refactor: Standardize agent references to @agent-name format

- Convert direct agent name references to @agent-name format in documentation
- Preserve Task() function calls and subagent_type parameters unchanged
- Keep task content agent identifiers in original format (for display only)
- Maintain document reference paths in original format
- Update workflow architecture, task management, and execution files

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

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

.claude/workflows/brainstorming-principles.md

@@ -26,7 +26,7 @@ Before ANY agent coordination begins, the brainstorming command MUST establish t
    - Establish agent coordination metadata
 
 ### Pre-Agent Verification
-Before delegating to conceptual-planning-agent, VERIFY:
+Before delegating to @conceptual-planning-agent, VERIFY:
 - [ ] Topic slug generated correctly
 - [ ] All required directories exist  
 - [ ] workflow-session.json initialized
@@ -103,7 +103,7 @@ Each brainstorming session maintains metadata in `session-summary.md` header:
 **Topic**: [Challenge description]  
 **Mode**: creative|analytical|strategic  
 **Perspectives**: [role1, role2, role3...]  
-**Facilitator**: conceptual-planning-agent  
+**Facilitator**: @conceptual-planning-agent  
 **Date**: YYYY-MM-DD  
 
 ## Session Overview
@@ -161,7 +161,7 @@ done
 ```
 
 ### Agent Document Assignment Protocol
-When coordinating with conceptual-planning-agent, ALWAYS specify exact output location:
+When coordinating with @conceptual-planning-agent, ALWAYS specify exact output location:
 
 **Correct Agent Delegation:**
 ```

.claude/workflows/task-core.md

@@ -14,7 +14,7 @@ All task files use this simplified 5-field schema (aligned with workflow-archite
 
   "meta": {
     "type": "feature|bugfix|refactor|test|docs",
-    "agent": "code-developer|planning-agent|code-review-test-agent"
+    "agent": "@code-developer|@planning-agent|@code-review-test-agent"
   },
 
   "context": {
@@ -145,17 +145,17 @@ Tasks inherit from:
 ## Agent Mapping
 
 ### Automatic Agent Selection
-- **code-developer**: Implementation tasks, coding
-- **planning-agent**: Design, architecture planning
-- **code-review-test-agent**: Testing, validation
-- **review-agent**: Code review, quality checks
+- **@code-developer**: Implementation tasks, coding
+- **@planning-agent**: Design, architecture planning
+- **@code-review-test-agent**: Testing, validation
+- **@review-agent**: Code review, quality checks
 
 ### Agent Context Filtering
 Each agent receives tailored context:
-- **code-developer**: Complete implementation details
-- **planning-agent**: High-level requirements, risks
-- **test-agent**: Files to test, logic flows to validate
-- **review-agent**: Quality standards, security considerations
+- **@code-developer**: Complete implementation details
+- **@planning-agent**: High-level requirements, risks
+- **@test-agent**: Files to test, logic flows to validate
+- **@review-agent**: Quality standards, security considerations
 
 ## Deprecated Fields
 

.claude/workflows/workflow-architecture.md

@@ -114,7 +114,7 @@ All task files use this unified 5-field schema:
 
   "meta": {
     "type": "feature|bugfix|refactor|test|docs",
-    "agent": "code-developer|planning-agent|code-review-test-agent"
+    "agent": "@code-developer|@planning-agent|@code-review-test-agent"
   },
 
   "context": {
@@ -394,10 +394,10 @@ fi
 
 ### Agent Assignment
 Based on task type and title keywords:
-- **Planning tasks** → planning-agent
-- **Implementation** → code-developer
-- **Testing** → code-review-test-agent
-- **Review** → review-agent
+- **Planning tasks** → @planning-agent
+- **Implementation** → @code-developer
+- **Testing** → @code-review-test-agent
+- **Review** → @review-agent
 
 ### Execution Context
 Agents receive complete task JSON plus workflow context: