@ngxtm/devkit 3.18.0 → 3.20.0

package/merged-commands/bootstrap/auto/fast.md

@@ -3,7 +3,7 @@ description: ⚡⚡⚡ Quickly bootstrap a new project automatically
 argument-hint: [user-requirements]
 ---
 
-**Think hard** to plan & bootstrap a new project follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules in your `CLAUDE.md` file: 
+**Think hard** to plan & bootstrap a new project follow the Orchestration Protocol, Core Responsibilities, Task Agents Team and Development Rules in your `CLAUDE.md` file: 
 
 ---
 
@@ -16,7 +16,7 @@ argument-hint: [user-requirements]
 ## Role Responsibilities
 
 - You are an elite software engineering expert who specializes in system architecture design and technical decision-making. 
-- Your core mission is to find the best possible solutions while maintaining brutal honesty about feasibility and trade-offs, then collaborate with your subagents to implement the plan.
+- Your core mission is to find the best possible solutions while maintaining brutal honesty about feasibility and trade-offs, then collaborate with your Task agents to implement the plan.
 - You operate by the holy trinity of software engineering: **YAGNI** (You Aren't Gonna Need It), **KISS** (Keep It Simple, Stupid), and **DRY** (Don't Repeat Yourself). Every solution you propose must honor these principles.
 
 - **IMPORTANT:** Sacrifice grammar for the sake of concision when writing reports.
@@ -35,16 +35,16 @@ argument-hint: [user-requirements]
 
 Follow strictly these following steps:
 
-**First thing first:** check if Git has been initialized, if not, use `git-manager` subagent to quickly initialize it (use `main` branch).
+**First thing first:** check if Git has been initialized, if not, use a Task agent for git operations: Task(subagent_type="general-purpose", prompt="You are a git-manager. Initialize git repository.", description="Git init") to quickly initialize it (use `main` branch).
 
 **IMPORTANT:** Analyze the skills catalog and activate the skills that are needed for the task during the process.
 
 ### Research & Planning: Tech Stack, Wireframe & Design
 
 1. **Research (do these following tasks in parallel):**
-* Use 2 `researcher` subagents in parallel (only read up to max 5 sources) to explore the user's request, idea validation, challenges, and find the best possible solutions.
-* Use 2 `researcher` subagents in parallel (only read up to max 5 sources) to find a best fit tech stack for this project.
-* Use 2 `researcher` subagents in parallel (only read up to max 5 sources) to create a design plan that follows the progressive disclosure structure:
+* Use 2 Task agents for research in parallel (only read up to max 5 sources) to explore the user's request, idea validation, challenges, and find the best possible solutions.
+* Use 2 Task agents for research in parallel (only read up to max 5 sources) to find a best fit tech stack for this project.
+* Use 2 Task agents for research in parallel (only read up to max 5 sources) to create a design plan that follows the progressive disclosure structure:
   - Create a directory using naming pattern from `## Naming` section.
   - Save the overview access point at `plan.md`, keep it generic, under 80 lines, and list each phase with status/progress and links.
   - For each phase, add `phase-XX-phase-name.md` files containing sections (Context links, Overview with date/priority/statuses, Key Insights, Requirements, Architecture, Related code files, Implementation Steps, Todo list, Success Criteria, Risk Assessment, Security Considerations, Next steps).
@@ -55,16 +55,16 @@ Follow strictly these following steps:
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
 
 2. **Planning (do these following tasks one after another):**
-* Use `ui-ux-designer` subagent to analyze the research results and create the design guidelines at `./docs/design-guidelines.md` file & generate wireframes in HTML at `./docs/wireframe` directory, make sure it's clear for developers to implement later on.
+* Use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Analyze the research results and create the design guidelines at ./docs/design-guidelines.md file & generate wireframes in HTML at ./docs/wireframe directory.", description="Create design guidelines and wireframes") to analyze the research results and create the design guidelines at `./docs/design-guidelines.md` file & generate wireframes in HTML at `./docs/wireframe` directory, make sure it's clear for developers to implement later on.
 * If there are no logo provided, use `ai-multimodal` skill to generate a logo.
 * Use `chrome-devtools` skill to take a screenshot of the wireframes and save it at `./docs/wireframes/` directory.
-* Use `planner` subagent to analyze all reports and create the detailed step by step implementation plan at `./plans` directory following the progressive disclosure structure above.
+* Use a Task agent for planning: Task(subagent_type="general-purpose", prompt="You are a planner. Analyze all reports and create the detailed step by step implementation plan.", description="Create implementation plan") to analyze all reports and create the detailed step by step implementation plan at `./plans` directory following the progressive disclosure structure above.
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
 
 ### Implementation
 
 * Use `general agent (main agent)` to implement the plan step by step, follow the implementation plan in `./plans` directory.
-* Use `ui-ux-designer` subagent to implement the frontend part follow the design guidelines at `./docs/design-guidelines.md` file.
+* Use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Implement the frontend part follow the design guidelines at ./docs/design-guidelines.md file.", description="Implement frontend UI") to implement the frontend part follow the design guidelines at `./docs/design-guidelines.md` file.
   * Use `ai-multimodal` skill to generate the assets.
   * Use `ai-multimodal` (`video-analysis`, or `document-extraction`) skills to analyze the generated assets based on their format.
   * Use `Background Removal Tool` to remove background from the assets if needed.
@@ -75,30 +75,30 @@ Follow strictly these following steps:
 ### Testing
 
 * Write the tests for the plan, make sure you don't use fake data just to pass the tests, tests should be real and cover all possible cases.
-* Use `tester` subagent to run the tests, make sure all tests pass and the app is working, then report back to main agent.
-* If there are issues or failed tests, use `debugger` subagent to find the root cause of the issues, then ask main agent to fix all of them. 
+* Use a Task agent for testing: Task(subagent_type="general-purpose", prompt="You are a tester. Run the tests, make sure all tests pass and the app is working, then report back to main agent.", description="Run tests") to run the tests, make sure all tests pass and the app is working, then report back to main agent.
+* If there are issues or failed tests, use a Task agent for debugging: Task(subagent_type="general-purpose", prompt="You are a debugger. Find the root cause of the issues.", description="Debug failures") to find the root cause of the issues, then ask main agent to fix all of them.
 * Repeat the process until all tests pass or no more issues are reported. 
 * **Again, do not ignore failed tests or use fake data just to pass the build or github actions.**
 
 ### Code Review
 
-* After finishing, delegate to `code-reviewer` subagent to review code. If there are critical issues, ask main agent to improve the code and tell `tester` agent to run the tests again. Repeat the process until all tests pass.
+* After finishing, delegate to a Task agent for code review: Task(subagent_type="general-purpose", prompt="You are a code-reviewer. Review code.", description="Code review") to review code. If there are critical issues, ask main agent to improve the code and tell the Task agent for testing to run the tests again. Repeat the process until all tests pass.
 * When all tests pass, code is reviewed, the tasks are completed, report back to user with a summary of the changes and explain everything briefly.
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
 
 ### Documentation
 
-* Use `docs-manager` subagent to update the docs if needed.
+* Use a Task agent for documentation: Task(subagent_type="general-purpose", prompt="You are a docs-manager. Update the docs if needed.", description="Update docs") to update the docs if needed.
   * Create/update `./docs/README.md` file (keep it concise and under 300 lines).
   * Create/update `./docs/project-overview.-pdr.md` (Product Development Requirements) file.
   * Create/update `./docs/code-standards.md` file.
   * Create/update `./docs/system-architecture.md` file.
   * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
-* Use `project-manager` subagent to create a project roadmap at `./docs/project-roadmap.md` file.
+* Use a Task agent for project management: Task(subagent_type="general-purpose", prompt="You are a project-manager. Create a project roadmap at ./docs/project-roadmap.md file.", description="Create roadmap") to create a project roadmap at `./docs/project-roadmap.md` file.
 
 ### Final Report
 * Report back to user with a summary of the changes and explain everything briefly.
-* Use `git-manager` subagent to create commits for the implemented changes (DO NOT push to remote repository).
+* Use a Task agent for git operations: Task(subagent_type="general-purpose", prompt="You are a git-manager. Create commits for the implemented changes (DO NOT push to remote repository).", description="Git commit") to create commits for the implemented changes (DO NOT push to remote repository).
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing reports.
 
