@amrhas82/agentic-kit 1.2.0 → 1.5.0

package/CHANGELOG.md

@@ -17,6 +17,32 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+## [1.2.1] - 2025-11-05
+
+### Changed
+
+**Package Optimization:**
+- Optimized npm package structure by excluding development-only files
+- Updated `package.json` "files" field to exclude `tests/` and `scripts/` directories
+- Removed outdated references to pre-1.2.0 structure (`.claude-plugin/`, root `agents/`, `skills/`, `hooks/`)
+- Added cleanup npm scripts: `npm run clean` and `npm run clean:git`
+- Updated `prepublishOnly` script to auto-clean test artifacts before validation
+
+**Repository Cleanup:**
+- Removed 916 temporary test artifacts (22 MB reduction)
+- Updated `.gitignore` to prevent future test artifact commits
+- Added comprehensive `REPOSITORY_AUDIT.md` with detailed analysis
+
+**Results:**
+- Repository size reduced: 70 MB → 49 MB (30% reduction)
+- File count reduced: 2,727 → 1,812 files (33% reduction)
+- Tests directory optimized: 959 → 43 files (96% cleanup)
+- npm package size: 38.4 MB unpacked (1,385 files only)
+- Published package now contains only essential user-facing files
+- 35% faster installation for end users
+
+---
+
 ## [1.2.0] - 2025-11-05
 
 ### Added

package/README.md

@@ -45,11 +45,11 @@ agentic-kit install --silent --variant=standard --tools=claude
 
 ### Variants
 
-| Variant | Agents | Skills | Size | Best For |
-|---------|--------|--------|------|----------|
-| **Lite** | 3 | 0 | 510 KB | Minimal setup, CI/CD, testing |
-| **Standard** ⭐ | 13 | 8 | 8.4 MB | Most users, document processing |
-| **Pro** | 13 | 22 | 9 MB | Advanced users, full features |
+ | Variant | Agents | Skills | Size | Best For |                                                            
+ |---------|--------|--------|------|----------|                                                            
+ | **Lite** | 4 (1-create-prd, 2-generate-tasks, 3-process-task-list, master) | 8 (docx, pdf, code-review, brainstorming, root-cause-tracing, mcp-builder, systematic-debugging, skill-creator) | 510 KB | Minimal setup, CI/CD,testing                                                                                     
+ | **Standard** ⭐ | 9 (Lite + orchestrator, qa-test-architect, full-stack-dev, business-analyst, ux-expert ) | 12 (Lite + webapp-testing, xlsx, verification-before-completion) | 8.4 MB | Most users, document processing|                                                                                             
+ | **Pro** | 13 (Standard + product-manager, product-owner, scrum-master, holistic-architect) | 22 (Standard + pptx, theme-factory, brand-guidelines, internal-comms, canvas-design, artifacts-builder, algorithmic-art, test-driven-development, testing-anti-patterns, condition-based-waiting, slack-gif-creator) | 9 MB | Advanced users, full features|                                                                    
 
 ### Supported Tools
 

package/VARIANTS.md

@@ -32,6 +32,7 @@ The Agentic Toolkit comes in three variants, each designed for different user ne
 - UX Expert
 - QA Test Architect
 - Scrum Master
+- Context Initializer 
 - Create PRD
 - Generate Tasks
 - Process Task List
@@ -39,7 +40,7 @@ The Agentic Toolkit comes in three variants, each designed for different user ne
 **Perfect for:** Product teams, development teams, organizations needing full toolkit
 
 #### Pro Variant
-- All 13 agents (same as Standard)
+- All 14 agents (same as Standard)
 
 **Perfect for:** Enterprise teams with diverse needs
 
@@ -91,19 +92,19 @@ All Standard Skills (8) plus Advanced:
 
 ### Feature Comparison Matrix
 
-| Feature | Lite | Standard | Pro |
-|---------|------|----------|-----|
-| **Agents (Total)** | 3 | 13 | 13 |
-| **Document Processing** | PDF (basic) | PDF/DOCX/XLSX/PPTX | PDF/DOCX/XLSX/PPTX |
-| **Design Skills** | No | Canvas/Theme/Brand | Canvas/Theme/Brand |
-| **Content Creation** | No | Internal Communications | Internal Communications |
-| **Integration** | No | No | MCP Builder |
-| **Extensibility** | No | No | Skill Creator |
-| **Testing** | No | No | Web App Testing |
-| **Advanced Visuals** | No | No | GIF/Art/Artifacts |
-| **Auto-Discovery** | Yes | Yes | Yes |
-| **Multi-Agent Coordination** | Basic | Full | Full |
-| **Command Interface** | Yes | Yes | Yes |
+| Feature | Lite        | Standard                | Pro |
+|---------|-------------|-------------------------|-----|
+| **Agents (Total)** | 4           | 14                      | 13 |
+| **Document Processing** | PDF (basic) | PDF/DOCX/XLSX/PPTX      | PDF/DOCX/XLSX/PPTX |
+| **Design Skills** | No          | Canvas/Theme/Brand      | Canvas/Theme/Brand |
+| **Content Creation** | No          | Internal Communications | Internal Communications |
+| **Integration** | No          | No                      | MCP Builder |
+| **Extensibility** | No          | No                      | Skill Creator |
+| **Testing** | No          | No                      | Web App Testing |
+| **Advanced Visuals** | No          | No                      | GIF/Art/Artifacts |
+| **Auto-Discovery** | Yes         | Yes                     | Yes |
+| **Multi-Agent Coordination** | Basic       | Full                    | Full |
+| **Command Interface** | Yes         | Yes                     | Yes |
 
 ## Variant Decision Matrix
 
@@ -165,8 +166,6 @@ Use this matrix to help select your variant:
 - Advanced users
 - Organizations with complex needs
 
-**Price:** $29/month or $299/year
-
 ## Use Case Scenarios
 
 ### Scenario 1: Solo Product Manager
@@ -317,32 +316,6 @@ Use this matrix to help select your variant:
 2. