diff --git a/.claude/commands/task/breakdown.md b/.claude/commands/task/breakdown.md index 0a244183..503e4ec1 100644 --- a/.claude/commands/task/breakdown.md +++ b/.claude/commands/task/breakdown.md @@ -77,8 +77,8 @@ Proceed with breakdown? (y/n): y ✅ Task IMPL-1 broken down: ▸ IMPL-1: Build authentication module (container) - ├── IMPL-1.1: User authentication core → code-developer - └── IMPL-1.2: OAuth integration → code-developer + ├── IMPL-1.1: User authentication core → @code-developer + └── IMPL-1.2: OAuth integration → @code-developer Files updated: .task/IMPL-1.json + 2 subtask files + TODO_LIST.md ``` @@ -86,10 +86,10 @@ Files updated: .task/IMPL-1.json + 2 subtask files + TODO_LIST.md ## Decomposition Logic ### Agent Assignment -- **Design/Planning** → `planning-agent` -- **Implementation** → `code-developer` -- **Testing** → `code-review-test-agent` -- **Review** → `review-agent` +- **Design/Planning** → `@planning-agent` +- **Implementation** → `@code-developer` +- **Testing** → `@code-review-test-agent` +- **Review** → `@review-agent` ### Context Inheritance - Subtasks inherit parent requirements @@ -160,9 +160,9 @@ See @~/.claude/workflows/workflow-architecture.md for: /task:breakdown impl-1 ▸ impl-1: Build authentication (container) - ├── impl-1.1: Design schema → planning-agent - ├── impl-1.2: Implement logic → code-developer - └── impl-1.3: Write tests → code-review-test-agent + ├── impl-1.1: Design schema → @planning-agent + ├── impl-1.2: Implement logic → @code-developer + └── impl-1.3: Write tests → @code-review-test-agent ``` ## Error Handling diff --git a/.claude/commands/task/create.md b/.claude/commands/task/create.md index 2c295dd1..aeab5733 100644 --- a/.claude/commands/task/create.md +++ b/.claude/commands/task/create.md @@ -45,7 +45,7 @@ Output: ✅ Task created: IMPL-1 Title: Build authentication module Type: feature -Agent: code-developer +Agent: @code-developer Status: pending ``` @@ -105,10 +105,10 @@ Tasks inherit from: ## Agent Assignment Based on task type and title keywords: -- **Build/Implement** → `code-developer` -- **Design/Plan** → `planning-agent` -- **Test/Validate** → `code-review-test-agent` -- **Review/Audit** → `review-agent` +- **Build/Implement** → `@code-developer` +- **Design/Plan** → `@planning-agent` +- **Test/Validate** → `@code-review-test-agent` +- **Review/Audit** → `@review-agent` ## Validation Rules @@ -141,7 +141,7 @@ Based on task type and title keywords: ✅ Created IMPL-1: Implement user authentication Type: feature -Agent: code-developer +Agent: @code-developer Status: pending ``` @@ -151,7 +151,7 @@ Status: pending ✅ Created IMPL-2: Fix login validation bug Type: bugfix -Agent: code-developer +Agent: @code-developer Status: pending ``` diff --git a/.claude/commands/task/execute.md b/.claude/commands/task/execute.md index 91e68a43..5cdc2961 100644 --- a/.claude/commands/task/execute.md +++ b/.claude/commands/task/execute.md @@ -24,7 +24,7 @@ examples: - Executes step-by-step, requiring user confirmation at each checkpoint. - Allows for dynamic adjustments and manual review during the process. - **review** - - Executes under the supervision of a `review-agent`. + - Executes under the supervision of a `@review-agent`. - Performs quality checks and provides detailed feedback at each step. ### 🤖 **Agent Selection Logic** @@ -42,15 +42,15 @@ FUNCTION select_agent(task, agent_override): ELSE: CASE task.title: WHEN CONTAINS "Build API", "Implement": - RETURN "code-developer" + RETURN "@code-developer" WHEN CONTAINS "Design schema", "Plan": - RETURN "planning-agent" + RETURN "@planning-agent" WHEN CONTAINS "Write tests": - RETURN "code-review-test-agent" + RETURN "@code-review-test-agent" WHEN CONTAINS "Review code": - RETURN "review-agent" + RETURN "@review-agent" DEFAULT: - RETURN "code-developer" // Default agent + RETURN "@code-developer" // Default agent END CASE END FUNCTION ``` @@ -138,7 +138,7 @@ This is the simplified data structure loaded to provide context for task executi "title": "Build authentication module", "type": "feature", "status": "active", - "agent": "code-developer", + "agent": "@code-developer", "context": { "requirements": ["JWT authentication", "OAuth2 support"], "scope": ["src/auth/*", "tests/auth/*"], @@ -209,7 +209,7 @@ This is the simplified data structure loaded to provide context for task executi } }, "execution": { - "agent": "code-developer", + "agent": "@code-developer", "mode": "auto", "attempts": 0 } @@ -220,25 +220,25 @@ This is the simplified data structure loaded to provide context for task executi Different agents receive context tailored to their function, including implementation details: -**`code-developer`**: +**`@code-developer`**: - Complete implementation.files array with file paths and locations - original_code snippets and proposed_changes for precise modifications - logic_flow diagrams for understanding data flow - Dependencies and affected modules for integration planning - Performance and error handling considerations -**`planning-agent`**: +**`@planning-agent`**: - High-level requirements, constraints, success criteria - Implementation risks and mitigation strategies - Architecture implications from implementation.context_notes -**`code-review-test-agent`**: +**`@code-review-test-agent`**: - Files to test from implementation.files[].path - Logic flows to validate from implementation.modifications.logic_flow - Error conditions to test from implementation.context_notes.error_handling - Performance benchmarks from implementation.context_notes.performance_considerations -**`review-agent`**: +**`@review-agent`**: - Code quality standards and implementation patterns - Security considerations from implementation.context_notes.risks - Dependency validation from implementation.context_notes.dependencies @@ -262,7 +262,7 @@ Optional summary file generated at `.summaries/IMPL-[task-id]-summary.md`. - Added tests in tests/auth.test.ts ## Execution Results -- **Agent**: code-developer +- **Agent**: @code-developer - **Status**: completed ## Files Modified diff --git a/.claude/commands/workflow/docs.md b/.claude/commands/workflow/docs.md index 07ee60f6..07fb4a1d 100644 --- a/.claude/commands/workflow/docs.md +++ b/.claude/commands/workflow/docs.md @@ -111,7 +111,7 @@ Each documentation task uses the workflow-architecture.md 5-field schema: - **id**: IMPL-N format - **title**: Documentation task name - **status**: pending|active|completed|blocked -- **meta**: { type: "documentation", agent: "doc-generator" } +- **meta**: { type: "documentation", agent: "@doc-generator" } - **context**: { requirements, focus_paths, acceptance, scope } - **flow_control**: { pre_analysis[], implementation_approach, target_files[] } diff --git a/.claude/commands/workflow/execute.md b/.claude/commands/workflow/execute.md index ef3fd287..8cff23af 100644 --- a/.claude/commands/workflow/execute.md +++ b/.claude/commands/workflow/execute.md @@ -233,10 +233,10 @@ Task(subagent_type="{agent_type}", ``` meta.agent specified → Use specified agent meta.agent missing → Infer from meta.type: - - "feature" → code-developer - - "test" → code-review-test-agent - - "review" → code-review-agent - - "docs" → doc-generator + - "feature" → @code-developer + - "test" → @code-review-test-agent + - "review" → @code-review-agent + - "docs" → @doc-generator ``` #### Error Handling During Execution diff --git a/.claude/commands/workflow/status.md b/.claude/commands/workflow/status.md index d035e36a..3d1da6f4 100644 --- a/.claude/commands/workflow/status.md +++ b/.claude/commands/workflow/status.md @@ -70,7 +70,7 @@ Shows detailed task information: **Title**: Build authentication module **Status**: active -**Agent**: code-developer +**Agent**: @code-developer **Type**: feature ## Context @@ -245,7 +245,7 @@ Performs integrity checks: /workflow:status --format=tasks --filter=completed # Show tasks for specific agent -/workflow:status --format=tasks --agent=code-developer +/workflow:status --format=tasks --agent=@code-developer ``` ## Related Commands diff --git a/.claude/workflows/brainstorming-principles.md b/.claude/workflows/brainstorming-principles.md index e6bf94c6..bbeaa56e 100644 --- a/.claude/workflows/brainstorming-principles.md +++ b/.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:** ``` diff --git a/.claude/workflows/task-core.md b/.claude/workflows/task-core.md index 937e385a..6cd2f3d1 100644 --- a/.claude/workflows/task-core.md +++ b/.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 diff --git a/.claude/workflows/workflow-architecture.md b/.claude/workflows/workflow-architecture.md index bb5777ce..ad417457 100644 --- a/.claude/workflows/workflow-architecture.md +++ b/.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: