diff --git a/.claude/agents/cli-discuss-agent.md b/.claude/agents/cli-discuss-agent.md
index a4f6cdfd..7636ba2c 100644
--- a/.claude/agents/cli-discuss-agent.md
+++ b/.claude/agents/cli-discuss-agent.md
@@ -215,7 +215,7 @@ CONTEXT: @**/* | Memory: {ace_context_summary}
 
 EXPECTED: JSON with feasibility_score, findings, implementation_approaches, technical_concerns, code_locations
 
-RULES: $PROTO |
+CONSTRAINTS:
 - Specific file:line references
 - Quantify effort estimates
 - Concrete pros/cons
diff --git a/.claude/agents/cli-execution-agent.md b/.claude/agents/cli-execution-agent.md
index c22b4836..50401179 100644
--- a/.claude/agents/cli-execution-agent.md
+++ b/.claude/agents/cli-execution-agent.md
@@ -114,10 +114,10 @@ plan → planning/architecture-planning.txt | planning/task-breakdown.txt
 bug-fix → development/bug-diagnosis.txt
 ```
 
-**3. RULES Field**:
-- Use `--rule <template>` option to auto-load protocol + template as `$PROTO` and `$TMPL`
+**3. CONSTRAINTS Field**:
+- Use `--rule <template>` option to auto-load protocol + template (appended to prompt)
 - Template names: `category-function` format (e.g., `analysis-code-patterns`, `development-feature`)
-- NEVER escape: `\$`, `\"`, `\'` breaks variable expansion
+- NEVER escape: `\"`, `\'` breaks shell parsing
 
 **4. Structured Prompt**:
 ```bash
@@ -126,7 +126,7 @@ TASK: {specific_task_with_details}
 MODE: {analysis|write|auto}
 CONTEXT: {structured_file_references}
 EXPECTED: {clear_output_expectations}
-RULES: $PROTO $TMPL | {constraints}
+CONSTRAINTS: {constraints}
 ```
 
 ---
@@ -157,7 +157,7 @@ TASK: {task}
 MODE: analysis
 CONTEXT: @**/*
 EXPECTED: {output}
-RULES: $PROTO $TMPL
+CONSTRAINTS: {constraints}
 " --tool gemini --mode analysis --rule analysis-code-patterns --cd {dir}
 
 # Qwen fallback: Replace '--tool gemini' with '--tool qwen'
diff --git a/.claude/agents/cli-lite-planning-agent.md b/.claude/agents/cli-lite-planning-agent.md
index b8e51ca1..23d8868f 100644
--- a/.claude/agents/cli-lite-planning-agent.md
+++ b/.claude/agents/cli-lite-planning-agent.md
@@ -106,7 +106,7 @@ EXPECTED:
 ## Time Estimate
 **Total**: [time]
 
-RULES: $PROTO $TMPL |
+CONSTRAINTS:
 - Follow schema structure from {schema_path}
 - Acceptance/verification must be quantified
 - Dependencies use task IDs
diff --git a/.claude/agents/cli-planning-agent.md b/.claude/agents/cli-planning-agent.md
index 82e06064..eb93b02b 100644
--- a/.claude/agents/cli-planning-agent.md
+++ b/.claude/agents/cli-planning-agent.md
@@ -127,7 +127,7 @@ EXPECTED: Structured fix strategy with:
 - Fix approach ensuring business logic correctness (not just test passage)
 - Expected outcome and verification steps
 - Impact assessment: Will this fix potentially mask other issues?
-RULES: $PROTO $TMPL |
+CONSTRAINTS:
 - For {test_type} tests: {layer_specific_guidance}
 - Avoid 'surgical fixes' that mask underlying issues
 - Provide specific line numbers for modifications
diff --git a/.claude/agents/debug-explore-agent.md b/.claude/agents/debug-explore-agent.md
index d15ffac9..a2e4f6d9 100644
--- a/.claude/agents/debug-explore-agent.md
+++ b/.claude/agents/debug-explore-agent.md
@@ -105,7 +105,7 @@ TASK: • Analyze error pattern • Identify potential root causes • Suggest t
 MODE: analysis
 CONTEXT: @{affected_files}
 EXPECTED: Structured hypothesis list with priority ranking
-RULES: $PROTO $TMPL | Focus on testable conditions
+CONSTRAINTS: Focus on testable conditions
 " --tool gemini --mode analysis --cd {project_root}
 ```
 
@@ -213,7 +213,7 @@ EXPECTED:
 - Evidence summary
 - Root cause identification (if confirmed)
 - Next steps (if inconclusive)
-RULES: $PROTO $TMPL | Evidence-based reasoning only
+CONSTRAINTS: Evidence-based reasoning only
 " --tool gemini --mode analysis
 ```
 
@@ -271,7 +271,7 @@ TASK:
 MODE: write
 CONTEXT: @{affected_files}
 EXPECTED: Working fix that addresses root cause
-RULES: $PROTO $TMPL | Minimal changes only
+CONSTRAINTS: Minimal changes only
 " --tool codex --mode write --cd {project_root}
 ```
 
diff --git a/.claude/agents/doc-generator.md b/.claude/agents/doc-generator.md
index 840e87bf..6fe0fca0 100644
--- a/.claude/agents/doc-generator.md
+++ b/.claude/agents/doc-generator.md
@@ -70,7 +70,7 @@ The agent supports **two execution modes** based on task JSON's `meta.cli_execut
    CONTEXT: @**/* ./src/modules/auth|code|code:5|dirs:2
    ./src/modules/api|code|code:3|dirs:0
    EXPECTED: Documentation files in .workflow/docs/my_project/src/modules/
-   RULES: $PROTO $TMPL | Mirror source structure
+   CONSTRAINTS: Mirror source structure
    " --tool gemini --mode write --rule documentation-module --cd src/modules
    ```
 
@@ -216,7 +216,7 @@ Before completion, verify:
 {
   "step": "analyze_module_structure",
   "action": "Deep analysis of module structure and API",
-  "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: $PROTO $TMPL\" --tool gemini --mode analysis --rule documentation-module --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\nCONSTRAINTS: Mirror source structure\" --tool gemini --mode analysis --rule documentation-module --cd src/auth",
   "output_to": "module_analysis",
   "on_error": "fail"
 }
diff --git a/.claude/agents/issue-queue-agent.md b/.claude/agents/issue-queue-agent.md
index d697bf4d..4a992c3d 100644
--- a/.claude/agents/issue-queue-agent.md
+++ b/.claude/agents/issue-queue-agent.md
@@ -87,7 +87,7 @@ TASK: • Detect file conflicts (same file modified by multiple solutions)
 MODE: analysis
 CONTEXT: @.workflow/issues/solutions/**/*.jsonl | Solution data: \${SOLUTIONS_JSON}
 EXPECTED: JSON array of conflicts with type, severity, solutions, recommended_order
-RULES: $PROTO | Severity: high (API/data) > medium (file/dependency) > low (architecture)
+CONSTRAINTS: Severity: high (API/data) > medium (file/dependency) > low (architecture)
 " --tool gemini --mode analysis --cd .workflow/issues
 ```
 
diff --git a/.claude/commands/cli/codex-review.md b/.claude/commands/cli/codex-review.md
index e17428d6..6c31ef7c 100644
--- a/.claude/commands/cli/codex-review.md
+++ b/.claude/commands/cli/codex-review.md
@@ -30,7 +30,7 @@ TASK: • [step 1] • [step 2] • [step 3]
 MODE: review
 CONTEXT: [review target description] | Memory: [relevant context]
 EXPECTED: [deliverable format] + [quality criteria]
-RULES: $PROTO $TMPL | [focus constraints]
+CONSTRAINTS: [focus constraints]
 ```
 
 ## EXECUTION INSTRUCTIONS - START HERE
@@ -137,7 +137,7 @@ TASK: • Review code correctness and logic errors • Check coding standards an
 MODE: review
 CONTEXT: {target_description} | Memory: Project conventions from CLAUDE.md
 EXPECTED: Structured review report with: severity levels (Critical/High/Medium/Low), file:line references, specific improvement suggestions, priority ranking
-RULES: $PROTO $TMPL | Focus on actionable feedback
+CONSTRAINTS: Focus on actionable feedback
 ```
 
 **Security Focus Prompt:**
@@ -147,7 +147,7 @@ TASK: • Scan for injection vulnerabilities (SQL, XSS, command) • Check authe
 MODE: review
 CONTEXT: {target_description} | Memory: Security best practices, OWASP Top 10
 EXPECTED: Security report with: vulnerability classification, CVE references where applicable, remediation code snippets, risk severity matrix
-RULES: $PROTO $TMPL | Security-first analysis | Flag all potential vulnerabilities
+CONSTRAINTS: Security-first analysis | Flag all potential vulnerabilities
 ```
 
 **Performance Focus Prompt:**
@@ -157,7 +157,7 @@ TASK: • Analyze algorithmic complexity (Big-O) • Identify memory allocation
 MODE: review
 CONTEXT: {target_description} | Memory: Performance patterns and anti-patterns
 EXPECTED: Performance report with: complexity analysis, bottleneck identification, optimization suggestions with expected impact, benchmark recommendations
-RULES: $PROTO $TMPL | Performance optimization focus
+CONSTRAINTS: Performance optimization focus
 ```
 
 **Code Quality Focus Prompt:**
@@ -167,7 +167,7 @@ TASK: • Assess SOLID principles adherence • Identify code duplication and ab
 MODE: review
 CONTEXT: {target_description} | Memory: Project coding standards
 EXPECTED: Quality report with: principle violations, refactoring suggestions, naming improvements, maintainability score
-RULES: $PROTO $TMPL | Code quality and maintainability focus
+CONSTRAINTS: Code quality and maintainability focus
 ```
 
 **3.2 Build Target Description**
@@ -226,7 +226,7 @@ TASK: • Review correctness and logic • Check standards compliance • Identi
 MODE: review
 CONTEXT: Reviewing uncommitted changes | Memory: Project conventions
 EXPECTED: Structured report with severity levels, file:line refs, improvement suggestions
-RULES: $PROTO $TMPL | Actionable feedback
+CONSTRAINTS: Actionable feedback
 " --tool codex --mode review --uncommitted --rule analysis-review-code-quality
 ```
 
diff --git a/.claude/commands/issue/discover-by-prompt.md b/.claude/commands/issue/discover-by-prompt.md
index 28f27202..9efd308b 100644
--- a/.claude/commands/issue/discover-by-prompt.md
+++ b/.claude/commands/issue/discover-by-prompt.md
@@ -267,7 +267,7 @@ EXPECTED: JSON exploration plan following exploration-plan-schema.json:
   "estimated_iterations": N,
   "termination_conditions": [...]
 }
-RULES: $PROTO | Use ACE context to inform targets | Focus on actionable plan
+CONSTRAINTS: Use ACE context to inform targets | Focus on actionable plan
 `;
 
 // Step 3: Execute Gemini planning
diff --git a/.claude/commands/issue/plan.md b/.claude/commands/issue/plan.md
index afbc3fb4..88f017a7 100644
--- a/.claude/commands/issue/plan.md
+++ b/.claude/commands/issue/plan.md
@@ -131,7 +131,7 @@ TASK: • Analyze issue titles/tags semantically • Identify functional/archite
 MODE: analysis
 CONTEXT: Issue metadata only
 EXPECTED: JSON with groups array, each containing max 4 issue_ids, theme, rationale
-RULES: $PROTO | Each issue in exactly one group | Max 4 issues per group | Balance group sizes
+CONSTRAINTS: Each issue in exactly one group | Max 4 issues per group | Balance group sizes
 
 INPUT:
 ${JSON.stringify(issueSummaries, null, 2)}
diff --git a/.claude/commands/memory/swagger-docs.md b/.claude/commands/memory/swagger-docs.md
index 90b2b179..6cc3ffb6 100644
--- a/.claude/commands/memory/swagger-docs.md
+++ b/.claude/commands/memory/swagger-docs.md
@@ -223,7 +223,7 @@ TASK:
 MODE: analysis
 CONTEXT: @src/**/*.controller.ts @src/**/*.routes.ts @src/**/*.dto.ts @src/**/middleware/**/*
 EXPECTED: JSON format API structure analysis report with modules, endpoints, security schemes, and error codes
-RULES: $PROTO | Strict RESTful standards | Identify all public endpoints | Document output language: {lang}
+CONSTRAINTS: Strict RESTful standards | Identify all public endpoints | Document output language: {lang}
 " --tool gemini --mode analysis --rule analysis-code-patterns --cd {project_root}
 ```
 
@@ -387,7 +387,7 @@ bash(cat ${session_dir}/.process/swagger-planning-data.json | jq -r '.api_struct
         "step": 1,
         "title": "Generate OpenAPI spec file",
         "description": "Create complete swagger.yaml specification file",
-        "cli_prompt": "PURPOSE: Generate OpenAPI 3.0.3 specification file from analyzed API structure\nTASK:\n• Define openapi version: 3.0.3\n• Define info: title, description, version, contact, license\n• Define servers: development, staging, production environments\n• Define tags: organized by business modules\n• Define paths: all API endpoints with complete specifications\n• Define components: schemas, securitySchemes, parameters, responses\nMODE: write\nCONTEXT: @[api_analysis]\nEXPECTED: Complete swagger.yaml file following OpenAPI 3.0.3 specification\nRULES: $PROTO $TMPL | Use {lang} for all descriptions | Strict RESTful standards\n--rule documentation-swagger-api",
+        "cli_prompt": "PURPOSE: Generate OpenAPI 3.0.3 specification file from analyzed API structure\nTASK:\n• Define openapi version: 3.0.3\n• Define info: title, description, version, contact, license\n• Define servers: development, staging, production environments\n• Define tags: organized by business modules\n• Define paths: all API endpoints with complete specifications\n• Define components: schemas, securitySchemes, parameters, responses\nMODE: write\nCONTEXT: @[api_analysis]\nEXPECTED: Complete swagger.yaml file following OpenAPI 3.0.3 specification\nCONSTRAINTS: Use {lang} for all descriptions | Strict RESTful standards\n--rule documentation-swagger-api",
         "output": "swagger.yaml"
       }
     ],
@@ -429,7 +429,7 @@ bash(cat ${session_dir}/.process/swagger-planning-data.json | jq -r '.api_struct
       {
         "step": 1,
         "title": "Generate authentication documentation",
-        "cli_prompt": "PURPOSE: Generate comprehensive authentication documentation for API security\nTASK:\n• Document authentication mechanism: JWT Bearer Token\n• Explain header format: Authorization: Bearer <token>\n• Describe token lifecycle: acquisition, refresh, expiration handling\n• Define permission levels: public, user, admin, super_admin\n• Document authentication failure responses: 401/403 error handling\nMODE: write\nCONTEXT: @[auth_patterns] @src/**/auth/**/* @src/**/guard/**/*\nEXPECTED: Complete authentication guide in {lang}\nRULES: $PROTO | Include code examples | Clear step-by-step instructions\n--rule development-feature",
+        "cli_prompt": "PURPOSE: Generate comprehensive authentication documentation for API security\nTASK:\n• Document authentication mechanism: JWT Bearer Token\n• Explain header format: Authorization: Bearer <token>\n• Describe token lifecycle: acquisition, refresh, expiration handling\n• Define permission levels: public, user, admin, super_admin\n• Document authentication failure responses: 401/403 error handling\nMODE: write\nCONTEXT: @[auth_patterns] @src/**/auth/**/* @src/**/guard/**/*\nEXPECTED: Complete authentication guide in {lang}\nCONSTRAINTS: Include code examples | Clear step-by-step instructions\n--rule development-feature",
         "output": "{auth_doc_name}"
       }
     ],
@@ -464,7 +464,7 @@ bash(cat ${session_dir}/.process/swagger-planning-data.json | jq -r '.api_struct
       {
         "step": 1,
         "title": "Generate error code specification document",
-        "cli_prompt": "PURPOSE: Generate comprehensive error code specification for consistent API error handling\nTASK:\n• Define error response format: {code, message, details, timestamp}\n• Document authentication errors (AUTH_xxx): 401/403 series\n• Document parameter errors (PARAM_xxx): 400 series\n• Document business errors (BIZ_xxx): business logic errors\n• Document system errors (SYS_xxx): 500 series\n• For each error code: HTTP status, error message, possible causes, resolution suggestions\nMODE: write\nCONTEXT: @src/**/*.exception.ts @src/**/*.filter.ts\nEXPECTED: Complete error code specification in {lang} with tables and examples\nRULES: $PROTO | Include response examples | Clear categorization\n--rule development-feature",
+        "cli_prompt": "PURPOSE: Generate comprehensive error code specification for consistent API error handling\nTASK:\n• Define error response format: {code, message, details, timestamp}\n• Document authentication errors (AUTH_xxx): 401/403 series\n• Document parameter errors (PARAM_xxx): 400 series\n• Document business errors (BIZ_xxx): business logic errors\n• Document system errors (SYS_xxx): 500 series\n• For each error code: HTTP status, error message, possible causes, resolution suggestions\nMODE: write\nCONTEXT: @src/**/*.exception.ts @src/**/*.filter.ts\nEXPECTED: Complete error code specification in {lang} with tables and examples\nCONSTRAINTS: Include response examples | Clear categorization\n--rule development-feature",
         "output": "{error_doc_name}"
       }
     ],
@@ -523,7 +523,7 @@ bash(cat ${session_dir}/.process/swagger-planning-data.json | jq -r '.api_struct
         "step": 1,
         "title": "Generate module API documentation",
         "description": "Generate complete API documentation for ${module_name}",
-        "cli_prompt": "PURPOSE: Generate complete RESTful API documentation for ${module_name} module\nTASK:\n• Create module overview: purpose, use cases, prerequisites\n• Generate endpoint index: grouped by functionality\n• For each endpoint document:\n  - Functional description: purpose and business context\n  - Request method: GET/POST/PUT/DELETE\n  - URL path: complete API path\n  - Request headers: Authorization and other required headers\n  - Path parameters: {id} and other path variables\n  - Query parameters: pagination, filters, etc.\n  - Request body: JSON Schema format\n  - Response body: success and error responses\n  - Field description table: type, required, example, description\n• Add usage examples: cURL, JavaScript, Python\n• Add version info: v1.0.0, last updated date\nMODE: write\nCONTEXT: @[module_endpoints] @[source_code]\nEXPECTED: Complete module API documentation in {lang} with all endpoints fully documented\nRULES: $PROTO $TMPL | RESTful standards | Include all response codes\n--rule documentation-swagger-api",
+        "cli_prompt": "PURPOSE: Generate complete RESTful API documentation for ${module_name} module\nTASK:\n• Create module overview: purpose, use cases, prerequisites\n• Generate endpoint index: grouped by functionality\n• For each endpoint document:\n  - Functional description: purpose and business context\n  - Request method: GET/POST/PUT/DELETE\n  - URL path: complete API path\n  - Request headers: Authorization and other required headers\n  - Path parameters: {id} and other path variables\n  - Query parameters: pagination, filters, etc.\n  - Request body: JSON Schema format\n  - Response body: success and error responses\n  - Field description table: type, required, example, description\n• Add usage examples: cURL, JavaScript, Python\n• Add version info: v1.0.0, last updated date\nMODE: write\nCONTEXT: @[module_endpoints] @[source_code]\nEXPECTED: Complete module API documentation in {lang} with all endpoints fully documented\nCONSTRAINTS: RESTful standards | Include all response codes\n--rule documentation-swagger-api",
         "output": "${module_doc_name}"
       }
     ],
@@ -559,7 +559,7 @@ bash(cat ${session_dir}/.process/swagger-planning-data.json | jq -r '.api_struct
       {
         "step": 1,
         "title": "Generate API overview",
-        "cli_prompt": "PURPOSE: Generate API overview document with navigation and quick start guide\nTASK:\n• Create introduction: system features, tech stack, version\n• Write quick start guide: authentication, first request example\n• Build module navigation: categorized links to all modules\n• Document environment configuration: development, staging, production\n• List SDKs and tools: client libraries, Postman collection\nMODE: write\nCONTEXT: @[all_module_docs] @.workflow/docs/${project_name}/api/swagger.yaml\nEXPECTED: Complete API overview in {lang} with navigation links\nRULES: $PROTO | Clear structure | Quick start focus\n--rule development-feature",
+        "cli_prompt": "PURPOSE: Generate API overview document with navigation and quick start guide\nTASK:\n• Create introduction: system features, tech stack, version\n• Write quick start guide: authentication, first request example\n• Build module navigation: categorized links to all modules\n• Document environment configuration: development, staging, production\n• List SDKs and tools: client libraries, Postman collection\nMODE: write\nCONTEXT: @[all_module_docs] @.workflow/docs/${project_name}/api/swagger.yaml\nEXPECTED: Complete API overview in {lang} with navigation links\nCONSTRAINTS: Clear structure | Quick start focus\n--rule development-feature",
         "output": "README.md"
       }
     ],
@@ -602,7 +602,7 @@ bash(cat ${session_dir}/.process/swagger-planning-data.json | jq -r '.api_struct
       {
         "step": 1,
         "title": "Generate test report",
-        "cli_prompt": "PURPOSE: Generate comprehensive API test validation report\nTASK:\n• Document test environment configuration\n• Calculate endpoint coverage statistics\n• Report test results: pass/fail counts\n• Document boundary tests: parameter limits, null values, special characters\n• Document exception tests: auth failures, permission denied, resource not found\n• List issues found with recommendations\nMODE: write\nCONTEXT: @[swagger_spec]\nEXPECTED: Complete test report in {lang} with detailed results\nRULES: $PROTO | Include test cases | Clear pass/fail status\n--rule development-tests",
+        "cli_prompt": "PURPOSE: Generate comprehensive API test validation report\nTASK:\n• Document test environment configuration\n• Calculate endpoint coverage statistics\n• Report test results: pass/fail counts\n• Document boundary tests: parameter limits, null values, special characters\n• Document exception tests: auth failures, permission denied, resource not found\n• List issues found with recommendations\nMODE: write\nCONTEXT: @[swagger_spec]\nEXPECTED: Complete test report in {lang} with detailed results\nCONSTRAINTS: Include test cases | Clear pass/fail status\n--rule development-tests",
         "output": "{test_doc_name}"
       }
     ],
diff --git a/.claude/commands/workflow/lite-execute.md b/.claude/commands/workflow/lite-execute.md
index 8ed77c10..1ca4ffe6 100644
--- a/.claude/commands/workflow/lite-execute.md
+++ b/.claude/commands/workflow/lite-execute.md
@@ -486,7 +486,7 @@ TASK: • Verify plan acceptance criteria fulfillment • Analyze code quality 
 MODE: analysis
 CONTEXT: @**/* @{plan.json} [@{exploration.json}] | Memory: Review lite-execute changes against plan requirements
 EXPECTED: Quality assessment with acceptance criteria verification, issue identification, and recommendations. Explicitly check each acceptance criterion from plan.json tasks.
-RULES: $PROTO $TMPL | Focus on plan acceptance criteria and plan adherence | analysis=READ-ONLY
+CONSTRAINTS: Focus on plan acceptance criteria and plan adherence | analysis=READ-ONLY
 ```
 
 **Tool-Specific Execution** (Apply shared prompt template above):
diff --git a/.claude/commands/workflow/lite-lite-lite.md b/.claude/commands/workflow/lite-lite-lite.md
index f7255176..ce34b20a 100644
--- a/.claude/commands/workflow/lite-lite-lite.md
+++ b/.claude/commands/workflow/lite-lite-lite.md
@@ -167,7 +167,7 @@ TASK: ${tasks.map(t => `• ${t}`).join(' ')}
 MODE: analysis
 CONTEXT: @**/*
 EXPECTED: ${expected}
-RULES: $PROTO | ${rules}
+CONSTRAINTS: ${rules}
 `
 }
 
@@ -373,7 +373,7 @@ TASK: ${extractedTasks.join(' • ')}
 MODE: write
 CONTEXT: @${affectedFiles.join(' @')}
 EXPECTED: Working implementation with all changes applied
-RULES: $PROTO
+CONSTRAINTS: Follow existing patterns
 " --tool ${executionTool.name} --mode write`,
     run_in_background: false
   })
diff --git a/.claude/commands/workflow/tools/conflict-resolution.md b/.claude/commands/workflow/tools/conflict-resolution.md
index 71f6e399..ac10b9a3 100644
--- a/.claude/commands/workflow/tools/conflict-resolution.md
+++ b/.claude/commands/workflow/tools/conflict-resolution.md
@@ -154,7 +154,7 @@ Task(subagent_type="cli-execution-agent", run_in_background=false, prompt=`
     - Validation of exploration conflict_indicators
     - ModuleOverlap conflicts with overlap_analysis
     - Targeted clarification questions
-  RULES: $PROTO $TMPL | Focus on breaking changes, migration needs, and functional overlaps | Prioritize exploration-identified conflicts | analysis=READ-ONLY
+  CONSTRAINTS: Focus on breaking changes, migration needs, and functional overlaps | Prioritize exploration-identified conflicts | analysis=READ-ONLY
   " --tool gemini --mode analysis --rule analysis-code-patterns --cd {project_root}
 
   Fallback: Qwen (same prompt) → Claude (manual analysis)
diff --git a/.claude/skills/skill-generator/specs/cli-integration.md b/.claude/skills/skill-generator/specs/cli-integration.md
index 26e588e2..d002c591 100644
--- a/.claude/skills/skill-generator/specs/cli-integration.md
+++ b/.claude/skills/skill-generator/specs/cli-integration.md
@@ -304,14 +304,14 @@ async function runWithTool(tool, context) {
 ### 引用协议模板
 
