claude/workflows/cli-templates/prompts/test/test-concept-analysis.txt)" --tool gemini --mode write --cd .workflow/active/{test_session_id}/.process
 
 2. Generate TEST_ANALYSIS_RESULTS.md:
    Synthesize gemini-test-analysis.md into standardized format for task generation

.claude/commands/workflow/ui-design/import-from-code.md

@@ -181,7 +181,7 @@ Task(subagent_type="ui-design-agent",
   - Pattern: rg → Extract values → Compare → If different → Read full context with comments → Record conflict
   - Alternative (if many files): Execute CLI analysis for comprehensive report:
     \`\`\`bash
-    ccw cli exec \"
+    ccw cli -p \"
     PURPOSE: Detect color token conflicts across all CSS/SCSS/JS files
     TASK: • Scan all files for color definitions • Identify conflicting values • Extract semantic comments
     MODE: analysis
@@ -297,7 +297,7 @@ Task(subagent_type="ui-design-agent",
   - Pattern: rg → Identify animation types → Map framework usage → Prioritize extraction targets
   - Alternative (if complex framework mix): Execute CLI analysis for comprehensive report:
     \`\`\`bash
-    ccw cli exec \"
+    ccw cli -p \"
     PURPOSE: Detect animation frameworks and patterns
     TASK: • Identify frameworks • Map animation patterns • Categorize by complexity
     MODE: analysis
@@ -377,7 +377,7 @@ Task(subagent_type="ui-design-agent",
   - Pattern: rg → Count occurrences → Classify by frequency → Prioritize universal components
   - Alternative (if large codebase): Execute CLI analysis for comprehensive categorization:
     \`\`\`bash
-    ccw cli exec \"
+    ccw cli -p \"
     PURPOSE: Classify components as universal vs specialized
     TASK: • Identify UI components • Classify reusability • Map layout systems
     MODE: analysis

.claude/skills/command-guide/SKILL.md

@@ -205,7 +205,7 @@ Comprehensive command guide for Claude Code Workflow (CCW) system covering 78 co
    - Specify required analysis depth
    - Request structured comparison/synthesis
    ```bash
-   ccw cli exec "
+   ccw cli -p "
    PURPOSE: Analyze command documentation to answer user query
    TASK: • [extracted user question with context]
    MODE: analysis

.claude/skills/command-guide/reference/agents/action-planning-agent.md

@@ -470,14 +470,14 @@ function computeCliStrategy(task, allTasks) {
   // Pattern: Gemini CLI deep analysis
   {
     "step": "gemini_analyze_[aspect]",
-    "command": "ccw cli exec 'PURPOSE: [goal]\\nTASK: [tasks]\\nMODE: analysis\\nCONTEXT: @[paths]\\nEXPECTED: [output]\\nRULES: $(cat [template]) | [constraints] | analysis=READ-ONLY' --tool gemini --mode analysis --cd [path]",
+    "command": "ccw cli -p 'PURPOSE: [goal]\\nTASK: [tasks]\\nMODE: analysis\\nCONTEXT: @[paths]\\nEXPECTED: [output]\\nRULES: $(cat [template]) | [constraints] | analysis=READ-ONLY' --tool gemini --mode analysis --cd [path]",
     "output_to": "analysis_result"
   },
 
   // Pattern: Qwen CLI analysis (fallback/alternative)
   {
     "step": "qwen_analyze_[aspect]",
-    "command": "ccw cli exec '[similar to gemini pattern]' --tool qwen --mode analysis --cd [path]",
+    "command": "ccw cli -p '[similar to gemini pattern]' --tool qwen --mode analysis --cd [path]",
     "output_to": "analysis_result"
   },
 
@@ -518,7 +518,7 @@ The examples above demonstrate **patterns**, not fixed requirements. Agent MUST:
 4. **Command Composition Patterns**:
    - **Single command**: `bash([simple_search])`
    - **Multiple commands**: `["bash([cmd1])", "bash([cmd2])"]`
-   - **CLI analysis**: `ccw cli exec '[prompt]' --tool gemini --mode analysis --cd [path]`
+   - **CLI analysis**: `ccw cli -p '[prompt]' --tool gemini --mode analysis --cd [path]`
    - **MCP integration**: `mcp__[tool]__[function]([params])`
 
 **Key Principle**: Examples show **structure patterns**, not specific implementations. Agent must create task-appropriate steps dynamically.
@@ -542,9 +542,9 @@ The `implementation_approach` supports **two execution modes** based on the pres
    - **Use for**: Large-scale features, complex refactoring, or when user explicitly requests CLI tool usage
    - **Required fields**: Same as default mode **PLUS** `command`, `resume_from` (optional)
    - **Command patterns** (with resume support):
-     - `ccw cli exec '[prompt]' --tool codex --mode write --cd [path]`
+     - `ccw cli -p '[prompt]' --tool codex --mode write --cd [path]`
-     - `ccw cli exec '[prompt]' --resume ${previousCliId} --tool codex --mode write` (resume from previous)
+     - `ccw cli -p '[prompt]' --resume ${previousCliId} --tool codex --mode write` (resume from previous)
-     - `ccw cli exec '[prompt]' --tool gemini --mode write --cd [path]` (write mode)
+     - `ccw cli -p '[prompt]' --tool gemini --mode write --cd [path]` (write mode)
    - **Resume mechanism**: When step depends on previous CLI execution, include `--resume` with previous execution ID
 
 **Semantic CLI Tool Selection**:
@@ -621,7 +621,7 @@ Agent determines CLI tool usage per-step based on user semantics and task nature
     "step": 3,
     "title": "Execute implementation using CLI tool",
     "description": "Use Codex/Gemini for complex autonomous execution",
-    "command": "ccw cli exec '[prompt]' --tool codex --mode write --cd [path]",
+    "command": "ccw cli -p '[prompt]' --tool codex --mode write --cd [path]",
     "modification_points": ["[Same as default mode]"],
     "logic_flow": ["[Same as default mode]"],
     "depends_on": [1, 2],
@@ -634,7 +634,7 @@ Agent determines CLI tool usage per-step based on user semantics and task nature
     "step": 4,
     "title": "Continue implementation with context",
     "description": "Resume from previous step with accumulated context",
-    "command": "ccw cli exec '[continuation prompt]' --resume ${step3_cli_id} --tool codex --mode write",
+    "command": "ccw cli -p '[continuation prompt]' --resume ${step3_cli_id} --tool codex --mode write",
     "resume_from": "step3_cli_id",  // Reference previous step's CLI ID
     "modification_points": ["[Continue from step 3]"],
     "logic_flow": ["[Build on previous output]"],

.claude/skills/command-guide/reference/agents/cli-execution-agent.md

@@ -148,7 +148,7 @@ discuss → multi (gemini + codex parallel)
 
 **Gemini/Qwen (Analysis)**:
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: {goal}
 TASK: {task}
 MODE: analysis
@@ -162,17 +162,17 @@ RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)
 
 **Gemini/Qwen (Write)**:
 ```bash
-ccw cli exec "..." --tool gemini --mode write --cd {dir}
+ccw cli -p "..." --tool gemini --mode write --cd {dir}
 ```
 
 **Codex (Write)**:
 ```bash
-ccw cli exec "..." --tool codex --mode write --cd {dir}
+ccw cli -p "..." --tool codex --mode write --cd {dir}
 ```
 
 **Cross-Directory** (Gemini/Qwen):
 ```bash
-ccw cli exec "CONTEXT: @**/* @../shared/**/*" --tool gemini --mode analysis --cd src/auth --includeDirs ../shared
+ccw cli -p "CONTEXT: @**/* @../shared/**/*" --tool gemini --mode analysis --cd src/auth --includeDirs ../shared
 ```
 
 **Directory Scope**:

.claude/skills/command-guide/reference/agents/cli-explore-agent.md

@@ -78,7 +78,7 @@ rg "^import .* from " -n | head -30
 ### Gemini Semantic Analysis (deep-scan, dependency-map)
 
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: {from prompt}
 TASK: {from prompt}
 MODE: analysis

.claude/skills/command-guide/reference/agents/cli-lite-planning-agent.md

@@ -78,7 +78,7 @@ Phase 4: planObject Generation
 ## CLI Command Template
 
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Generate plan for {task_description}
 TASK:
 • Analyze task/bug description and context

