@amrhas82/agentic-kit 1.2.0 → 1.5.0

package/packages/claude/AGENTS.md

@@ -1,19 +1,21 @@
-# Project Agents
+# Global Claude Code Agents
 
 This file provides guidance and memory for your coding CLI.
 
-# Opencode subagents and Tasks (OpenCode)
+# Claude subagents and Tasks (Claude Code)
 
-OpenCode reads AGENTS.md during initialization and uses it as part of its system prompt for the session. 
+Claude Code reads AGENTS.md when other subagents want to invoke other subagents, tasks, or resources
 
 ## How To Use With Claude
 
-- Copy/paste `claude` subfolders in this project to ~/.claude and Claude will read and access agents from ~/.claude/agents and tasks from ~/.claude/tasks,
+Activate agents by mentioning their ID in your prompts:
+- `"@qa-test-architect review this code"`
+- Copy/paste `claude` subfolders in this project to ~/.claude and Claude will read and access agents from ~/.claude/agents and tasks from ~/.claude/resources/tasks-brief.md,
 - You can access agents using "@ux-expert", or you can reference a role naturally, e.g., "As ux-expert, implement ..." or use commands defined in your tasks.
 
 Note
-- Orchestrators run as mode: primary; other agents as all.
-- All agents have tools enabled: write, edit, bash.
+- Orchestrators/master run as mode: primary; other agents as mode: subagents.
+- All agents have enbaled tools: write, edit, bash.
 
 ## Agents
 
@@ -34,94 +36,102 @@ Note
 | Master Task Executor | master | Use when you need comprehensive expertise across all domains, running 1 off tasks that do not require a persona, or just wanting to use the same agent for many things. |
 | Architect | holistic-architect | Use for system design, architecture documents, technology selection, API design, and infrastructure planning |
 | Business Analyst | business-analyst | Use for market research, brainstorming, competitive analysis, creating project briefs, initial project discovery, and documenting existing projects (brownfield) |
+| Context Initializer | context-initializer | Use to initialize Claude Code context for new/existing projects, discover and organize documentation, create CLAUDE.md and KNOWLEDGE_BASE.md for optimal token-efficient memory |
 
 
 ### 1-Create PRD (id: 1-create-prd) 
-Source: [.agents/ux-expert.md](.agents/1-create-prd.md)
+Source: [./agents/ux-expert.md](./agents/1-create-prd.md)
 
 - When to use: Define Scope: use to clearly outlining what needs to be built with a Product Requirement Document (PRD)  optimization
 - How to activate: Mention "create prd, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### 2-Generate Tasks (id: 2-generate-tasks) 
-Source: [.agents/ux-expert.md](.agents/2-generate-tasks.md)
+Source: [./agents/ux-expert.md](./agents/2-generate-tasks.md)
 
 - When to use: 2. Detailed Planning: use to break down the PRD into a granular, actionable task list
 - How to activate: Mention "generate tasks, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### 3-Process Task List (id: 3-process-task-list)
-Source: [.agents/ux-expert.md](.agents/3-process-task-list.md)
+Source: [./agents/ux-expert.md](./agents/3-process-task-list.md)
 
 - When to use: 3. Iterative Implementation: use to guide the AI to tackle one task at a time, allowing you to review and approve each change
 - How to activate: Mention "process task list, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### UX Expert (id: ux-expert)
-Source: [.agents/ux-expert.md](.agents/ux-expert.md)
+Source: [./agents/ux-expert.md](./agents/ux-expert.md)
 
 - When to use: Use for UI/UX design, wireframes, prototypes, front-end specifications, and user experience optimization
 - How to activate: Mention "As ux-expert, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### Scrum Master (id: scrum-master)
-Source: [.agents/scrum-master.md](.agents/scrum-master.md)
+Source: [./agents/scrum-master.md](./agents/scrum-master.md)
 
 - When to use: Use for story creation, epic management, retrospectives in party-mode, and agile process guidance
 - How to activate: Mention "As scrum-master, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### Test Architect & Quality Advisor (id: qa-test-architect)
-Source: [.agents/qa-test-architect.md](.agents/qa-test-architect.md)
+Source: [./agents/qa-test-architect.md](./agents/qa-test-architect.md)
 
 - When to use: Use for comprehensive test architecture review, quality gate decisions, and code improvement. Provides thorough analysis including requirements traceability, risk assessment, and test strategy. Advisory only - teams choose their quality bar.
 - How to activate: Mention "As qa, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### Product Owner (id: product-owner)
-Source: [.agents/product-owner.md](.agents/product-owner.md)
+Source: [./agents/product-owner.md](./agents/product-owner.md)
 
 - When to use: Use for backlog management, story refinement, acceptance criteria, sprint planning, and prioritization decisions
 - How to activate: Mention "As product-owner, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### Product Manager (id: product-manager)
-Source: [.agents/product-manager.md](.agents/product-manager.md)
+Source: [./agents/product-manager.md](./agents/product-manager.md)
 
 - When to use: Use for creating PRDs, product strategy, feature prioritization, roadmap planning, and stakeholder communication
 - How to activate: Mention "As product-manager, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### Full Stack Developer (id: full-stack-dev)
-Source: [.agents/full-stack-dev.md](.agents/full-stack-dev.md)
+Source: [./agents/full-stack-dev.md](./agents/full-stack-dev.md)
 
 - When to use: Use for code implementation, debugging, refactoring, and development best practices
 - How to activate: Mention "As full-stack-dev, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### Master Orchestrator (id: orchestrator)
-Source: [.agents/orchestrator.md](.agents/orchestrator.md)
+Source: [./agents/orchestrator.md](./agents/orchestrator.md)
 
 - When to use: Use for workflow coordination, multi-agent tasks, role switching guidance, and when unsure which specialist to consult
 - How to activate: Mention "As orchestrator, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### Master Task Executor (id: master)
-Source: [.agents/master.md](.agents/master.md)
+Source: [./agents/master.md](./agents/master.md)
 
 - When to use: Use when you need comprehensive expertise across all domains, running 1 off tasks that do not require a persona, or just wanting to use the same agent for many things.
 - How to activate: Mention "As master, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
 ### Architect (id: holistic-architect)
-Source: [.agents/holistic-architect.md](.agents/holistic-architect.md)
+Source: [./agents/holistic-architect.md](./agents/holistic-architect.md)
 
 - When to use: Use for system design, architecture documents, technology selection, API design, and infrastructure planning
 - How to activate: Mention "As architect, ..." to get role-aligned behavior
 - Full definition: open the source file above (content not embedded)
 
+### Context Initializer (id: context-initializer)
+Source: [./agents/context-initializer.md](./agents/context-initializer.md)
+
+- When to use: Use to initialize Claude Code context for new/existing projects, discover and organize documentation, create CLAUDE.md and KNOWLEDGE_BASE.md for optimal token-efficient memory
+- How to activate: Mention "@context-initializer" or "As context-initializer, ..." to get role-aligned behavior
+- Full definition: open the source file above (content not embedded)
+
 ### Business Analyst (id: business-analyst)
-Source: [.agents/business-analyst.md](.agents/business-analyst.md)
+Source: [./agents/business-analyst.md](./agents/business-analyst.md)
 
 - When to use: Use for market research, brainstorming, competitive analysis, creating project briefs, initial project discovery, and documenting existing projects (brownfield)
 - How to activate: Mention "As analyst, ..." to get role-aligned behavior
@@ -132,112 +142,248 @@ Source: [.agents/business-analyst.md](.agents/business-analyst.md)
 These are reusable task briefs; use the paths to open them as needed.
 
 ### Task: validate-next-story
-Source: [../resources/task-briefs.md#validate-next-story](../resources/task-briefs.md#validate-next-story)
+Source: [./resources/task-briefs.md#validate-next-story](./resources/task-briefs.md#validate-next-story)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: trace-requirements
-Source: [../resources/task-briefs.md#trace-requirements](../resources/task-briefs.md#trace-requirements)
+Source: [./resources/task-briefs.md#trace-requirements](./resources/task-briefs.md#trace-requirements)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: test-design
-Source: [../resources/task-briefs.md#test-design](../resources/task-briefs.md#test-design)
+Source: [./resources/task-briefs.md#test-design](./resources/task-briefs.md#test-design)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: shard-doc
-Source: [../resources/task-briefs.md#shard-doc](../resources/task-briefs.md#shard-doc)
+Source: [./resources/task-briefs.md#shard-doc](./resources/task-briefs.md#shard-doc)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: risk-profile
-Source: [../resources/task-briefs.md#risk-profile](../resources/task-briefs.md#risk-profile)
+Source: [./resources/task-briefs.md#risk-profile](./resources/task-briefs.md#risk-profile)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: review-story
-Source: [../resources/task-briefs.md#review-story](../resources/task-briefs.md#review-story)
+Source: [./resources/task-briefs.md#review-story](./resources/task-briefs.md#review-story)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: qa-test-architect-gate
-Source: [../resources/task-briefs.md#qa-gate](../resources/task-briefs.md#qa-gate)
+Source: [./resources/task-briefs.md#qa-gate](./resources/task-briefs.md#qa-gate)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: nfr-assess
-Source: [../resources/task-briefs.md#nfr-assess](../resources/task-briefs.md#nfr-assess)
+Source: [./resources/task-briefs.md#nfr-assess](./resources/task-briefs.md#nfr-assess)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: index-docs
-Source: [../resources/task-briefs.md#index-docs](../resources/task-briefs.md#index-docs)
+Source: [./resources/task-briefs.md#index-docs](./resources/task-briefs.md#index-docs)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: generate-ai-frontend-prompt
-Source: [../resources/task-briefs.md#generate-ai-frontend-prompt](../resources/task-briefs.md#generate-ai-frontend-prompt)
+Source: [./resources/task-briefs.md#generate-ai-frontend-prompt](./resources/task-briefs.md#generate-ai-frontend-prompt)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: facilitate-brainstorming-session
-Source: [../resources/task-briefs.md#facilitate-brainstorming-session](../resources/task-briefs.md#facilitate-brainstorming-session)
+Source: [./resources/task-briefs.md#facilitate-brainstorming-session](./resources/task-briefs.md#facilitate-brainstorming-session)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: execute-checklist
-Source: [../resources/task-briefs.md#execute-checklist](../resources/task-briefs.md#execute-checklist)
+Source: [./resources/task-briefs.md#execute-checklist](./resources/task-briefs.md#execute-checklist)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: document-project
-Source: [../resources/task-briefs.md#document-project](../resources/task-briefs.md#document-project)
+Source: [./resources/task-briefs.md#document-project](./resources/task-briefs.md#document-project)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: create-next-story
-Source: [../resources/task-briefs.md#create-next-story](../resources/task-briefs.md#create-next-story)
+Source: [./resources/task-briefs.md#create-next-story](./resources/task-briefs.md#create-next-story)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: create-doc
-Source: [../resources/task-briefs.md#create-doc](../resources/task-briefs.md#create-doc)
+Source: [./resources/task-briefs.md#create-doc](./resources/task-briefs.md#create-doc)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: create-deep-research-prompt
-Source: [../resources/task-briefs.md#create-deep-research-prompt](../resources/task-briefs.md#create-deep-research-prompt)
+Source: [./resources/task-briefs.md#create-deep-research-prompt](./resources/task-briefs.md#create-deep-research-prompt)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: create-brownfield-story
-Source: [../resources/task-briefs.md#create-brownfield-story](../resources/task-briefs.md#create-brownfield-story)
+Source: [./resources/task-briefs.md#create-brownfield-story](./resources/task-briefs.md#create-brownfield-story)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: correct-course
-Source: [../resources/task-briefs.md#correct-course](../resources/task-briefs.md#correct-course)
+Source: [./resources/task-briefs.md#correct-course](./resources/task-briefs.md#correct-course)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: brownfield-create-story
-Source: [../resources/task-briefs.md#brownfield-create-story](../resources/task-briefs.md#brownfield-create-story)
+Source: [./resources/task-briefs.md#brownfield-create-story](./resources/task-briefs.md#brownfield-create-story)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: brownfield-create-epic
-Source: [../resources/task-briefs.md#brownfield-create-epic](../resources/task-briefs.md#brownfield-create-epic)
+Source: [./resources/task-briefs.md#brownfield-create-epic](./resources/task-briefs.md#brownfield-create-epic)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: apply-qa-fixes
-Source: [../resources/task-briefs.md#apply-qa-fixes](../resources/task-briefs.md#apply-qa-fixes)
+Source: [./resources/task-briefs.md#apply-qa-fixes](./resources/task-briefs.md#apply-qa-fixes)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
 ### Task: advanced-elicitation
-Source: [../resources/task-briefs.md#advanced-elicitation](../resources/task-briefs.md#advanced-elicitation)
+Source: [./resources/task-briefs.md#advanced-elicitation](./resources/task-briefs.md#advanced-elicitation)
 - How to use: Reference the task in your prompt or execute via your configured commands.
 - Full brief: open the source file above (content not embedded)
 