 ```bash
-# 分析模式 - 使用 --rule 自动加载协议和模板
+# Analysis mode - use --rule to auto-load protocol and template (appended to prompt)
 ccw cli -p "
-RULES: $PROTO $TMPL | ...
+CONSTRAINTS: ...
 ..." --tool gemini --mode analysis --rule analysis-code-patterns
 
-# 写入模式 - 使用 --rule 自动加载协议和模板
+# Write mode - use --rule to auto-load protocol and template (appended to prompt)
 ccw cli -p "
-RULES: $PROTO $TMPL | ...
+CONSTRAINTS: ...
 ..." --tool codex --mode write --rule development-feature
 ```
 
@@ -319,11 +319,7 @@ RULES: $PROTO $TMPL | ...
 
 ```javascript
 function buildPrompt(config) {
-  const { purpose, task, mode, context, expected, template } = config;
-
-  const protocolPath = mode === 'write'
-    ? '~/.claude/workflows/cli-templates/protocols/write-protocol.md'
-    : '~/.claude/workflows/cli-templates/protocols/analysis-protocol.md';
+  const { purpose, task, mode, context, expected, constraints } = config;
 
   return `
 PURPOSE: ${purpose}
@@ -331,8 +327,8 @@ TASK: ${task.map(t => `• ${t}`).join('\n')}
 MODE: ${mode}
 CONTEXT: ${context}
 EXPECTED: ${expected}
-RULES: $PROTO $TMPL
-`; // Use --rule option to specify template
+CONSTRAINTS: ${constraints || ''}
+`; // Use --rule option to auto-append protocol + template
 }
 ```
 
@@ -433,11 +429,11 @@ CLI 调用 (Bash + ccw cli):
 - 相关任务使用 `--resume` 保持上下文
 - 独立任务不使用 `--resume`
 
-### 4. 提示词规范
+### 4. Prompt Specification
 
-- 始终使用 PURPOSE/TASK/MODE/CONTEXT/EXPECTED/RULES 结构
-- 使用 `--rule <template>` 自动加载协议和模板（`$PROTO` 和 `$TMPL`）
-- 模板名格式: `category-function` (如 `analysis-code-patterns`)
+- Always use PURPOSE/TASK/MODE/CONTEXT/EXPECTED/CONSTRAINTS structure
+- Use `--rule <template>` to auto-append protocol + template to prompt
+- Template name format: `category-function` (e.g., `analysis-code-patterns`)
 
 ### 5. 结果处理
 
diff --git a/.claude/workflows/cli-templates/prompts/workflow-skill-conflict-patterns.txt b/.claude/workflows/cli-templates/prompts/workflow-skill-conflict-patterns.txt
index 6fe8f780..848d8c8d 100644
--- a/.claude/workflows/cli-templates/prompts/workflow-skill-conflict-patterns.txt
+++ b/.claude/workflows/cli-templates/prompts/workflow-skill-conflict-patterns.txt
@@ -76,7 +76,7 @@ TASK: • Extract conflicts from IMPL_PLAN and lessons • Group by type (archit
 MODE: analysis
 CONTEXT: @.workflow/.archives/*/IMPL_PLAN.md @.workflow/.archives/manifest.json
 EXPECTED: Conflict patterns with frequency and resolution
-RULES: $PROTO $TMPL | analysis=READ-ONLY
+CONSTRAINTS: analysis=READ-ONLY
 " --tool gemini --mode analysis --rule workflow-skill-aggregation --cd .workflow/.archives
 ```
 
diff --git a/.claude/workflows/cli-templates/prompts/workflow-skill-lessons-learned.txt b/.claude/workflows/cli-templates/prompts/workflow-skill-lessons-learned.txt
index a26c82c7..74a33932 100644
--- a/.claude/workflows/cli-templates/prompts/workflow-skill-lessons-learned.txt
+++ b/.claude/workflows/cli-templates/prompts/workflow-skill-lessons-learned.txt
@@ -72,7 +72,7 @@ TASK: • Group successes by functional domain • Categorize challenges by seve
 MODE: analysis
 CONTEXT: @.workflow/.archives/manifest.json
 EXPECTED: Aggregated lessons with frequency counts
-RULES: $PROTO $TMPL | analysis=READ-ONLY
+CONSTRAINTS: analysis=READ-ONLY
 " --tool gemini --mode analysis --rule workflow-skill-aggregation --cd .workflow/.archives
 ```
 
diff --git a/.claude/workflows/cli-tools-usage.md b/.claude/workflows/cli-tools-usage.md
index 69419c70..db9fac05 100644
--- a/.claude/workflows/cli-tools-usage.md
+++ b/.claude/workflows/cli-tools-usage.md
@@ -111,14 +111,13 @@ When primary tool fails or is unavailable:
 ### Universal Prompt Template
 
 ```bash
-# Use --rule to auto-load protocol and template as $PROTO and $TMPL
 ccw cli -p "
 PURPOSE: [what] + [why] + [success criteria] + [constraints/scope]
 TASK: • [step 1: specific action] • [step 2: specific action] • [step 3: specific action]
 MODE: [analysis|write]
 CONTEXT: @[file patterns] | Memory: [session/tech/module context]
 EXPECTED: [deliverable format] + [quality criteria] + [structure requirements]
-RULES: $PROTO $TMPL | [domain constraints]
+CONSTRAINTS: [domain constraints]
 " --tool <tool-id> --mode <analysis|write> --rule <category-template>
 ```
 
@@ -168,11 +167,11 @@ Every command MUST include these fields:
   - Bad Example: "Report"
   - Good Example: "Markdown report with: severity levels (Critical/High/Medium/Low), file:line references, remediation code snippets, priority ranking"
 
-- **RULES**
-  - Purpose: Protocol + template + constraints
-  - Components: $PROTO + $TMPL + domain rules (variables loaded beforehand)
-  - Bad Example: (missing)
-  - Good Example: "$PROTO $TMPL | Focus on authentication | Ignore test files" (where PROTO and TMPL are pre-loaded variables)
+- **CONSTRAINTS**
+  - Purpose: Domain-specific constraints
+  - Components: Scope limits, special requirements, focus areas
+  - Bad Example: (missing or too vague)
+  - Good Example: "Focus on authentication | Ignore test files | No breaking changes"
 
 ### CONTEXT Configuration
 
@@ -221,27 +220,24 @@ CONTEXT: @components/Auth.tsx @types/auth.d.ts | Memory: Previous type refactori
 ccw cli -p "..." --tool <tool-id> --mode analysis --cd src
 ```
 
-### RULES Configuration
+### --rule Configuration
 
 **Use `--rule` option to auto-load templates**:
 
 ```bash
-ccw cli -p "... RULES: \$PROTO \$TMPL | constraints" --tool gemini --mode analysis --rule analysis-review-architecture
+ccw cli -p "..." --tool gemini --mode analysis --rule analysis-review-architecture
 ```
 
 **`--rule` How It Works**:
 1. Auto-discovers templates from `~/.claude/workflows/cli-templates/prompts/`
 2. Auto-loads corresponding protocol based on `--mode` (analysis-protocol.md or write-protocol.md)
-3. Sets environment variables `$PROTO` (protocol) and `$TMPL` (template) for subprocess
-4. Reference `$PROTO` and `$TMPL` in prompt
-
-> **Important**: `$PROTO` is required and must be included in RULES. `$TMPL` is optional.
+3. Appends protocol and template content to the end of your prompt
 
 ### Mode Protocol References
 
-**`--rule` auto-handles Protocol**:
-- `--mode analysis` → `$PROTO` = analysis-protocol.md
-- `--mode write` → `$PROTO` = write-protocol.md
+**`--rule` auto-loads Protocol based on mode**:
+- `--mode analysis` → analysis-protocol.md
+- `--mode write` → write-protocol.md
 
 **Protocol Mapping**:
 
@@ -336,9 +332,9 @@ ccw cli -p "... RULES: \$PROTO \$TMPL | constraints" --tool gemini --mode analys
   - Default: -
 
 - **`--rule <template>`**
-  - Description: 模板名称，自动加载 protocol + template 为 $PROTO 和 $TMPL 环境变量
-  - Default: none
-  - 根据 --mode 自动选择 protocol
+  - Description: Template name, auto-loads protocol + template appended to prompt
+  - Default: universal-rigorous-style
+  - Auto-selects protocol based on --mode
 
 ### Directory Configuration
 
@@ -407,7 +403,7 @@ TASK: • Scan for injection flaws (SQL, command, LDAP) • Check authentication
 MODE: analysis
 CONTEXT: @src/auth/**/* @src/middleware/auth.ts | Memory: Using bcrypt for passwords, JWT for sessions
 EXPECTED: Security report with: severity matrix, file:line references, CVE mappings where applicable, remediation code snippets prioritized by risk
-RULES: \$PROTO \$TMPL | Focus on authentication | Ignore test files
+CONSTRAINTS: Focus on authentication | Ignore test files
 " --tool gemini --mode analysis --rule analysis-assess-security-risks --cd src/auth
 ```
 
@@ -419,7 +415,7 @@ TASK: • Create rate limiter middleware with sliding window • Implement per-r
 MODE: write
 CONTEXT: @src/middleware/**/* @src/config/**/* | Memory: Using Express.js, Redis already configured, existing middleware pattern in auth.ts
 EXPECTED: Production-ready code with: TypeScript types, unit tests, integration test, configuration example, migration guide
-RULES: \$PROTO \$TMPL | Follow existing middleware patterns | No breaking changes
+CONSTRAINTS: Follow existing middleware patterns | No breaking changes
 " --tool gemini --mode write --rule development-implement-feature
 ```
 