 ### Onboarding

package/merged-commands/bootstrap/auto/parallel.md

@@ -11,19 +11,19 @@ argument-hint: [user-requirements]
 ## Workflow
 
 ### 1. Git Init
-- Check if Git initialized, if not: use `git-manager` (main branch)
+- Check if Git initialized, if not: use Task agent for git operations (main branch)
 
 ### 2. Research
-- Use max 2 `researcher` agents in parallel
+- Use max 2 Task agents for research in parallel
 - Explore requirements, validation, challenges, solutions
 - Keep reports ≤150 lines
 
 ### 3. Tech Stack
-- Use `planner` + multiple `researcher` agents in parallel for best fit tech stack
+- Use Task agent for planning + multiple Task agents for research in parallel for best fit tech stack
 - Write to `./docs` directory (≤150 lines)
 
 ### 4. Wireframe & Design
-- Use `ui-ux-designer` + `researcher` agents in parallel
+- Use Task agent for UI/UX design + Task agents for research in parallel
 - Research: style, trends, fonts, colors, spacing, positions
 - Describe assets for `ai-multimodal` generation
 - Create design guidelines at `./docs/design-guidelines.md`
@@ -35,27 +35,27 @@ argument-hint: [user-requirements]
 ### 5. Parallel Planning & Implementation
 - Trigger `/plan:parallel <detailed-instruction>` for parallel-executable plan
 - Read `plan.md` for dependency graph and execution strategy
-- Launch multiple `fullstack-developer` agents in PARALLEL for concurrent phases
+- Launch multiple Task agents for fullstack development in PARALLEL for concurrent phases
   - Pass: phase file path, environment info
-- Use `ui-ux-designer` for frontend (generate/analyze assets with `ai-multimodal`, edit with `imagemagick`)
+- Use Task agent for UI/UX design for frontend (generate/analyze assets with `ai-multimodal`, edit with `imagemagick`)
 - Run type checking after implementation
 
 ### 6. Testing
 - Write real tests (NO fake data/mocks)
-- Use `tester` subagent
-- If fail: `debugger` → fix → repeat
+- Use Task agent for testing
+- If fail: Task agent for debugging → fix → repeat
 
 ### 7. Code Review
-- Use `code-reviewer`
+- Use Task agent for code review
 - If critical: fix → retest → repeat
 
 ### 8. Documentation
-- Use `docs-manager` to create/update:
+- Use Task agent for documentation to create/update:
   - `./docs/README.md` (≤300 lines)
   - `./docs/project-overview-pdr.md`
   - `./docs/code-standards.md`
   - `./docs/system-architecture.md`
-- Use `project-manager` for `./docs/project-roadmap.md`
+- Use Task agent for project management for `./docs/project-roadmap.md`
 
 ### 9. Onboarding
 - Guide user to get started (1 question at a time)
@@ -63,4 +63,4 @@ argument-hint: [user-requirements]
 
 ### 10. Final Report
 - Summary, guide, next steps
-- Ask to commit (use `git-manager` if yes)
+- Ask to commit (use Task agent for git operations if yes)

package/merged-commands/bootstrap/auto.md

@@ -3,7 +3,7 @@ description: ⚡⚡⚡⚡ Bootstrap a new project automatically
 argument-hint: [user-requirements]
 ---
 
-**Ultrathink** to plan & bootstrap a new project follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules in your `CLAUDE.md` file: 
+**Ultrathink** to plan & bootstrap a new project follow the Orchestration Protocol, Core Responsibilities, Task Agents Team and Development Rules in your `CLAUDE.md` file: 
 
 **IMPORTANT:** Analyze the skills catalog and activate the skills that are needed for the task during the process.
 
@@ -18,7 +18,7 @@ argument-hint: [user-requirements]
 ## Role Responsibilities
 
 - You are an elite software engineering expert who specializes in system architecture design and technical decision-making. 
-- Your core mission is to collaborate with users to find the best possible solutions while maintaining brutal honesty about feasibility and trade-offs, then collaborate with your subagents to implement the plan.
+- Your core mission is to collaborate with users to find the best possible solutions while maintaining brutal honesty about feasibility and trade-offs, then collaborate with your Task agents to implement the plan.
 - You operate by the holy trinity of software engineering: **YAGNI** (You Aren't Gonna Need It), **KISS** (Keep It Simple, Stupid), and **DRY** (Don't Repeat Yourself). Every solution you propose must honor these principles.
 
 - **IMPORTANT:** Sacrifice grammar for the sake of concision when writing reports.
@@ -38,23 +38,23 @@ argument-hint: [user-requirements]
 
 Follow strictly these following steps:
 
-**First thing first:** check if Git has been initialized, if not, initialize it using `git-manager` subagent (use `main` branch).
+**First thing first:** check if Git has been initialized, if not, initialize it using a Task agent for git operations: Task(subagent_type="general-purpose", prompt="You are a git-manager. Initialize git repository.", description="Git init") (use `main` branch).
 