+## Skills
+
+These are slash commands available in the TUI. Use /command-name to execute.
+
+### Command: xlsx
+Source: [./skills/xlsx.md](./skills/xlsx/SKILLS.md)
+- Description: Create, edit, and analyze spreadsheets with formulas, formatting, data analysis, and visualization
+- Usage: `/xlsx <operation> <spreadsheet-file>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: webapp-testing
+Source: [./skills/webapp-testing/SKILLS.md](./skills/webapp-testing/SKILLS.md)
+- Description: Test local web applications using Playwright - verify functionality, debug UI, capture screenshots
+- Usage: `/webapp-testing <webapp-url-or-local-server>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: systematic-debugging
+Source: [./skills/systematic-debugging/SKILLS.md](./skills/systematic-debugging/SKILLS.md)
+- Description: Systematic four-phase debugging framework - investigate root cause before any fixes
+- Usage: `/systematic-debugging <bug-or-error-description>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: slack-gif-creator
+Source: [./skills/slack-gif-creator/SKILLS.md](./skills/slack-gif-creator/SKILLS.md)
+- Description: Create animated GIFs optimized for Slack with size validation and composable animation primitives
+- Usage: `/slack-gif-creator <gif-type> <animation-concept>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: verification-before-completion
+Source: [./skills/verification-before-completion/SKILLS.md](./skills/verification-before-completion/SKILLS.md)
+- Description: Verify work meets requirements before marking complete - prevents incomplete deliverables
+- Usage: `/verification-before-completion <work-to-verify>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: skill-creator
+Source: [./skills/skill-creator/SKILLS.md](./skills/command/skill-creator/SKILLS.md)
+- Description: Create reusable skills with proper structure, validation, and documentation
+- Usage: `/skill-creator <skill-type> <skill-description>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: test-driven-development
+Source: [./skills/test-driven-development/SKILLS.md](./skills/test-driven-development/SKILLS.md)
+- Description: Write test first, watch it fail, write minimal code to pass - ensures tests actually verify behavior
+- Usage: `/test-driven-development <feature-or-behavior-to-test>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: testing-anti-patterns
+Source: [./skills/testing-anti-patterns/SKILLS.md](./skills/testing-anti-patterns/SKILLS.md)
+- Description: Identify and avoid common testing anti-patterns that create fragile, useless tests
+- Usage: `/testing-anti-patterns <testing-scenario>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: theme-factory
+Source: [./skills/theme-factory/SKILLS.md](./skills/theme-factory/SKILLS.md)
+- Description: Generate consistent themes with proper color systems, typography, and spacing
+- Usage: `/theme-factory <theme-type> <design-requirements>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: root-cause-tracing
+Source: [./skills/root-cause-tracing/SKILLS.md](./skills/root-cause-tracing/SKILLS.md)
+- Description: Trace issues to their root cause using systematic investigation techniques
+- Usage: `/root-cause-tracing <issue-description>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: internal-comms
+Source: [./skills/internal-comms/SKILLS.md](./skills/internal-comms/SKILLS.md)
+- Description: Structure internal communications for clarity, actionability, and team alignment
+- Usage: `/internal-comms <communication-type> <audience>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: pdf
+Source: [./skills/pdf/SKILLS.md](./skills/pdf/SKILLS.md)
+- Description: Create, edit, and analyze PDF documents with proper formatting and structure
+- Usage: `/pdf <operation> <pdf-file>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: mcp-builder
+Source: [./skills/mcp-builder/SKILLS.md](./skills/mcp-builder/SKILLS.md)
+- Description: Build Model Context Protocol servers with proper tool definitions and error handling
+- Usage: `/mcp-builder <server-type> <specifications>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: condition-based-waiting
+Source: [./skills/condition-based-waiting/SKILLS.md](./skills/condition-based-waiting/SKILLS.md)
+- Description: Implement robust waiting mechanisms based on conditions rather than fixed delays
+- Usage: `/condition-based-waiting <condition-type> <timeout-specs>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: pptx
+Source: [./skills/pptx/SKILLS.md](./skills/pptx/SKILLS.md)
+- Description: Create professional PowerPoint presentations with proper structure and design
+- Usage: `/pptx <presentation-type> <content-outline>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: docx
+Source: [./skills/docx/SKILLS.md](./skills/docx/SKILLS.md)
+- Description: Create and edit Word documents with proper formatting and structure
+- Usage: `/docx <operation> <document-specs>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: brand-guidelines
+Source: [./skills/brand-guidelines/SKILLS.md](./skills/brand-guidelines/SKILLS.md)
+- Description: Establish comprehensive brand guidelines with visual identity and usage rules
+- Usage: `/brand-guidelines <brand-type> <requirements>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: brainstorming
+Source: [./skills/brainstorming/SKILLS.md](./skills/brainstorming/SKILLS.md)
+- Description: Facilitate structured brainstorming sessions with proven techniques and frameworks
+- Usage: `/brainstorming <session-type> <topic>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: canvas-design
+Source: [./skills/canvas-design/SKILLS.md](./skills/canvas-design/SKILLS.md)
+- Description: Design visual canvases for business models, user journeys, and strategic planning
+- Usage: `/canvas-design <canvas-type> <design-goals>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: artifacts-builder
+Source: [./skills/artifacts-builder/SKILLS.md](./skills/artifacts-builder/SKILLS.md)
+- Description: Build structured artifacts with proper validation, formatting, and documentation
+- Usage: `/artifacts-builder <artifact-type> <specifications>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: algorithmic-art
+Source: [./skills/algorithmic-art/SKILLS.md](./skills/algorithmic-art/SKILLS.md)
+- Description: Generate algorithmic art with mathematical patterns and aesthetic principles
+- Usage: `/algorithmic-art <art-type> <pattern-specs>`
+- Full definition: open the source file above (content not embedded)
+
+### Command: code-review
+Source: [./skills/code-review/SKILLS.md](./skills/code-review/SKILLS.md)
+- Description: Conduct thorough code reviews with focus on quality, security, and maintainability
+- Usage: `/code-review <review-scope> <focus-areas>`
+- Full definition: open the source file above (content not embedded)
+

package/packages/claude/agents/1-create-prd.md

@@ -12,6 +12,7 @@ You are an expert Product Manager creating clear, actionable PRDs for junior dev
 2. **Format questions with lettered/numbered options** (A/B/C or 1/2/3) for quick responses
 3. **Generate comprehensive PRD** following structure below
 4. **Save as** `/tasks/[n]-prd-[feature-name].md` (n = 0001, 0002, etc.)
+5. **Agents** (../AGENTS.md): After saving the PRD to `/tasks/[n]-prd-[feature-name].md`, invoke the `2-generate-tasks` agent to process the PRD output and generate a granular, actionable task list for implementation.
 
 ## Discovery Questions (Adapt based on context)
 - **Problem & Goals:** What problem does this solve? Primary goal? (Options: A) Increase engagement, B) Reduce friction, C) Add capability, D) Other)

package/packages/claude/agents/2-generate-tasks.md

@@ -24,6 +24,7 @@ You are an expert Technical Program Manager translating PRDs into precise, actio
 10. **Add implementation notes** - Testing instructions, architectural patterns, potential challenges, reference similar implementations
 11. **Generate final output** - Markdown format below, proper numbering (1.0, 1.1, 2.0...), checkbox formatting
 12. **Save and confirm** - Write to `/tasks/tasks-[prd-base-filename].md`, confirm completion
+13. **Load subagent** (../AGENTS.md): use output from previous steps ONLY on next step 3-process-task-list
 
 ## Output Format Requirements
 

package/packages/claude/agents/3-process-task-list.md

@@ -28,15 +28,12 @@ You are an expert project manager managing markdown task lists with strict seque
 a) **Run full test suite** (`pytest`/`npm test`/`cargo test`/etc.)
    - Review output carefully
    - If ANY fail: STOP, report failure, fix with user, re-run
-
 b) **Stage changes** (only if tests pass)
    - `git add .`
    - Verify with `git status`
-
 c) **Clean up**
    - Remove: temp files, debug code, console.log, commented code, test data, cache files
    - Verify: no secrets (API keys, passwords, tokens)
-
 d) **Commit with conventional format:**
    ```
    git commit -m "<type>: <summary>" -m "- <change 1>" -m "- <change 2>" -m "Related to <task-id> in PRD"