@@ -431,7 +427,7 @@ TASK: • Trace connection lifecycle from open to close • Identify event liste
 MODE: analysis
 CONTEXT: @src/websocket/**/* @src/services/connection-manager.ts | Memory: Using ws library, ~5000 concurrent connections in production
 EXPECTED: Root cause analysis with: memory profile, leak source (file:line), fix recommendation with code, verification steps
-RULES: \$PROTO \$TMPL | Focus on resource cleanup
+CONSTRAINTS: Focus on resource cleanup
 " --tool gemini --mode analysis --rule analysis-diagnose-bug-root-cause --cd src
 ```
 
@@ -443,7 +439,7 @@ TASK: • Extract gateway interface from current implementation • Create strat
 MODE: write
 CONTEXT: @src/payments/**/* @src/types/payment.ts | Memory: Currently only Stripe, adding PayPal next sprint, must support future gateways
 EXPECTED: Refactored code with: strategy interface, concrete implementations, factory class, updated tests, migration checklist
-RULES: \$PROTO \$TMPL | Preserve all existing behavior | Tests must pass
+CONSTRAINTS: Preserve all existing behavior | Tests must pass
 " --tool gemini --mode write --rule development-refactor-codebase
 ```
 
@@ -481,15 +477,15 @@ ccw cli -p "Check for breaking changes in API contracts and backward compatibili
 - **Use tools early and often** - Tools are faster and more thorough
 - **Unified CLI** - Always use `ccw cli -p` for consistent parameter handling
 - **Default mode is analysis** - Omit `--mode` for read-only operations, explicitly use `--mode write` for file modifications
-- **Use `--rule` for templates** - 自动加载 protocol + template 为 `$PROTO` 和 `$TMPL` 环境变量
+- **Use `--rule` for templates** - Auto-loads protocol + template appended to prompt
 - **Write protection** - Require EXPLICIT `--mode write` for file operations
 
 ### Workflow Principles
 
 - **Use CCW unified interface** for all executions
-- **Always include template** - 使用 `--rule <template-name>` 加载模板
+- **Always include template** - Use `--rule <template-name>` to load templates
 - **Be specific** - Clear PURPOSE, TASK, EXPECTED fields
-- **Include constraints** - File patterns, scope in RULES
+- **Include constraints** - File patterns, scope in CONSTRAINTS
 - **Leverage memory context** when building on previous work
 - **Discover patterns first** - Use rg/MCP before CLI execution
 - **Default to full context** - Use `@**/*` unless specific files needed
@@ -501,8 +497,8 @@ ccw cli -p "Check for breaking changes in API contracts and backward compatibili
 - [ ] **Context gathered** - File references + memory (default `@**/*`)
 - [ ] **Directory navigation** - `--cd` and/or `--includeDirs`
 - [ ] **Tool selected** - Explicit `--tool` or tag-based auto-selection
-- [ ] **Rule template** - `--rule <template-name>` 自动加载 protocol + template
-- [ ] **Constraints specified** - Scope, requirements
+- [ ] **Rule template** - `--rule <template-name>` loads template
+- [ ] **Constraints** - Domain constraints in CONSTRAINTS field
 
 ### Execution Workflow
 
diff --git a/ccw/src/commands/cli.ts b/ccw/src/commands/cli.ts
index d01063bd..2dd3b6f8 100644
--- a/ccw/src/commands/cli.ts
+++ b/ccw/src/commands/cli.ts
@@ -551,6 +551,8 @@ async function execAction(positionalPrompt: string | undefined, options: CliExec
   }
 
   // Priority: 1. --file, 2. --prompt/-p option, 3. positional argument
+  // Note: On Windows, quoted arguments like -p "say hello" may be split into
+  // -p "say" and positional "hello". We merge them back together.
   let finalPrompt: string | undefined;
 
   if (file) {
@@ -569,7 +571,8 @@ async function execAction(positionalPrompt: string | undefined, options: CliExec
     }
   } else if (optionPrompt) {
     // Use --prompt/-p option (preferred for multi-line)
-    finalPrompt = optionPrompt;
+    // Merge with positional argument if Windows split the quoted string
+    finalPrompt = positionalPrompt ? `${optionPrompt} ${positionalPrompt}` : optionPrompt;
   } else {
     // Fall back to positional argument
     finalPrompt = positionalPrompt;
@@ -586,20 +589,21 @@ async function execAction(positionalPrompt: string | undefined, options: CliExec
 
   const prompt_to_use = finalPrompt || '';
 
-  // Load rules templates (will be passed as env vars)
+  // Load rules templates (concatenation mode - directly prepend to prompt)
   // Default to universal-rigorous-style if --rule not specified
   const effectiveRule = rule || 'universal-rigorous-style';
-  let rulesEnv: { PROTO?: string; TMPL?: string } = {};
+  let systemRules = '';  // Protocol content
+  let roles = '';        // Template content
   try {
     const { loadProtocol, loadTemplate } = await import('../tools/template-discovery.js');
     const proto = loadProtocol(mode);
     const tmpl = loadTemplate(effectiveRule);
-    if (proto) rulesEnv.PROTO = proto;
-    if (tmpl) rulesEnv.TMPL = tmpl;
+    if (proto) systemRules = proto;
+    if (tmpl) roles = tmpl;
     if (debug) {
       console.log(chalk.gray(`  Rule loaded: ${effectiveRule}${!rule ? ' (default)' : ''}`));
-      console.log(chalk.gray(`  PROTO(${proto ? proto.length : 0} chars) + TMPL(${tmpl ? tmpl.length : 0} chars)`));
-      console.log(chalk.gray(`  Use $PROTO and $TMPL in your prompt to reference them`));
+      console.log(chalk.gray(`  systemRules(${systemRules.length} chars) + roles(${roles.length} chars)`));
+      console.log(chalk.gray(`  Rules will be prepended to prompt automatically`));
     }
   } catch (error) {
     console.error(chalk.red(`Error loading rule template: ${error instanceof Error ? error.message : error}`));
@@ -728,6 +732,24 @@ async function execAction(positionalPrompt: string | undefined, options: CliExec
     }
   }
 