.claude/skills/command-guide/reference/agents/cli-planning-agent.md

@@ -107,7 +107,7 @@ Phase 3: Task JSON Generation
 
 **Template-Based Command Construction with Test Layer Awareness**:
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Analyze {test_type} test failures and generate fix strategy for iteration {iteration}
 TASK:
 • Review {failed_tests.length} {test_type} test failures: [{test_names}]
@@ -527,7 +527,7 @@ See: `.process/iteration-{iteration}-cli-output.txt`
 1. **Detect test_type**: "integration" → Apply integration-specific diagnosis
 2. **Execute CLI**:
    ```bash
-   ccw cli exec "PURPOSE: Analyze integration test failure...
+   ccw cli -p "PURPOSE: Analyze integration test failure...
    TASK: Examine component interactions, data flow, interface contracts...
    RULES: Analyze full call stack and data flow across components" --tool gemini --mode analysis
    ```

.claude/skills/command-guide/reference/agents/code-developer.md

@@ -123,7 +123,7 @@ When task JSON contains `flow_control.implementation_approach` array:
 
 **CLI Command Execution (CLI Execute Mode)**:
 When step contains `command` field with Codex CLI, execute via CCW CLI. For Codex resume:
-- First task (`depends_on: []`): `ccw cli exec "..." --tool codex --mode write --cd [path]`
+- First task (`depends_on: []`): `ccw cli -p "..." --tool codex --mode write --cd [path]`
 - Subsequent tasks (has `depends_on`): Use CCW CLI with resume context to maintain session
 
 **Test-Driven Development**:

.claude/skills/command-guide/reference/agents/doc-generator.md

@@ -63,7 +63,7 @@ The agent supports **two execution modes** based on task JSON's `meta.cli_execut
    - Agent substitutes [target_folders] into command
    - Agent executes CLI command via CCW:
    ```bash
-   ccw cli exec "
+   ccw cli -p "
    PURPOSE: Generate module documentation
    TASK: Create API.md and README.md for each module
    MODE: write
@@ -216,7 +216,7 @@ Before completion, verify:
 {
   "step": "analyze_module_structure",
   "action": "Deep analysis of module structure and API",
-  "command": "ccw cli exec \"PURPOSE: Document module comprehensively\nTASK: Extract module purpose, architecture, public API, dependencies\nMODE: analysis\nCONTEXT: @**/* System: [system_context]\nEXPECTED: Complete module analysis for documentation\nRULES: $(cat ~/.claude/workflows/cli-templates/prompts/documentation/module-documentation.txt)\" --tool gemini --mode analysis --cd src/auth",
+  "command": "ccw cli -p \"PURPOSE: Document module comprehensively\nTASK: Extract module purpose, architecture, public API, dependencies\nMODE: analysis\nCONTEXT: @**/* System: [system_context]\nEXPECTED: Complete module analysis for documentation\nRULES: $(cat ~/.claude/workflows/cli-templates/prompts/documentation/module-documentation.txt)\" --tool gemini --mode analysis --cd src/auth",
   "output_to": "module_analysis",
   "on_error": "fail"
 }

.claude/skills/command-guide/reference/commands/memory/docs.md

@@ -239,9 +239,9 @@ api_id=$((group_count + 3))
 | **CLI** | true | implementation_approach | write | --mode write | Execute CLI commands, validate output |
 
 **Command Patterns**:
-- Gemini/Qwen: `ccw cli exec "..." --tool gemini --mode analysis --cd dir`
+- Gemini/Qwen: `ccw cli -p "..." --tool gemini --mode analysis --cd dir`
-- CLI Mode: `ccw cli exec "..." --tool gemini --mode write --cd dir`
+- CLI Mode: `ccw cli -p "..." --tool gemini --mode write --cd dir`
-- Codex: `ccw cli exec "..." --tool codex --mode write --cd dir`
+- Codex: `ccw cli -p "..." --tool codex --mode write --cd dir`
 
 **Generation Process**:
 1. Read configuration values (tool, cli_execute, mode) from workflow-session.json
@@ -332,7 +332,7 @@ api_id=$((group_count + 3))
 {
   "step": 2,
   "title": "Batch generate documentation via CLI",
-  "command": "ccw cli exec 'PURPOSE: Generate module docs\\nTASK: Create documentation\\nMODE: write\\nCONTEXT: @**/* [phase2_context]\\nEXPECTED: API.md and README.md\\nRULES: Mirror structure' --tool gemini --mode write --cd ${dirs_from_group}",
+  "command": "ccw cli -p 'PURPOSE: Generate module docs\\nTASK: Create documentation\\nMODE: write\\nCONTEXT: @**/* [phase2_context]\\nEXPECTED: API.md and README.md\\nRULES: Mirror structure' --tool gemini --mode write --cd ${dirs_from_group}",
   "depends_on": [1],
   "output": "generated_docs"
 }
@@ -364,7 +364,7 @@ api_id=$((group_count + 3))
       },
       {
         "step": "analyze_project",
-        "command": "bash(ccw cli exec \"PURPOSE: Analyze project structure\\nTASK: Extract overview from modules\\nMODE: analysis\\nCONTEXT: [all_module_docs]\\nEXPECTED: Project outline\" --tool gemini --mode analysis)",
+        "command": "bash(ccw cli -p \"PURPOSE: Analyze project structure\\nTASK: Extract overview from modules\\nMODE: analysis\\nCONTEXT: [all_module_docs]\\nEXPECTED: Project outline\" --tool gemini --mode analysis)",
         "output_to": "project_outline"
       }
     ],
@@ -404,7 +404,7 @@ api_id=$((group_count + 3))
     "pre_analysis": [
       {"step": "load_existing_docs", "command": "bash(cat .workflow/docs/${project_name}/{ARCHITECTURE,EXAMPLES}.md 2>/dev/null || echo 'No existing docs')", "output_to": "existing_arch_examples"},
       {"step": "load_all_docs", "command": "bash(cat .workflow/docs/${project_name}/README.md && find .workflow/docs/${project_name} -type f -name '*.md' ! -path '*/README.md' ! -path '*/ARCHITECTURE.md' ! -path '*/EXAMPLES.md' ! -path '*/api/*' | xargs cat)", "output_to": "all_docs"},
-      {"step": "analyze_architecture", "command": "bash(ccw cli exec \"PURPOSE: Analyze system architecture\\nTASK: Synthesize architectural overview and examples\\nMODE: analysis\\nCONTEXT: [all_docs]\\nEXPECTED: Architecture + Examples outline\" --tool gemini --mode analysis)", "output_to": "arch_examples_outline"}
+      {"step": "analyze_architecture", "command": "bash(ccw cli -p \"PURPOSE: Analyze system architecture\\nTASK: Synthesize architectural overview and examples\\nMODE: analysis\\nCONTEXT: [all_docs]\\nEXPECTED: Architecture + Examples outline\" --tool gemini --mode analysis)", "output_to": "arch_examples_outline"}
     ],
     "implementation_approach": [
       {
@@ -441,7 +441,7 @@ api_id=$((group_count + 3))
     "pre_analysis": [
       {"step": "discover_api", "command": "bash(rg 'router\\.| @(Get|Post)' -g '*.{ts,js}')", "output_to": "endpoint_discovery"},
       {"step": "load_existing_api", "command": "bash(cat .workflow/docs/${project_name}/api/README.md 2>/dev/null || echo 'No existing API docs')", "output_to": "existing_api_docs"},
-      {"step": "analyze_api", "command": "bash(ccw cli exec \"PURPOSE: Document HTTP API\\nTASK: Analyze endpoints\\nMODE: analysis\\nCONTEXT: @src/api/**/* [endpoint_discovery]\\nEXPECTED: API outline\" --tool gemini --mode analysis)", "output_to": "api_outline"}
+      {"step": "analyze_api", "command": "bash(ccw cli -p \"PURPOSE: Document HTTP API\\nTASK: Analyze endpoints\\nMODE: analysis\\nCONTEXT: @src/api/**/* [endpoint_discovery]\\nEXPECTED: API outline\" --tool gemini --mode analysis)", "output_to": "api_outline"}
     ],
     "implementation_approach": [
       {

.claude/skills/command-guide/reference/commands/memory/load.md

@@ -136,7 +136,7 @@ Task(
 Execute Gemini/Qwen CLI for deep analysis (saves main thread tokens):
 
 \`\`\`bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Extract project core context for task: ${task_description}
 TASK: Analyze project architecture, tech stack, key patterns, relevant files
 MODE: analysis

.claude/skills/command-guide/reference/commands/memory/workflow-skill-memory.md

@@ -187,7 +187,7 @@ Objectives:
 
 3. Use Gemini for aggregation (optional):
    Command pattern:
-   ccw cli exec "
+   ccw cli -p "
    PURPOSE: Extract lessons and conflicts from workflow session
    TASK:
    • Analyze IMPL_PLAN and lessons from manifest
@@ -334,7 +334,7 @@ Objectives:
    - Sort sessions by date
 
 2. Use Gemini for final aggregation:
-   ccw cli exec "
+   ccw cli -p "
    PURPOSE: Aggregate lessons and conflicts from all workflow sessions
    TASK:
    • Group successes by functional domain