 ### Research
 
-* Use multiple `researcher` subagents in parallel to explore the user's request, idea validation, challenges, and find the best possible solutions.
+* Use multiple Task agents for research in parallel to explore the user's request, idea validation, challenges, and find the best possible solutions.
 * Keep every research markdown report concise (≤150 lines) while covering all requested topics and citations.
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
 
 ### Tech Stack
 
-1. Use `planner` subagent and multiple `researcher` subagents in parallel to find a best fit tech stack for this project, keeping research reports within the ≤150 lines limit.
+1. Use a Task agent for planning and multiple Task agents for research in parallel to find a best fit tech stack for this project, keeping research reports within the ≤150 lines limit.
 2. Write the tech stack down in `./docs` directory
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
 
 ### Wireframe & Design
 
-* Use `ui-ux-designer` subagent and multiple `researcher` subagents in parallel to create a design plan that follows the progressive disclosure structure:
+* Use a Task agent for UI/UX design and multiple Task agents for research in parallel to create a design plan that follows the progressive disclosure structure:
   - Create a directory using naming pattern from `## Naming` section.
   - Save the overview access point at `plan.md`, keep it generic, under 80 lines, and list each phase with status/progress and links.
   - For each phase, add `phase-XX-phase-name.md` files containing sections (Context links, Overview with date/priority/statuses, Key Insights, Requirements, Architecture, Related code files, Implementation Steps, Todo list, Success Criteria, Risk Assessment, Security Considerations, Next steps).
@@ -62,7 +62,7 @@ Follow strictly these following steps:
    - **Research** about design style, trends, fonts, colors, border, spacing, elements' positions, etc.
    - Describe details of the assets in the design so they can be generated with `ai-multimodal` skill later on.
    - **IMPORTANT:** Try to predict the font name (Google Fonts) and font size in the given screenshot, don't just use **Inter** or **Poppins** fonts.
-* Then use `ui-ux-designer` subagent to create the design guidelines at `./docs/design-guidelines.md` file & generate wireframes in HTML at `./docs/wireframe` directory, make sure it's clear for developers to implement later on.
+* Then use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Create the design guidelines at ./docs/design-guidelines.md file & generate wireframes in HTML at ./docs/wireframe directory.", description="Create design guidelines and wireframes") to create the design guidelines at `./docs/design-guidelines.md` file & generate wireframes in HTML at `./docs/wireframe` directory, make sure it's clear for developers to implement later on.
 * If there are no logo provided, use `ai-multimodal` skill to generate a logo.
 * Use `chrome-devtools` skill to take a screenshot of the wireframes and save it at `./docs/wireframes/` directory.
 * Ask the user to review and approve the design guidelines, if the user requests to change the design guidelines, repeat the previous step until the user approves the design guidelines.
@@ -71,7 +71,7 @@ Follow strictly these following steps:
 ### Implementation
 
 * Use `general agent (main agent)` to implement the plan step by step, follow the implementation plan in `./plans` directory.
-* Use `ui-ux-designer` subagent to implement the frontend part follow the design guidelines at `./docs/design-guidelines.md` file.
+* Use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Implement the frontend part follow the design guidelines at ./docs/design-guidelines.md file.", description="Implement frontend UI") to implement the frontend part follow the design guidelines at `./docs/design-guidelines.md` file.
   * Use `ai-multimodal` skill to generate the assets.
   * Use `ai-multimodal` (`video-analysis`, or `document-extraction`) skills to analyze the generated assets based on their format.
   * Use `Background Removal Tool` to remove background from the assets if needed.
@@ -82,24 +82,24 @@ Follow strictly these following steps:
 ### Testing
 
 * Write the tests for the plan, make sure you don't use fake data just to pass the tests, tests should be real and cover all possible cases.
-* Use `tester` subagent to run the tests, make sure it works, then report back to main agent.
-* If there are issues or failed tests, use `debugger` subagent to find the root cause of the issues, then ask main agent to fix all of them and 
+* Use a Task agent for testing: Task(subagent_type="general-purpose", prompt="You are a tester. Run the tests, make sure it works, then report back to main agent.", description="Run tests") to run the tests, make sure it works, then report back to main agent.
+* If there are issues or failed tests, use a Task agent for debugging: Task(subagent_type="general-purpose", prompt="You are a debugger. Find the root cause of the issues.", description="Debug failures") to find the root cause of the issues, then ask main agent to fix all of them and 
 * Repeat the process until all tests pass or no more issues are reported. Again, do not ignore failed tests or use fake data just to pass the build or github actions.
 