+  // Concatenate systemRules and roles to the end of prompt (if loaded)
+  // Format: [USER_PROMPT]\n[SYSTEM_RULES]\n[ROLES]
+  if (systemRules || roles) {
+    const parts: string[] = [actualPrompt];
+    if (systemRules) {
+      parts.push(`=== SYSTEM RULES ===\n${systemRules}`);
+    }
+    if (roles) {
+      parts.push(`=== ROLES ===\n${roles}`);
+    }
+    actualPrompt = parts.join('\n\n');
+
+    if (debug) {
+      console.log(chalk.gray(`  Prompt structure: USER_PROMPT(${prompt_to_use.length}) + SYSTEM_RULES(${systemRules.length}) + ROLES(${roles.length})`));
+      console.log(chalk.gray(`  Total prompt length: ${actualPrompt.length} chars`));
+    }
+  }
+
   // Parse resume IDs for merge scenario
   const resumeIds = resume && typeof resume === 'string' ? resume.split(',').map(s => s.trim()).filter(Boolean) : [];
   const isMerge = resumeIds.length > 1;
@@ -835,6 +857,7 @@ async function execAction(positionalPrompt: string | undefined, options: CliExec
       switch (unit.type) {
         case 'stdout':
         case 'code':
+        case 'streaming_content':  // Show streaming delta content in real-time
           process.stdout.write(typeof unit.content === 'string' ? unit.content : JSON.stringify(unit.content));
           break;
         case 'stderr':
@@ -879,9 +902,8 @@ async function execAction(positionalPrompt: string | undefined, options: CliExec
       uncommitted,
       base,
       commit,
-      title,
-      // Rules env vars (PROTO, TMPL)
-      rulesEnv: Object.keys(rulesEnv).length > 0 ? rulesEnv : undefined
+      title
+      // Rules are now concatenated directly into prompt (no env vars)
     }, onOutput); // Always pass onOutput for real-time dashboard streaming
 
     if (elapsedInterval) clearInterval(elapsedInterval);
@@ -1228,7 +1250,15 @@ export async function cliCommand(
 
       if (hasPromptOption || hasFileOption || hasResume || subcommandIsPrompt) {
         // Treat as exec: use subcommand as positional prompt if no -p/-f option
-        const positionalPrompt = subcommandIsPrompt ? subcommand : undefined;
+        let positionalPrompt = subcommandIsPrompt ? subcommand : undefined;
+
+        // On Windows, quoted arguments like -p "a b c" may be split across argsArray
+        // Merge them back together to reconstruct the full prompt
+        if (argsArray.length > 0 && hasPromptOption) {
+          const extraArgs = argsArray.join(' ');
+          positionalPrompt = positionalPrompt ? `${positionalPrompt} ${extraArgs}` : extraArgs;
+        }
+
         await execAction(positionalPrompt, execOptions);
       } else {
         // Show help
diff --git a/ccw/src/tools/cli-executor-core.ts b/ccw/src/tools/cli-executor-core.ts
index 87c6fad7..12f5d767 100644
--- a/ccw/src/tools/cli-executor-core.ts
+++ b/ccw/src/tools/cli-executor-core.ts
@@ -1149,7 +1149,7 @@ async function executeCliTool(
         duration_ms: duration,
         output: newTurnOutput,
         parsedOutput: flattenOutputUnits(allOutputUnits, {
-          excludeTypes: ['stderr', 'progress', 'metadata', 'system', 'tool_call']
+          excludeTypes: ['stderr', 'progress', 'metadata', 'system', 'tool_call', 'thought']
         })
       };
 
diff --git a/ccw/src/tools/cli-output-converter.ts b/ccw/src/tools/cli-output-converter.ts
index b3b0e884..0b1edf67 100644
--- a/ccw/src/tools/cli-output-converter.ts
+++ b/ccw/src/tools/cli-output-converter.ts
@@ -20,7 +20,8 @@ export type CliOutputUnitType =
   | 'progress'       // Progress updates
   | 'metadata'       // Session/execution metadata
   | 'system'         // System events/messages
-  | 'tool_call';     // Tool invocation/result (Gemini tool_use/tool_result)
+  | 'tool_call'      // Tool invocation/result (Gemini tool_use/tool_result)
+  | 'streaming_content';  // Streaming delta content (only last one used in final output)
 
 /**
  * Intermediate Representation unit
@@ -292,9 +293,9 @@ export class JsonLinesParser implements IOutputParser {
     if (json.type === 'message' && json.role) {
       // Gemini assistant/user message
       if (json.role === 'assistant') {
-        // Delta messages are incremental streaming chunks - treat as progress (filtered from final output)
-        // Only non-delta messages are final content
-        const outputType = json.delta === true ? 'progress' : 'stdout';
+        // Delta messages use 'streaming_content' type - only last one is used in final output
+        // Non-delta (final) messages use 'stdout' type
+        const outputType = json.delta === true ? 'streaming_content' : 'stdout';
         return {
           type: outputType,
           content: json.content || '',
@@ -1125,8 +1126,26 @@ export function flattenOutputUnits(
     separator = '\n'
   } = options || {};
 
+  // Special handling for streaming_content: concatenate all into a single stdout unit
+  // Gemini delta messages are incremental (each contains partial content to append)
+  let processedUnits = units;
+  const streamingUnits = units.filter(u => u.type === 'streaming_content');
+  if (streamingUnits.length > 0) {
+    // Concatenate all streaming_content into one
+    const concatenatedContent = streamingUnits
+      .map(u => typeof u.content === 'string' ? u.content : '')
+      .join('');
+    processedUnits = units.filter(u => u.type !== 'streaming_content');
+    // Add concatenated content as stdout type for inclusion
+    processedUnits.push({
+      type: 'stdout',
+      content: concatenatedContent,
+      timestamp: streamingUnits[streamingUnits.length - 1].timestamp
+    });
+  }
+
   // Filter units by type
-  let filtered = units;
+  let filtered = processedUnits;
   if (includeTypes && includeTypes.length > 0) {
     filtered = filtered.filter(u => includeTypes.includes(u.type));
   }