.claude/skills/command-guide/reference/commands/workflow/lite-execute.md

@@ -473,7 +473,7 @@ Detailed plan: ${executionContext.session.artifacts.plan}`)
   return prompt
 }
 
-ccw cli exec "${buildCLIPrompt(batch)}" --tool codex --mode write
+ccw cli -p "${buildCLIPrompt(batch)}" --tool codex --mode write
 ```
 
 **Execution with fixed IDs** (predictable ID pattern):
@@ -496,8 +496,8 @@ const previousCliId = batch.resumeFromCliId || null
 
 // Build command with fixed ID (and optional resume for continuation)
 const cli_command = previousCliId
-  ? `ccw cli exec "${buildCLIPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId} --resume ${previousCliId}`
+  ? `ccw cli -p "${buildCLIPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId} --resume ${previousCliId}`
-  : `ccw cli exec "${buildCLIPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId}`
+  : `ccw cli -p "${buildCLIPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId}`
 
 bash_result = Bash(
   command=cli_command,
@@ -519,7 +519,7 @@ if (bash_result.status === 'failed' || bash_result.status === 'timeout') {
 ⚠️ Execution incomplete. Resume available:
    Fixed ID: ${fixedExecutionId}
    Lookup: ccw cli detail ${fixedExecutionId}
-   Resume: ccw cli exec "Continue tasks" --resume ${fixedExecutionId} --tool codex --mode write --id ${fixedExecutionId}-retry
+   Resume: ccw cli -p "Continue tasks" --resume ${fixedExecutionId} --tool codex --mode write --id ${fixedExecutionId}-retry
 `)
 
   // Store for potential retry in same session
@@ -574,15 +574,15 @@ RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/02-review-code-q
 # - Report findings directly
 
 # Method 2: Gemini Review (recommended)
-ccw cli exec "[Shared Prompt Template with artifacts]" --tool gemini --mode analysis
+ccw cli -p "[Shared Prompt Template with artifacts]" --tool gemini --mode analysis
 # CONTEXT includes: @**/* @${plan.json} [@${exploration.json}]
 
 # Method 3: Qwen Review (alternative)
-ccw cli exec "[Shared Prompt Template with artifacts]" --tool qwen --mode analysis
+ccw cli -p "[Shared Prompt Template with artifacts]" --tool qwen --mode analysis
 # Same prompt as Gemini, different execution engine
 
 # Method 4: Codex Review (autonomous)
-ccw cli exec "[Verify plan acceptance criteria at ${plan.json}]" --tool codex --mode write
+ccw cli -p "[Verify plan acceptance criteria at ${plan.json}]" --tool codex --mode write
 ```
 
 **Multi-Round Review with Fixed IDs**:
@@ -591,12 +591,12 @@ ccw cli exec "[Verify plan acceptance criteria at ${plan.json}]" --tool codex --
 const reviewId = `${sessionId}-review`
 
 // First review pass with fixed ID
-const reviewResult = Bash(`ccw cli exec "[Review prompt]" --tool gemini --mode analysis --id ${reviewId}`)
+const reviewResult = Bash(`ccw cli -p "[Review prompt]" --tool gemini --mode analysis --id ${reviewId}`)
 
 // If issues found, continue review dialog with fixed ID chain
 if (hasUnresolvedIssues(reviewResult)) {
   // Resume with follow-up questions
-  Bash(`ccw cli exec "Clarify the security concerns you mentioned" --resume ${reviewId} --tool gemini --mode analysis --id ${reviewId}-followup`)
+  Bash(`ccw cli -p "Clarify the security concerns you mentioned" --resume ${reviewId} --tool gemini --mode analysis --id ${reviewId}-followup`)
 }
 ```
 
@@ -671,7 +671,7 @@ console.log(`✓ Development index: [${category}] ${entry.title}`)
 | Empty file | File exists but no content | Error: "File is empty: {path}. Provide task description." |
 | Invalid Enhanced Task JSON | JSON missing required fields | Warning: "Missing required fields. Treating as plain text." |
 | Malformed JSON | JSON parsing fails | Treat as plain text (expected for non-JSON files) |
-| Execution failure | Agent/Codex crashes | Display error, use fixed ID `${sessionId}-${groupId}` for resume: `ccw cli exec "Continue" --resume <fixed-id> --id <fixed-id>-retry` |
+| Execution failure | Agent/Codex crashes | Display error, use fixed ID `${sessionId}-${groupId}` for resume: `ccw cli -p "Continue" --resume <fixed-id> --id <fixed-id>-retry` |
 | Execution timeout | CLI exceeded timeout | Use fixed ID for resume with extended timeout |
 | Codex unavailable | Codex not installed | Show installation instructions, offer Agent execution |
 | Fixed ID not found | Custom ID lookup failed | Check `ccw cli history`, verify date directories |
@@ -744,5 +744,5 @@ Appended to `previousExecutionResults` array for context continuity in multi-exe
 ccw cli detail ${fixedCliId}
 
 # Resume with new fixed ID for retry
-ccw cli exec "Continue from where we left off" --resume ${fixedCliId} --tool codex --mode write --id ${fixedCliId}-retry
+ccw cli -p "Continue from where we left off" --resume ${fixedCliId} --tool codex --mode write --id ${fixedCliId}-retry
 ```

.claude/skills/command-guide/reference/commands/workflow/review.md

@@ -137,7 +137,7 @@ After bash validation, the model takes control to:
      ```
    - Use Gemini for security analysis:
      ```bash
-     ccw cli exec "
+     ccw cli -p "
      PURPOSE: Security audit of completed implementation
      TASK: Review code for security vulnerabilities, insecure patterns, auth/authz issues
      CONTEXT: @.summaries/IMPL-*.md,../.. @../../CLAUDE.md
@@ -149,7 +149,7 @@ After bash validation, the model takes control to:
    **Architecture Review** (`--type=architecture`):
    - Use Qwen for architecture analysis:
      ```bash
-     ccw cli exec "
+     ccw cli -p "
      PURPOSE: Architecture compliance review
      TASK: Evaluate adherence to architectural patterns, identify technical debt, review design decisions
      CONTEXT: @.summaries/IMPL-*.md,../.. @../../CLAUDE.md
@@ -161,7 +161,7 @@ After bash validation, the model takes control to:
    **Quality Review** (`--type=quality`):
    - Use Gemini for code quality:
      ```bash
-     ccw cli exec "
+     ccw cli -p "
      PURPOSE: Code quality and best practices review
      TASK: Assess code readability, maintainability, adherence to best practices
      CONTEXT: @.summaries/IMPL-*.md,../.. @../../CLAUDE.md
@@ -183,7 +183,7 @@ After bash validation, the model takes control to:
      done
 
      # Check implementation summaries against requirements
-     ccw cli exec "
+     ccw cli -p "
      PURPOSE: Verify all requirements and acceptance criteria are met
      TASK: Cross-check implementation summaries against original requirements
      CONTEXT: @.task/IMPL-*.json,.summaries/IMPL-*.md,../.. @../../CLAUDE.md

.claude/skills/command-guide/reference/commands/workflow/tdd-verify.md

@@ -141,7 +141,7 @@ done
 **Gemini analysis for comprehensive TDD compliance report**
 
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Generate TDD compliance report
 TASK: Analyze TDD workflow execution and generate quality report
 CONTEXT: @{.workflow/active/{sessionId}/.task/*.json,.workflow/active/{sessionId}/.summaries/*,.workflow/active/{sessionId}/.process/tdd-cycle-report.md}

.claude/skills/command-guide/reference/commands/workflow/tools/conflict-resolution.md

@@ -133,7 +133,7 @@ Task(subagent_type="cli-execution-agent", prompt=`
   ### 2. Execute CLI Analysis (Enhanced with Exploration + Scenario Uniqueness)
 
   Primary (Gemini):
-  ccw cli exec "
+  ccw cli -p "
   PURPOSE: Detect conflicts between plan and codebase, using exploration insights
   TASK:
   • **Review pre-identified conflict_indicators from exploration results**

.claude/skills/command-guide/reference/commands/workflow/tools/task-generate-agent.md

@@ -255,7 +255,7 @@ Based on userConfig.executionMethod:
 CLI Resume Support (MANDATORY for all CLI commands):
 - Use --resume parameter to continue from previous task execution
 - Read previous task's cliExecutionId from session state
-- Format: ccw cli exec "[prompt]" --resume ${previousCliId} --tool ${tool} --mode write
+- Format: ccw cli -p "[prompt]" --resume ${previousCliId} --tool ${tool} --mode write
 