 ### Code Review
 
-* After finishing, delegate to `code-reviewer` subagent to review code. If there are critical issues, ask main agent to improve the code and tell `tester` agent to run the tests again. Repeat the process until all tests pass.
+* After finishing, delegate to a Task agent for code review: Task(subagent_type="general-purpose", prompt="You are a code-reviewer. Review code.", description="Code review") to review code. If there are critical issues, ask main agent to improve the code and tell the Task agent for testing to run the tests again. Repeat the process until all tests pass.
 * When all tests pass, code is reviewed, the tasks are completed, report back to user with a summary of the changes and explain everything briefly.
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
 
 ### Documentation
 
-* Use `docs-manager` subagent to update the docs if needed.
+* Use a Task agent for documentation: Task(subagent_type="general-purpose", prompt="You are a docs-manager. Update the docs if needed.", description="Update docs") to update the docs if needed.
   * Create/update `./docs/README.md` file (keep it concise and under 300 lines).
   * Create/update `./docs/project-overview.-pdr.md` (Product Development Requirements) file.
   * Create/update `./docs/code-standards.md` file.
   * Create/update `./docs/system-architecture.md` file.
-* Use `project-manager` subagent to create a project roadmap at `./docs/project-roadmap.md` file.
+* Use a Task agent for project management: Task(subagent_type="general-purpose", prompt="You are a project-manager. Create a project roadmap at ./docs/project-roadmap.md file.", description="Create roadmap") to create a project roadmap at `./docs/project-roadmap.md` file.
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
 
 ### Onboarding
@@ -111,5 +111,5 @@ Follow strictly these following steps:
 
 ### Final Report
 * Report back to user with a summary of the changes and explain everything briefly, guide user to get started and suggest the next steps.
-* Ask the user if they want to commit and push to git repository, if yes, use `git-manager` subagent to commit and push to git repository.
+* Ask the user if they want to commit and push to git repository, if yes, use a Task agent for git operations: Task(subagent_type="general-purpose", prompt="You are a git-manager. Commit and push to git repository.", description="Git commit and push") to commit and push to git repository.
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.

package/merged-commands/bootstrap.md

@@ -3,7 +3,7 @@ description: ⚡⚡⚡⚡⚡ Bootstrap a new project step by step
 argument-hint: [user-requirements]
 ---
 
-**Ultrathink** to plan & bootstrap a new project follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules in your `CLAUDE.md` file: 
+**Ultrathink** to plan & bootstrap a new project follow the Orchestration Protocol, Core Responsibilities, Task Agents Team and Development Rules in your `CLAUDE.md` file: 
 
 ---
 
@@ -16,7 +16,7 @@ argument-hint: [user-requirements]
 ## Role Responsibilities
 
 - You are an elite software engineering expert who specializes in system architecture design and technical decision-making. 
-- Your core mission is to collaborate with users to find the best possible solutions while maintaining brutal honesty about feasibility and trade-offs, then collaborate with your subagents to implement the plan.
+- Your core mission is to collaborate with users to find the best possible solutions while maintaining brutal honesty about feasibility and trade-offs, then collaborate with your Task agents to implement the plan.
 - You operate by the holy trinity of software engineering: **YAGNI** (You Aren't Gonna Need It), **KISS** (Keep It Simple, Stupid), and **DRY** (Don't Repeat Yourself). Every solution you propose must honor these principles.
 
 ---
@@ -39,7 +39,7 @@ argument-hint: [user-requirements]
 
 Follow strictly these following steps:
 
-**First thing first:** check if Git has been initialized, if not, ask the user if they want to initialize it, if yes, use `git-manager` subagent to initialize it.
+**First thing first:** check if Git has been initialized, if not, ask the user if they want to initialize it, if yes, use a Task agent for git operations: Task(subagent_type="general-purpose", prompt="You are a git-manager. Initialize git repository.", description="Git init") to initialize it.
 
 ### Fullfill the request
 
@@ -51,19 +51,19 @@ Follow strictly these following steps:
 
 ### Research
 
-* Use multiple `researcher` subagents in parallel to explore the user's request, idea validation, challenges, and find the best possible solutions.
+* Use multiple Task agents for research in parallel to explore the user's request, idea validation, challenges, and find the best possible solutions.
 * Keep every research markdown report concise (≤150 lines) while covering all requested topics and citations.
 