 ## EXPLORATION CONTEXT (from context-package.exploration_results)
 - Load exploration_results from context-package.json
@@ -307,10 +307,10 @@ Each task JSON MUST include:
 4. **merge_fork**: Task has multiple parents - merges all parent contexts into new conversation
 
 **Execution Command Patterns**:
-- new: `ccw cli exec "[prompt]" --tool [tool] --mode write --id [cli_execution_id]`
+- new: `ccw cli -p "[prompt]" --tool [tool] --mode write --id [cli_execution_id]`
-- resume: `ccw cli exec "[prompt]" --resume [resume_from] --tool [tool] --mode write`
+- resume: `ccw cli -p "[prompt]" --resume [resume_from] --tool [tool] --mode write`
-- fork: `ccw cli exec "[prompt]" --resume [resume_from] --id [cli_execution_id] --tool [tool] --mode write`
+- fork: `ccw cli -p "[prompt]" --resume [resume_from] --id [cli_execution_id] --tool [tool] --mode write`
-- merge_fork: `ccw cli exec "[prompt]" --resume [merge_from.join(',')] --id [cli_execution_id] --tool [tool] --mode write`
+- merge_fork: `ccw cli -p "[prompt]" --resume [merge_from.join(',')] --id [cli_execution_id] --tool [tool] --mode write`
 
 ## QUALITY STANDARDS
 Hard Constraints:

.claude/skills/command-guide/reference/commands/workflow/tools/test-concept-enhanced.md

@@ -89,7 +89,7 @@ Template: ~/.claude/workflows/cli-templates/prompts/test/test-concept-analysis.t
 
 ## EXECUTION STEPS
 1. Execute Gemini analysis:
-   ccw cli exec "$(cat ~/.claude/workflows/cli-templates/prompts/test/test-concept-analysis.txt)" --tool gemini --mode write --cd .workflow/active/{test_session_id}/.process
+   ccw cli -p "$(cat ~/.claude/workflows/cli-templates/prompts/test/test-concept-analysis.txt)" --tool gemini --mode write --cd .workflow/active/{test_session_id}/.process
 
 2. Generate TEST_ANALYSIS_RESULTS.md:
    Synthesize gemini-test-analysis.md into standardized format for task generation

.claude/skills/command-guide/reference/commands/workflow/ui-design/import-from-code.md

@@ -180,7 +180,7 @@ Task(subagent_type="ui-design-agent",
   - Pattern: rg → Extract values → Compare → If different → Read full context with comments → Record conflict
   - Alternative (if many files): Execute CLI analysis for comprehensive report:
     \`\`\`bash
-    ccw cli exec \"
+    ccw cli -p \"
     PURPOSE: Detect color token conflicts across all CSS/SCSS/JS files
     TASK: • Scan all files for color definitions • Identify conflicting values • Extract semantic comments
     MODE: analysis
@@ -295,7 +295,7 @@ Task(subagent_type="ui-design-agent",
   - Pattern: rg → Identify animation types → Map framework usage → Prioritize extraction targets
   - Alternative (if complex framework mix): Execute CLI analysis for comprehensive report:
     \`\`\`bash
-    ccw cli exec \"
+    ccw cli -p \"
     PURPOSE: Detect animation frameworks and patterns
     TASK: • Identify frameworks • Map animation patterns • Categorize by complexity
     MODE: analysis
@@ -374,7 +374,7 @@ Task(subagent_type="ui-design-agent",
   - Pattern: rg → Count occurrences → Classify by frequency → Prioritize universal components
   - Alternative (if large codebase): Execute CLI analysis for comprehensive categorization:
     \`\`\`bash
-    ccw cli exec \"
+    ccw cli -p \"
     PURPOSE: Classify components as universal vs specialized
     TASK: • Identify UI components • Classify reusability • Map layout systems
     MODE: analysis

.claude/workflows/cli-templates/prompts/workflow/skill-conflict-patterns.txt

@@ -70,7 +70,7 @@ Document recurring conflict patterns across workflow sessions with resolutions.
 
 **Command Pattern**:
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Identify conflict patterns from workflow sessions
 TASK: • Extract conflicts from IMPL_PLAN and lessons • Group by type (architecture/dependencies/testing/performance) • Identify recurring patterns (same conflict in different sessions) • Link resolutions to specific sessions
 MODE: analysis

.claude/workflows/cli-templates/prompts/workflow/skill-lessons-learned.txt

@@ -66,7 +66,7 @@ Aggregate lessons learned from workflow sessions, categorized by functional doma
 
 **Command Pattern**:
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Aggregate workflow lessons from session data
 TASK: • Group successes by functional domain • Categorize challenges by severity (HIGH/MEDIUM/LOW) • Identify watch patterns with frequency >= 2 • Mark CRITICAL patterns (3+ sessions)
 MODE: analysis

.claude/workflows/cli-tools-usage.md

@@ -62,7 +62,7 @@ RULES: $(cat ~/.claude/workflows/cli-templates/protocols/[mode]-protocol.md) $(c
 ## Essential Command Structure
 
 ```bash
-ccw cli exec "<PROMPT>" --tool <gemini|qwen|codex> --mode <analysis|write>
+ccw cli -p "<PROMPT>" --tool <gemini|qwen|codex> --mode <analysis|write>
 ```
 
 **⚠️ CRITICAL**: `--mode` parameter is **MANDATORY** for all CLI executions. No defaults are assumed.
@@ -70,7 +70,7 @@ ccw cli exec "<PROMPT>" --tool <gemini|qwen|codex> --mode <analysis|write>
 ### Core Principles
 
 - **Use tools early and often** - Tools are faster and more thorough
-- **Unified CLI** - Always use `ccw cli exec` for consistent parameter handling
+- **Unified CLI** - Always use `ccw cli -p` for consistent parameter handling
 - **Mode is MANDATORY** - ALWAYS explicitly specify `--mode analysis|write` (no implicit defaults)
 - **One template required** - ALWAYS reference exactly ONE template in RULES (use universal fallback if no specific match)
 - **Write protection** - Require EXPLICIT `--mode write` for file operations
@@ -131,7 +131,7 @@ RULES: $(cat ~/.claude/workflows/cli-templates/protocols/write-protocol.md) $(ca
 
 ### Gemini & Qwen
 
-**Via CCW**: `ccw cli exec "<prompt>" --tool gemini --mode analysis` or `--tool qwen --mode analysis`
+**Via CCW**: `ccw cli -p "<prompt>" --tool gemini --mode analysis` or `--tool qwen --mode analysis`
 
 **Characteristics**:
 - Large context window, pattern recognition
@@ -147,7 +147,7 @@ RULES: $(cat ~/.claude/workflows/cli-templates/protocols/write-protocol.md) $(ca
 
 ### Codex
 
-**Via CCW**: `ccw cli exec "<prompt>" --tool codex --mode write`
+**Via CCW**: `ccw cli -p "<prompt>" --tool codex --mode write`
 
 **Characteristics**:
 - Autonomous development, mathematical reasoning
@@ -161,8 +161,8 @@ RULES: $(cat ~/.claude/workflows/cli-templates/protocols/write-protocol.md) $(ca
 **Resume via `--resume` parameter**:
 
 ```bash
-ccw cli exec "Continue analyzing" --tool gemini --mode analysis --resume              # Resume last session
+ccw cli -p "Continue analyzing" --tool gemini --mode analysis --resume              # Resume last session
-ccw cli exec "Fix issues found" --tool codex --mode write --resume <id>           # Resume specific session
+ccw cli -p "Fix issues found" --tool codex --mode write --resume <id>           # Resume specific session
 ```
 
 - **`--resume` (empty)**: Resume most recent session
@@ -264,7 +264,7 @@ rg "export.*Component" --files-with-matches --type ts
 CONTEXT: @components/Auth.tsx @types/auth.d.ts | Memory: Previous type refactoring
 
 # Step 3: Execute CLI
-ccw cli exec "..." --tool gemini --mode analysis --cd src
+ccw cli -p "..." --tool gemini --mode analysis --cd src
 ```
 
 ### RULES Configuration
@@ -284,13 +284,13 @@ ccw cli exec "..." --tool gemini --mode analysis --cd src
 **Critical**: Use double quotes `"..."` around the entire prompt to enable `$(cat ...)` expansion:
 ```bash
 # ✓ CORRECT - double quotes allow shell expansion
-ccw cli exec "RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) ..." --tool gemini
+ccw cli -p "RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) ..." --tool gemini
 
 # ✗ WRONG - single quotes prevent expansion
-ccw cli exec 'RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) ...' --tool gemini
+ccw cli -p 'RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) ...' --tool gemini
 
 # ✗ WRONG - escaped $ prevents expansion
-ccw cli exec "RULES: \$(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) ..." --tool gemini
+ccw cli -p "RULES: \$(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) ..." --tool gemini
 ```
 
 **Examples**:
@@ -397,10 +397,10 @@ When using `--cd`:
 
 ```bash
 # Single directory
-ccw cli exec "CONTEXT: @**/* @../shared/**/*" --tool gemini --mode analysis --cd src/auth --includeDirs ../shared
+ccw cli -p "CONTEXT: @**/* @../shared/**/*" --tool gemini --mode analysis --cd src/auth --includeDirs ../shared
 
 # Multiple directories
-ccw cli exec "..." --tool gemini --mode analysis --cd src/auth --includeDirs ../shared,../types,../utils
+ccw cli -p "..." --tool gemini --mode analysis --cd src/auth --includeDirs ../shared,../types,../utils
 ```
 
 **Rule**: If CONTEXT contains `@../dir/**/*`, MUST include `--includeDirs ../dir`
@@ -433,7 +433,7 @@ CCW automatically maps to tool-specific syntax:
 
 **Analysis Task** (Security Audit):
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Identify OWASP Top 10 vulnerabilities in authentication module to pass security audit; success = all critical/high issues documented with remediation
 TASK: • Scan for injection flaws (SQL, command, LDAP) • Check authentication bypass vectors • Evaluate session management • Assess sensitive data exposure
 MODE: analysis
@@ -445,7 +445,7 @@ RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) $
 
 **Implementation Task** (New Feature):
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Implement rate limiting for API endpoints to prevent abuse; must be configurable per-endpoint; backward compatible with existing clients
 TASK: • Create rate limiter middleware with sliding window • Implement per-route configuration • Add Redis backend for distributed state • Include bypass for internal services
 MODE: write
@@ -457,7 +457,7 @@ RULES: $(cat ~/.claude/workflows/cli-templates/protocols/write-protocol.md) $(ca
 
 **Bug Fix Task**:
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Fix memory leak in WebSocket connection handler causing server OOM after 24h; root cause must be identified before any fix
 TASK: • Trace connection lifecycle from open to close • Identify event listener accumulation • Check cleanup on disconnect • Verify garbage collection eligibility
 MODE: analysis
@@ -469,7 +469,7 @@ RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) $
 
 **Refactoring Task**:
 ```bash
-ccw cli exec "
+ccw cli -p "
 PURPOSE: Refactor payment processing to use strategy pattern for multi-gateway support; no functional changes; all existing tests must pass
 TASK: • Extract gateway interface from current implementation • Create strategy classes for Stripe, PayPal • Implement factory for gateway selection • Migrate existing code to use strategies
 MODE: write
@@ -501,8 +501,8 @@ RULES: $(cat ~/.claude/workflows/cli-templates/protocols/write-protocol.md) $(ca
 **Codex Multiplier**: 3x allocated time (minimum 15min / 900000ms)
 
 ```bash
-ccw cli exec "<prompt>" --tool gemini --mode analysis --timeout 600000   # 10 min
+ccw cli -p "<prompt>" --tool gemini --mode analysis --timeout 600000   # 10 min
-ccw cli exec "<prompt>" --tool codex --mode write --timeout 1800000   # 30 min
+ccw cli -p "<prompt>" --tool codex --mode write --timeout 1800000   # 30 min
 ```
 
 ### Permission Framework
@@ -530,10 +530,10 @@ ccw cli exec "<prompt>" --tool codex --mode write --timeout 1800000   # 30 min
 
 ### Workflow Integration
 
-- **Understanding**: `ccw cli exec "<prompt>" --tool gemini --mode analysis`
+- **Understanding**: `ccw cli -p "<prompt>" --tool gemini --mode analysis`
-- **Architecture**: `ccw cli exec "<prompt>" --tool gemini --mode analysis`
+- **Architecture**: `ccw cli -p "<prompt>" --tool gemini --mode analysis`
-- **Implementation**: `ccw cli exec "<prompt>" --tool codex --mode write`
+- **Implementation**: `ccw cli -p "<prompt>" --tool codex --mode write`
-- **Quality**: `ccw cli exec "<prompt>" --tool codex --mode write`
+- **Quality**: `ccw cli -p "<prompt>" --tool codex --mode write`
 
 ### Planning Checklist
 

ccw/src/cli.ts

@@ -153,6 +153,8 @@ export function run(argv: string[]): void {
   program
     .command('cli [subcommand] [args...]')
     .description('Unified CLI tool executor (gemini/qwen/codex/claude)')
+    .option('-p, --prompt <prompt>', 'Prompt text (alternative to positional argument)')
+    .option('-f, --file <file>', 'Read prompt from file (best for multi-line prompts)')
     .option('--tool <tool>', 'CLI tool to use', 'gemini')
     .option('--mode <mode>', 'Execution mode: analysis, write, auto', 'analysis')
     .option('--model <model>', 'Model override')

ccw/src/commands/cli.ts

@@ -58,6 +58,8 @@ function notifyDashboard(data: Record<string, unknown>): void {
 }
 
 interface CliExecOptions {
+  prompt?: string; // Prompt via --prompt/-p option (preferred for multi-line)
+  file?: string; // Read prompt from file
   tool?: string;
   mode?: string;
   model?: string;
@@ -269,6 +271,83 @@ function showStorageHelp(): void {
   console.log();
 }
 
+/**
+ * Test endpoint for debugging multi-line prompt parsing
+ * Shows exactly how Commander.js parsed the arguments
+ */
+function testParseAction(args: string[], options: CliExecOptions): void {
+  console.log(chalk.bold.cyan('\n  ═══════════════════════════════════════════════'));
+  console.log(chalk.bold.cyan('  │       CLI PARSE TEST ENDPOINT              │'));
+  console.log(chalk.bold.cyan('  ═══════════════════════════════════════════════\n'));
+
+  // Show args array parsing
+  console.log(chalk.bold.yellow('📦 Positional Arguments (args[]):'));
+  console.log(chalk.gray('   Length: ') + chalk.white(args.length));
+  if (args.length === 0) {
+    console.log(chalk.gray('   (empty)'));
+  } else {
+    args.forEach((arg, i) => {
+      console.log(chalk.gray(`   [${i}]: `) + chalk.green(`"${arg}"`));
+      // Show if multiline
+      if (arg.includes('\n')) {
+        console.log(chalk.yellow(`        ↳ Contains ${arg.split('\n').length} lines`));
+      }
+    });
+  }
+
+  console.log();
+
+  // Show options parsing
+  console.log(chalk.bold.yellow('⚙️  Options:'));
+  const optionEntries = Object.entries(options).filter(([_, v]) => v !== undefined);
+  if (optionEntries.length === 0) {
+    console.log(chalk.gray('   (none)'));
+  } else {
+    optionEntries.forEach(([key, value]) => {
+      const displayValue = typeof value === 'string' && value.includes('\n')
+        ? `"${value.substring(0, 50)}..." (${value.split('\n').length} lines)`
+        : JSON.stringify(value);
+      console.log(chalk.gray(`   --${key}: `) + chalk.cyan(displayValue));
+    });
+  }
+
+  console.log();
+
+  // Show what would be used as prompt
+  console.log(chalk.bold.yellow('🎯 Final Prompt Resolution:'));
+  const { prompt: optionPrompt, file } = options;
+
+  if (file) {
+    console.log(chalk.gray('   Source: ') + chalk.magenta('--file/-f option'));
+    console.log(chalk.gray('   File: ') + chalk.cyan(file));
+  } else if (optionPrompt) {
+    console.log(chalk.gray('   Source: ') + chalk.magenta('--prompt/-p option'));
+    console.log(chalk.gray('   Value: ') + chalk.green(`"${optionPrompt.substring(0, 100)}${optionPrompt.length > 100 ? '...' : ''}"`));
+    if (optionPrompt.includes('\n')) {
+      console.log(chalk.yellow(`   ↳ Multiline: ${optionPrompt.split('\n').length} lines`));
+    }
+  } else if (args[0]) {
+    console.log(chalk.gray('   Source: ') + chalk.magenta('positional argument (args[0])'));
+    console.log(chalk.gray('   Value: ') + chalk.green(`"${args[0].substring(0, 100)}${args[0].length > 100 ? '...' : ''}"`));
+    if (args[0].includes('\n')) {
+      console.log(chalk.yellow(`   ↳ Multiline: ${args[0].split('\n').length} lines`));
+    }
+  } else {
+    console.log(chalk.red('   No prompt found!'));
+  }
+
+  console.log();
+
+  // Show raw debug info
+  console.log(chalk.bold.yellow('🔍 Raw Debug Info:'));
+  console.log(chalk.gray('   process.argv:'));
+  process.argv.forEach((arg, i) => {
+    console.log(chalk.gray(`     [${i}]: `) + chalk.dim(arg.length > 60 ? arg.substring(0, 60) + '...' : arg));
+  });
+
+  console.log(chalk.bold.cyan('\n  ═══════════════════════════════════════════════\n'));
+}
+
 /**
  * Show CLI tool status
  */
@@ -295,14 +374,42 @@ async function statusAction(): Promise<void> {
  * @param {string} prompt - Prompt to execute
  * @param {Object} options - CLI options
  */
-async function execAction(prompt: string | undefined, options: CliExecOptions): Promise<void> {
+async function execAction(positionalPrompt: string | undefined, options: CliExecOptions): Promise<void> {
-  if (!prompt) {
+  const { prompt: optionPrompt, file, tool = 'gemini', mode = 'analysis', model, cd, includeDirs, timeout, noStream, resume, id, noNative } = options;
+
+  // Priority: 1. --file, 2. --prompt/-p option, 3. positional argument
+  let finalPrompt: string | undefined;
+
+  if (file) {
+    // Read from file
+    const { readFileSync, existsSync } = await import('fs');
+    const { resolve } = await import('path');
+    const filePath = resolve(file);
+    if (!existsSync(filePath)) {
+      console.error(chalk.red(`Error: File not found: ${filePath}`));
+      process.exit(1);
+    }
+    finalPrompt = readFileSync(filePath, 'utf8').trim();
+    if (!finalPrompt) {
+      console.error(chalk.red('Error: File is empty'));
+      process.exit(1);
+    }
+  } else if (optionPrompt) {
+    // Use --prompt/-p option (preferred for multi-line)
+    finalPrompt = optionPrompt;
+  } else {
+    // Fall back to positional argument
+    finalPrompt = positionalPrompt;
+  }
+
+  if (!finalPrompt) {
     console.error(chalk.red('Error: Prompt is required'));
-    console.error(chalk.gray('Usage: ccw cli exec "<prompt>" --tool gemini'));
+    console.error(chalk.gray('Usage: ccw cli -p "<prompt>" --tool gemini'));
+    console.error(chalk.gray('   or: ccw cli -f prompt.txt --tool codex'));
     process.exit(1);
   }
 
-  const { tool = 'gemini', mode = 'analysis', model, cd, includeDirs, timeout, noStream, resume, id, noNative } = options;
+  const prompt_to_use = finalPrompt;
 
   // Parse resume IDs for merge scenario
   const resumeIds = resume && typeof resume === 'string' ? resume.split(',').map(s => s.trim()).filter(Boolean) : [];
@@ -333,7 +440,7 @@ async function execAction(prompt: string | undefined, options: CliExecOptions):
     event: 'started',
     tool,
     mode,
-    prompt_preview: prompt.substring(0, 100) + (prompt.length > 100 ? '...' : ''),
+    prompt_preview: prompt_to_use.substring(0, 100) + (prompt_to_use.length > 100 ? '...' : ''),
     custom_id: id || null
   });
 
@@ -345,7 +452,7 @@ async function execAction(prompt: string | undefined, options: CliExecOptions):
   try {
     const result = await cliExecutorTool.execute({
       tool,
-      prompt,
+      prompt: prompt_to_use,
       mode,
       model,
       cd,
@@ -398,7 +505,7 @@ async function execAction(prompt: string | undefined, options: CliExecOptions):
         console.error(chalk.red(result.stderr));
       }
 
-      // Notify dashboard: execution failed
+      // Notify dashboard: execution failccw cli -p
       notifyDashboard({
         event: 'completed',
         tool,
@@ -535,7 +642,7 @@ function getTimeAgo(date: Date): string {
   return date.toLocaleDateString();
 }
 
-/**
+/**ccw cli -p
  * CLI command entry point
  * @param {string} subcommand - Subcommand (status, exec, history, detail)
  * @param {string[]} args - Arguments array
@@ -553,10 +660,6 @@ export async function cliCommand(
       await statusAction();
       break;
 
-    case 'exec':
-      await execAction(argsArray[0], options as CliExecOptions);
-      break;
-
     case 'history':
       await historyAction(options as HistoryOptions);
       break;
@@ -569,42 +672,62 @@ export async function cliCommand(
       await storageAction(argsArray[0], options as unknown as StorageOptions);
       break;
 
-    default:
+    case 'test-parse':
-      console.log(chalk.bold.cyan('\n  CCW CLI Tool Executor\n'));
+      // Test endpoint to debug multi-line prompt parsing
-      console.log('  Unified interface for Gemini, Qwen, and Codex CLI tools.\n');
+      testParseAction(argsArray, options as CliExecOptions);
-      console.log('  Subcommands:');
+      break;
-      console.log(chalk.gray('    status              Check CLI tools availability'));
+
-      console.log(chalk.gray('    storage [cmd]       Manage CCW storage (info/clean/config)'));
+    default: {
-      console.log(chalk.gray('    exec <prompt>       Execute a CLI tool'));
+      const execOptions = options as CliExecOptions;
-      console.log(chalk.gray('    history             Show execution history'));
+      // Auto-exec if: has -p/--prompt, has --stdin, has --resume, or subcommand looks like a prompt
-      console.log(chalk.gray('    detail <id>         Show execution detail'));
+      const hasPromptOption = !!execOptions.prompt;
-      console.log();
+      const hasStdin = !!execOptions.stdin;
-      console.log('  Exec Options:');
+      const hasResume = execOptions.resume !== undefined;
-      console.log(chalk.gray('    --tool <tool>       Tool to use: gemini, qwen, codex (default: gemini)'));
+      const subcommandIsPrompt = subcommand && !subcommand.startsWith('-');
-      console.log(chalk.gray('    --mode <mode>       Mode: analysis, write, auto (default: analysis)'));
+
-      console.log(chalk.gray('    --model <model>     Model override'));
+      if (hasPromptOption || hasStdin || hasResume || subcommandIsPrompt) {
-      console.log(chalk.gray('    --cd <path>         Working directory'));
+        // Treat as exec: use subcommand as positional prompt if no -p option
-      console.log(chalk.gray('    --includeDirs <dirs>  Additional directories (comma-separated)'));
+        const positionalPrompt = subcommandIsPrompt ? subcommand : undefined;
-      console.log(chalk.gray('                        → gemini/qwen: --include-directories'));
+        await execAction(positionalPrompt, execOptions);
-      console.log(chalk.gray('                        → codex: --add-dir'));
+      } else {
-      console.log(chalk.gray('    --timeout <ms>      Timeout in milliseconds (default: 300000)'));
+        // Show help
-      console.log(chalk.gray('    --no-stream         Disable streaming output'));
+        console.log(chalk.bold.cyan('\n  CCW CLI Tool Executor\n'));
-      console.log(chalk.gray('    --resume [id]       Resume previous session (empty=last, or execution ID)'));
+        console.log('  Unified interface for Gemini, Qwen, and Codex CLI tools.\n');
-      console.log(chalk.gray('    --id <id>           Custom execution ID (e.g., IMPL-001-step1)'));
+        console.log('  Usage:');
-      console.log();
+        console.log(chalk.gray('    ccw cli -p "<prompt>" --tool <tool>     Direct execution (recommended)'));
-      console.log('  History Options:');
+        console.log(chalk.gray('    ccw cli "<prompt>" --tool <tool>        Shorthand'));
-      console.log(chalk.gray('    --limit <n>         Number of results (default: 20)'));
+        console.log(chalk.gray('    ccw cli exec "<prompt>" --tool <tool>   Explicit exec'));
-      console.log(chalk.gray('    --tool <tool>       Filter by tool'));
+        console.log();
-      console.log(chalk.gray('    --status <status>   Filter by status'));
+        console.log('  Subcommands:');
-      console.log();
+        console.log(chalk.gray('    status              Check CLI tools availability'));
-      console.log('  Examples:');
+        console.log(chalk.gray('    storage [cmd]       Manage CCW storage (info/clean/config)'));
-      console.log(chalk.gray('    ccw cli status'));
+        console.log(chalk.gray('    exec <prompt>       Execute a CLI tool (optional, default behavior)'));
-      console.log(chalk.gray('    ccw cli exec "Analyze the auth module" --tool gemini'));
+        console.log(chalk.gray('    history             Show execution history'));
-      console.log(chalk.gray('    ccw cli exec "Analyze with context" --tool gemini --includeDirs ../shared,../types'));
+        console.log(chalk.gray('    detail <id>         Show execution detail'));
-      console.log(chalk.gray('    ccw cli exec "Implement feature" --tool codex --mode auto --includeDirs ./lib'));
+        console.log(chalk.gray('    test-parse [args]   Debug CLI argument parsing'));
-      console.log(chalk.gray('    ccw cli exec "Continue analysis" --resume               # Resume last session'));
+        console.log();
-      console.log(chalk.gray('    ccw cli exec "Continue..." --resume <id> --tool gemini  # Resume specific session'));
+        console.log('  Exec Options:');
-      console.log(chalk.gray('    ccw cli history --tool gemini --limit 10'));
+        console.log(chalk.gray('    -p, --prompt <text> Prompt text (preferred for multi-line)'));
-      console.log();
+        console.log(chalk.gray('    -f, --file <file>   Read prompt from file'));
+        console.log(chalk.gray('    --stdin             Read prompt from stdin'));
+        console.log(chalk.gray('    --tool <tool>       Tool to use: gemini, qwen, codex (default: gemini)'));
+        console.log(chalk.gray('    --mode <mode>       Mode: analysis, write, auto (default: analysis)'));
+        console.log(chalk.gray('    --model <model>     Model override'));
+        console.log(chalk.gray('    --cd <path>         Working directory'));
+        console.log(chalk.gray('    --includeDirs <dirs>  Additional directories (comma-separated)'));
+        console.log(chalk.gray('    ccw cli -ps>      Timeout in milliseconds (default: 300000)'));
+        console.log(chalk.gray('    --no-stream         Disable streaming output'));
+        console.log(chalk.gray('    --resume [id]       Resume previous session'));
+        console.log(chalk.gray('    --id <id>           Custom execution ID'));
+        console.log();
+        console.log('  Examples:');
+        console.log(chalk.gray('    ccw cli -p "Analyze auth module" --tool gemini'));
+        console.log(chalk.gray('    ccw cli "Simple prompt" --tool codex --mode write'));
+        console.log(chalk.gray('    ccw cli -p "$(cat prompt.txt)" --tool gemini'));
+        console.log(chalk.gray('    ccw cli --resume --tool gemini'));
+        console.log(chalk.gray('    ccw cli history --tool gemini --limit 10'));
+        console.log();
+      }
+    }
   }
 }