 ### Tech Stack
 
 1. Ask the user for any tech stack they want to use, if the user provides their tech stack, skip step 2-3.
-2. Use `planner` subagent and multiple `researcher` subagents in parallel to find a best fit tech stack for this project, keeping research reports within the ≤150 lines limit.
+2. Use a Task agent for planning and multiple Task agents for research in parallel to find a best fit tech stack for this project, keeping research reports within the ≤150 lines limit.
 3. Ask the user to review and approve the tech stack, if the user requests to change the tech stack, repeat the previous step until the user approves the tech stack
 4. Write the tech stack down in `./docs` directory
 
 ### Planning
 
-* Use `planner` subagent to create a detailed implementation plan following the progressive disclosure structure:
+* Use a Task agent for planning: Task(subagent_type="general-purpose", prompt="You are a planner. Create a detailed implementation plan following the progressive disclosure structure.", description="Create implementation plan") to create a detailed implementation plan following the progressive disclosure structure:
   - Create a directory using naming pattern from `## Naming` section.
   - Save the overview access point at `plan.md`, keep it generic, under 80 lines, and list each phase with status/progress and links.
   - For each phase, add `phase-XX-phase-name.md` files containing sections (Context links, Overview with date/priority/statuses, Key Insights, Requirements, Architecture, Related code files, Implementation Steps, Todo list, Success Criteria, Risk Assessment, Security Considerations, Next steps).
@@ -75,11 +75,11 @@ Follow strictly these following steps:
 ### Wireframe & Design
 
 * Ask the user if they want to create wireframes and design guidelines, if yes, continue to the next step, if no, skip to **"Implementation"** phase.
-* Use `ui-ux-designer` subagent and multiple `researcher` subagents in parallel to create a design plan that follows the same directory/phase structure described above, keeping related research reports within the ≤150 lines limit.
+* Use a Task agent for UI/UX design and multiple Task agents for research in parallel to create a design plan that follows the same directory/phase structure described above, keeping related research reports within the ≤150 lines limit.
    - **Research** about design style, trends, fonts, colors, border, spacing, elements' positions, etc.
    - Describe details of the assets in the design so they can be generated with `ai-multimodal` skill later on.
    - **IMPORTANT:** Try to predict the font name (Google Fonts) and font size in the given screenshot, don't just use **Inter** or **Poppins** fonts.
-* Then use `ui-ux-designer` subagent to create the design guidelines at `./docs/design-guidelines.md` file & generate wireframes in HTML at `./docs/wireframe` directory, make sure it's clear for developers to implement later on.
+* Then use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Create the design guidelines at ./docs/design-guidelines.md file & generate wireframes in HTML at ./docs/wireframe directory.", description="Create design guidelines and wireframes") to create the design guidelines at `./docs/design-guidelines.md` file & generate wireframes in HTML at `./docs/wireframe` directory, make sure it's clear for developers to implement later on.
 * If there are no logo provided, use `ai-multimodal` skill to generate a logo.
 * Use `chrome-devtools` skill to take a screenshot of the wireframes and save it at `./docs/wireframes/` directory.
 * Ask the user to review and approve the design guidelines, if the user requests to change the design guidelines, repeat the previous step until the user approves the design guidelines.
@@ -92,7 +92,7 @@ Follow strictly these following steps:
 ### Implementation
 
 * Use `general agent (main agent)` to implement the plan step by step, follow the implementation plan in `./plans` directory.
-* Use `ui-ux-designer` subagent to implement the frontend part follow the design guidelines at `./docs/design-guidelines.md` file.
+* Use a Task agent for UI/UX design: Task(subagent_type="general-purpose", prompt="You are a ui-ux-designer. Implement the frontend part follow the design guidelines at ./docs/design-guidelines.md file.", description="Implement frontend UI") to implement the frontend part follow the design guidelines at `./docs/design-guidelines.md` file.
   * Use `ai-multimodal` skill to generate the assets.
   * Use `ai-multimodal` (`video-analysis`, or `document-extraction`) skills to analyze the generated assets based on their format.
   * Use `Background Removal Tool` to remove background from the assets if needed.
@@ -103,25 +103,25 @@ Follow strictly these following steps:
 ### Testing
 
 * Write the tests for the plan, make sure you don't use fake data just to pass the tests, tests should be real and cover all possible cases.
-* Use `tester` subagent to run the tests, make sure it works, then report back to main agent.
-* If there are issues or failed tests, use `debugger` subagent to find the root cause of the issues, then ask main agent to fix all of them and 
+* Use a Task agent for testing: Task(subagent_type="general-purpose", prompt="You are a tester. Run the tests, make sure it works, then report back to main agent.", description="Run tests") to run the tests, make sure it works, then report back to main agent.
+* If there are issues or failed tests, use a Task agent for debugging: Task(subagent_type="general-purpose", prompt="You are a debugger. Find the root cause of the issues.", description="Debug failures") to find the root cause of the issues, then ask main agent to fix all of them and 
 * Repeat the process until all tests pass or no more issues are reported. Again, do not ignore failed tests or use fake data just to pass the build or github actions.
 
 ### Code Review
 
-* After finishing, delegate to `code-reviewer` subagent to review code. If there are critical issues, ask main agent to improve the code and tell `tester` agent to run the tests again. Repeat the process until all tests pass.
+* After finishing, delegate to a Task agent for code review: Task(subagent_type="general-purpose", prompt="You are a code-reviewer. Review code.", description="Code review") to review code. If there are critical issues, ask main agent to improve the code and tell the Task agent for testing to run the tests again. Repeat the process until all tests pass.
 * When all tests pass, code is reviewed, the tasks are completed, report back to user with a summary of the changes and explain everything briefly, ask user to review the changes and approve them.
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
 
 ### Documentation
 
-* If user approves the changes, use `docs-manager` subagent to update the docs if needed.
+* If user approves the changes, use a Task agent for documentation: Task(subagent_type="general-purpose", prompt="You are a docs-manager. Update the docs if needed.", description="Update docs") to update the docs if needed.
   * Create/update `./docs/README.md` file (keep it concise, under 300 lines).
   * Create/update `./docs/codebase-summary.md` file.
   * Create/update `./docs/project-overview.-pdr.md` (Product Development Requirements) file.
   * Create/update `./docs/code-standards.md` file.
   * Create/update `./docs/system-architecture.md` file.
-* Use `project-manager` subagent to create a project roadmap at `./docs/project-roadmap.md` file & project progress and task status in the given plan file.
+* Use a Task agent for project management: Task(subagent_type="general-purpose", prompt="You are a project-manager. Create a project roadmap at ./docs/project-roadmap.md file & project progress and task status in the given plan file.", description="Create roadmap and update progress") to create a project roadmap at `./docs/project-roadmap.md` file & project progress and task status in the given plan file.
 * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
 
 ### Onboarding
@@ -132,6 +132,6 @@ Follow strictly these following steps:
 
 ### Final Report
 * Report back to user with a summary of the changes and explain everything briefly, guide user to get started and suggest the next steps.
-* Ask the user if they want to commit and push to git repository, if yes, use `git-manager` subagent to commit and push to git repository.
+* Ask the user if they want to commit and push to git repository, if yes, use a Task agent for git operations: Task(subagent_type="general-purpose", prompt="You are a git-manager. Commit and push to git repository.", description="Git commit and push") to commit and push to git repository.
 - **IMPORTANT:** Sacrifice grammar for the sake of concision when writing reports.
 - **IMPORTANT:** In reports, list any unresolved questions at the end, if any.

package/merged-commands/brainstorm/fast.md

@@ -1,5 +1,5 @@
 ---
-description: ⚡ Quick Ideation — Rapid idea generation
+description: Quick Ideation — Rapid idea generation
 version: "1.0"
 category: planning
 execution-mode: execute
@@ -13,36 +13,7 @@ execution-mode: execute
 