ccw/src/core/server.ts

@@ -68,7 +68,8 @@ const MODULE_CSS_FILES = [
   '13-claude-manager.css',
   '14-graph-explorer.css',
   '15-mcp-manager.css',
-  '16-help.css'
+  '16-help.css',
+  '17-core-memory.css'
 ];
 
 // Modular JS files in dependency order
@@ -82,41 +83,45 @@ const MODULE_FILES = [
   'components/modals.js',
   'components/navigation.js',
   'components/sidebar.js',
+  'components/tabs-context.js',
+  'components/tabs-other.js',
+  'components/task-drawer-core.js',
+  'components/task-drawer-renderers.js',
+  'components/flowchart.js',
   'components/carousel.js',
   'components/notifications.js',
   'components/global-notifications.js',
-  'components/version-check.js',
+  'components/task-queue-sidebar.js',
-  'components/mcp-manager.js',
-  'components/hook-manager.js',
   'components/cli-status.js',
   'components/cli-history.js',
+  'components/mcp-manager.js',
+  'components/hook-manager.js',
+  'components/version-check.js',
   'components/storage-manager.js',
+  'components/index-manager.js',
   'components/_exp_helpers.js',
-  'components/tabs-other.js',
-  'components/tabs-context.js',
   'components/_conflict_tab.js',
   'components/_review_tab.js',
-  'components/task-drawer-core.js',
-  'components/task-drawer-renderers.js',
-  'components/task-queue-sidebar.js',
-  'components/flowchart.js',
   'views/home.js',
   'views/project-overview.js',
   'views/session-detail.js',
   'views/review-session.js',
   'views/lite-tasks.js',
   'views/fix-session.js',
+  'views/cli-manager.js',
+  'views/codexlens-manager.js',
+  'views/explorer.js',
   'views/mcp-manager.js',
   'views/hook-manager.js',
-  'views/cli-manager.js',
   'views/history.js',
-  'views/explorer.js',
+  'views/graph-explorer.js',
   'views/memory.js',
+  'views/core-memory.js',
+  'views/core-memory-graph.js',
   'views/prompt-history.js',
   'views/skills-manager.js',
   'views/rules-manager.js',
   'views/claude-manager.js',
-  'views/graph-explorer.js',
   'views/help.js',
   'main.js'
 ];

ccw/src/templates/dashboard-js/components/navigation.js

@@ -138,7 +138,11 @@ function initNavigation() {
       } else if (currentView === 'help') {
         renderHelpView();
       } else if (currentView === 'core-memory') {
-        renderCoreMemoryView();
+        if (typeof renderCoreMemoryView === 'function') {
+          renderCoreMemoryView();
+        } else {
+          console.error('renderCoreMemoryView not defined - please refresh the page');
+        }
       }
     });
   });

ccw/src/templates/dashboard-js/components/notifications.js

@@ -208,7 +208,7 @@ function handleNotification(data) {
       break;
 
     case 'cli_execution':
-      // Handle CLI command notifications (ccw cli exec)
+      // Handle CLI command notifications (ccw cli -p)
       handleCliCommandNotification(payload);
       break;
 
@@ -500,7 +500,7 @@ function handleToolExecutionNotification(payload) {
 }
 
 /**
- * Handle CLI command notifications (ccw cli exec)
+ * Handle CLI command notifications (ccw cli -p)
  * @param {Object} payload - CLI execution payload
  */
 function handleCliCommandNotification(payload) {

ccw/src/templates/dashboard-js/help-i18n.js

@@ -67,9 +67,9 @@ var helpI18n = {
     'help.workflows.brainstorm.next': '进入规划阶段',
 
     // Workflow Steps - CLI Resume
-    'help.workflows.cliResume.firstExec': 'ccw cli exec "分析..."',
+    'help.workflows.cliResume.firstExec': 'ccw cli -p "分析..."',
     'help.workflows.cliResume.saveContext': '保存会话上下文',
-    'help.workflows.cliResume.resumeCmd': 'ccw cli exec --resume',
+    'help.workflows.cliResume.resumeCmd': 'ccw cli -p --resume',
     'help.workflows.cliResume.merge': '合并历史对话',
     'help.workflows.cliResume.continue': '继续执行任务',
     'help.workflows.cliResume.splitOutput': '拆分结果存储',
@@ -188,9 +188,9 @@ var helpI18n = {
     'help.workflows.brainstorm.next': 'Enter Planning Phase',
 
     // Workflow Steps - CLI Resume
-    'help.workflows.cliResume.firstExec': 'ccw cli exec "analyze..."',
+    'help.workflows.cliResume.firstExec': 'ccw cli -p "analyze..."',
     'help.workflows.cliResume.saveContext': 'Save Session Context',
-    'help.workflows.cliResume.resumeCmd': 'ccw cli exec --resume',
+    'help.workflows.cliResume.resumeCmd': 'ccw cli -p --resume',
     'help.workflows.cliResume.merge': 'Merge Conversation History',
     'help.workflows.cliResume.continue': 'Continue Execution',
     'help.workflows.cliResume.splitOutput': 'Split & Store Results',

ccw/src/templates/dashboard-js/views/core-memory-graph.js

@@ -87,7 +87,7 @@ function renderKnowledgeGraphD3(graph) {
   }));
 
   // Create SVG with zoom support
-  graphSvg = d3.select('#knowledgeGraphContainer')
+  coreMemGraphSvg = d3.select('#knowledgeGraphContainer')
     .append('svg')
     .attr('width', width)
     .attr('height', height)
@@ -95,19 +95,19 @@ function renderKnowledgeGraphD3(graph) {
     .attr('viewBox', [0, 0, width, height]);
 
   // Create a group for zoom/pan transformations
-  graphGroup = graphSvg.append('g').attr('class', 'graph-content');
+  coreMemGraphGroup = coreMemGraphSvg.append('g').attr('class', 'graph-content');
 
   // Setup zoom behavior
-  graphZoom = d3.zoom()
+  coreMemGraphZoom = d3.zoom()
     .scaleExtent([0.1, 4])
     .on('zoom', (event) => {
-      graphGroup.attr('transform', event.transform);
+      coreMemGraphGroup.attr('transform', event.transform);
     });
 
-  graphSvg.call(graphZoom);
+  coreMemGraphSvg.call(coreMemGraphZoom);
 
   // Add arrowhead marker
-  graphSvg.append('defs').append('marker')
+  coreMemGraphSvg.append('defs').append('marker')
     .attr('id', 'arrowhead-core')
     .attr('viewBox', '-0 -5 10 10')
     .attr('refX', 20)
@@ -122,7 +122,7 @@ function renderKnowledgeGraphD3(graph) {
     .style('stroke', 'none');
 