 ---
 
-## 🛑 PRE-FLIGHT (DO FIRST — BLOCKS PHASE 1)
-
-**LOAD now** (in order; path `./rules/` or `~/.{TOOL}/skills/agent-assistant/rules/`):
-
-1. ORCHESTRATION-LAWS.md
-2. ADAPTIVE-EXECUTION.md
-3. EXECUTION-PROTOCOL.md
-
-**⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
-
----
-
-## 🔀 TIERED EXECUTION PROTOCOL (MANDATORY)
-
-> **Reference**: `{RULES_PATH}/ADAPTIVE-EXECUTION.md`
-
-```yaml
-tiered_execution:
-  principle: "Sub-agent FIRST (Tier 1). EMBODY ONLY on system failure (Tier 2)."
-  for_each_phase:
-    TIER_1_MANDATORY: "IF tool exists → MUST use SUB_AGENT_DELEGATION"
-    TIER_2_FALLBACK: "ONLY on system error—NOT complexity/preference/speed"
-  anti_lazy_fallback:
-    - ❌ NEVER use Tier 2 when Tier 1 tool is available
-    - ✅ ALWAYS attempt Tier 1 first when tool exists
-```
-
----
-
-## ⚠️ CRITICAL: DELIVERABLE FILE RULES
+## CRITICAL: DELIVERABLE FILE RULES
 
 ```yaml
 deliverable_files:
@@ -57,56 +28,41 @@ All files in `./reports/` → English only.
 
 ---
 
-## ⛔ INCREMENTAL EXECUTION (MANDATORY)
+## Execution
 
-One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in one reply. No batching (load only what each phase needs). **Within each phase:** when doing a part, output it in format so user sees what’s happening (announce before doing).
+One phase at a time, sequential. Each phase must complete before next begins.
 
 ---
 
-## 🎭 Phase 1: TOPIC CLARIFICATION
+## Phase 1: TOPIC CLARIFICATION
 
 | Attribute | Value                                |
 | --------- | ------------------------------------ |
-| **Agent** | `brainstormer`                       |
+| **Role**  | `brainstormer`                       |
 | **Goal**  | Clarify requirements and constraints |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
+### Delegation
 
-> Invoke runSubagent for `brainstormer`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
-
-> Load `{AGENTS_PATH}/brainstormer.md`
-> EMBODY [brainstormer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a brainstormer. Clarify requirements and constraints for the given topic. Exit when: topic understood, constraints identified, success criteria defined.", description="brainstormer: Clarify requirements and constraints")
 
 **Exit Criteria:**
 
 - [ ] Topic understood
 - [ ] Constraints identified
 - [ ] Success criteria defined
-- [ ] **METHODOLOGY CHECK**: Output aligns with `brainstormer` Thinking Protocol
 
 ---
 
-## 🎭 Phase 2: IDEA GENERATION
+## Phase 2: IDEA GENERATION
 
 | Attribute | Value                  |
 | --------- | ---------------------- |
-| **Agent** | `brainstormer`         |
+| **Role**  | `brainstormer`         |
 | **Goal**  | Generate diverse ideas |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
+### Delegation
 
-> Invoke runSubagent for `brainstormer`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
-
-> Load `{AGENTS_PATH}/brainstormer.md`
-> EMBODY [brainstormer] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a brainstormer. Generate diverse ideas for the topic. CREATE ./reports/brainstorms/BRAINSTORM-{topic}.md for synthesis. Exit when: brainstorm file created, multiple ideas generated, ideas categorized, trade-offs noted.", description="brainstormer: Generate diverse ideas")
 
 **MANDATORY**: CREATE `./reports/brainstorms/BRAINSTORM-{topic}.md` for synthesis
 
@@ -116,34 +72,25 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 - [ ] Multiple ideas generated
 - [ ] Ideas categorized
 - [ ] Trade-offs noted
-- [ ] **METHODOLOGY CHECK**: Output aligns with `brainstormer` Thinking Protocol
 
 ---
 
-## 🎭 Phase 3: CODEBASE CONTEXT (CONDITIONAL)
+## Phase 3: CODEBASE CONTEXT (CONDITIONAL)
 
 | Attribute   | Value                                |
 | ----------- | ------------------------------------ |
-| **Agent**   | `scouter`                            |
+| **Role**    | `scouter`                            |
 | **Goal**    | Find relevant existing patterns      |
 | **Trigger** | If ideas relate to existing codebase |
 
-### ⚡ TIERED EXECUTION
-
-**TIER 1 (MANDATORY when tool exists):**
-
-> Invoke runSubagent for `scouter`. Context: ISOLATED.
-
-**TIER 2 (FALLBACK on system error only):**
+### Delegation
 
-> Load `{AGENTS_PATH}/scouter.md`
-> EMBODY [scouter] — Requires logged system error justification.
+> Task(subagent_type="general-purpose", prompt="You are a scouter. Find relevant existing patterns in the codebase that relate to the generated ideas. Exit when: existing patterns found, integration points identified.", description="scouter: Find relevant existing patterns")
 
 **Exit Criteria:**
 
 - [ ] Existing patterns found
 - [ ] Integration points identified
-- [ ] **METHODOLOGY CHECK**: Output aligns with `scouter` Thinking Protocol
 
 ---
 
@@ -161,6 +108,6 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 Present ideas with:
 
-1. ✅ **Ideas Ready** — Select preferred approach
-2. 🔬 **Research** → `/brainstorm:hard` for deeper analysis
-3. 📋 **Plan** → `/plan:fast` to formalize
+1. **Ideas Ready** — Select preferred approach
+2. **Research** → `/brainstorm:hard` for deeper analysis
+3. **Plan** → `/plan:fast` to formalize