   // Create force simulation
-  graphSimulation = d3.forceSimulation(nodes)
+  coreMemGraphSimulation = d3.forceSimulation(nodes)
     .force('link', d3.forceLink(edges).id(d => d.id).distance(100))
     .force('charge', d3.forceManyBody().strength(-300))
     .force('center', d3.forceCenter(width / 2, height / 2))
@@ -131,7 +131,7 @@ function renderKnowledgeGraphD3(graph) {
     .force('y', d3.forceY(height / 2).strength(0.05));
 
   // Draw edges
-  const link = graphGroup.append('g')
+  const link = coreMemGraphGroup.append('g')
     .attr('class', 'graph-links')
     .selectAll('line')
     .data(edges)
@@ -143,7 +143,7 @@ function renderKnowledgeGraphD3(graph) {
     .attr('marker-end', 'url(#arrowhead-core)');
 
   // Draw nodes
-  const node = graphGroup.append('g')
+  const node = coreMemGraphGroup.append('g')
     .attr('class', 'graph-nodes')
     .selectAll('g')
     .data(nodes)
@@ -183,7 +183,7 @@ function renderKnowledgeGraphD3(graph) {
     .attr('fill', '#333');
 
   // Update positions on simulation tick
-  graphSimulation.on('tick', () => {
+  coreMemGraphSimulation.on('tick', () => {
     link
       .attr('x1', d => d.source.x)
       .attr('y1', d => d.source.y)
@@ -195,7 +195,7 @@ function renderKnowledgeGraphD3(graph) {
 
   // Drag functions
   function dragstarted(event, d) {
-    if (!event.active) graphSimulation.alphaTarget(0.3).restart();
+    if (!event.active) coreMemGraphSimulation.alphaTarget(0.3).restart();
     d.fx = d.x;
     d.fy = d.y;
   }
@@ -206,7 +206,7 @@ function renderKnowledgeGraphD3(graph) {
   }
 
   function dragended(event, d) {
-    if (!event.active) graphSimulation.alphaTarget(0);
+    if (!event.active) coreMemGraphSimulation.alphaTarget(0);
     d.fx = null;
     d.fy = null;
   }

ccw/src/templates/dashboard-js/views/core-memory.js

@@ -1,15 +1,15 @@
 // Core Memory View
 // Manages strategic context entries with knowledge graph and evolution tracking
 
-// State for visualization
+// State for visualization (prefixed to avoid collision with memory.js)
-let graphSvg = null;
+var coreMemGraphSvg = null;
-let graphGroup = null;
+var coreMemGraphGroup = null;
-let graphZoom = null;
+var coreMemGraphZoom = null;
-let graphSimulation = null;
+var coreMemGraphSimulation = null;
 
 async function renderCoreMemoryView() {
   const content = document.getElementById('content');
-  hideStatsAndSearch();
+  hideStatsAndCarousel();
 
   // Fetch core memories
   const archived = false;
@@ -214,7 +214,8 @@ async function fetchCoreMemories(archived = false) {
   try {
     const response = await fetch(`/api/core-memory/memories?path=${encodeURIComponent(projectPath)}&archived=${archived}`);
     if (!response.ok) throw new Error(`HTTP ${response.status}`);
-    return await response.json();
+    const data = await response.json();
+    return data.memories || [];
   } catch (error) {
     console.error('Failed to fetch core memories:', error);
     showNotification(t('coreMemory.fetchError'), 'error');
@@ -226,7 +227,8 @@ async function fetchMemoryById(memoryId) {
   try {
     const response = await fetch(`/api/core-memory/memories/${memoryId}?path=${encodeURIComponent(projectPath)}`);
     if (!response.ok) throw new Error(`HTTP ${response.status}`);
-    return await response.json();
+    const data = await response.json();
+    return data.memory || null;
   } catch (error) {
     console.error('Failed to fetch memory:', error);
     showNotification(t('coreMemory.fetchError'), 'error');

ccw/src/templates/dashboard-js/views/mcp-manager.js

@@ -7,6 +7,7 @@ const CCW_MCP_TOOLS = [
   { name: 'write_file', desc: 'Write/create files', core: true },
   { name: 'edit_file', desc: 'Edit/replace content', core: true },
   { name: 'smart_search', desc: 'Hybrid search (regex + semantic)', core: true },
+  { name: 'core_memory', desc: 'Core memory management', core: true },
   // Optional tools
   { name: 'session_manager', desc: 'Workflow sessions', core: false },
   { name: 'generate_module_docs', desc: 'Generate docs', core: false },

ccw/src/tools/cli-config-manager.ts

@@ -11,7 +11,7 @@ import { StoragePaths, ensureStorageDir } from '../config/storage-paths.js';
 
 export interface CliToolConfig {
   enabled: boolean;
-  primaryModel: string;      // For CLI endpoint calls (ccw cli exec)
+  primaryModel: string;      // For CLI endpoint calls (ccw cli -p)
   secondaryModel: string;    // For internal calls (llm_enhancer, generate_module_docs)
 }
 

ccw/src/tools/cli-executor.ts

@@ -319,8 +319,9 @@ function buildCommand(params: {
       break;
 
     case 'codex':
-      // Codex does NOT support stdin - prompt must be passed as command line argument
+      // Codex supports stdin when using `-` as prompt argument
-      useStdin = false;
+      // Using stdin avoids Windows command line escaping issues with multi-line/special char prompts
+      useStdin = true;
       // Native resume: codex resume <uuid> [prompt] or --last
       if (nativeResume?.enabled) {
         args.push('resume');
@@ -333,8 +334,13 @@ function buildCommand(params: {
         if (dir) {
           args.push('-C', dir);
         }
+        // Permission configuration based on mode:
+        // - analysis: --full-auto (read-only sandbox, no prompts) - safer for read operations
+        // - write/auto: --dangerously-bypass-approvals-and-sandbox (full access for modifications)
         if (mode === 'write' || mode === 'auto') {
-          args.push('--skip-git-repo-check', '-s', 'danger-full-access');
+          args.push('--dangerously-bypass-approvals-and-sandbox');
+        } else {
+          args.push('--full-auto');
         }
         if (model) {
           args.push('-m', model);
@@ -345,19 +351,21 @@ function buildCommand(params: {
             args.push('--add-dir', addDir);
           }
         }
-        // Add prompt as positional argument for resume
+        // Use `-` to indicate reading prompt from stdin
-        if (prompt) {
+        args.push('-');
-          args.push(prompt);
-        }
       } else {
         // Standard exec mode
         args.push('exec');
         if (dir) {
           args.push('-C', dir);
         }
-        args.push('--full-auto');
+        // Permission configuration based on mode:
+        // - analysis: --full-auto (read-only sandbox, no prompts) - safer for read operations
+        // - write/auto: --dangerously-bypass-approvals-and-sandbox (full access for modifications)
         if (mode === 'write' || mode === 'auto') {
-          args.push('--skip-git-repo-check', '-s', 'danger-full-access');
+          args.push('--dangerously-bypass-approvals-and-sandbox');
+        } else {
+          args.push('--full-auto');
         }
         if (model) {
           args.push('-m', model);
@@ -368,10 +376,8 @@ function buildCommand(params: {
             args.push('--add-dir', addDir);
           }
         }
-        // Add prompt as positional argument (codex exec "prompt")
+        // Use `-` to indicate reading prompt from stdin (avoids Windows escaping issues)
-        if (prompt) {
+        args.push('-');
-          args.push(prompt);
-        }
       }
       break;
 
@@ -734,8 +740,8 @@ async function executeCliTool(
     }
   }
 
-  // Only pass model if explicitly provided - let CLI tools use their own defaults
+  // Use configured primary model if no explicit model provided
-  const effectiveModel = model;
+  const effectiveModel = model || getPrimaryModel(workingDir, tool);
 
   // Build command
   const { command, args, useStdin } = buildCommand({

codex-lens/_debug_output.txt

@@ -16,4 +16,4 @@ Got it. I'm ready for your first command.
 
   ✓ Completed in 16.1s
   ID: 1765691168543-gemini
-  Continue: ccw cli exec "..." --resume 1765691168543-gemini
+  Continue: ccw cli -p "..." --resume 1765691168543-gemini

codex-lens/_test_output.txt

@@ -17,6 +17,6 @@ Setup complete. I am ready for your first command.
 
   ✓ Completed in 19.6s
   ID: 1765690404300-gemini
-  Continue: ccw cli exec "..." --resume 1765690404300-gemini
+  Continue: ccw cli -p "..." --resume 1765690404300-gemini
 
 === STDERR ===

codex-lens/_test_result.txt

@@ -16,4 +16,4 @@ Setup complete. I am ready for your first command.
 
   ✓ Completed in 16.0s
   ID: 1765690668720-gemini
-  Continue: ccw cli exec "..." --resume 1765690668720-gemini
+  Continue: ccw cli -p "..." --resume 1765690668720-gemini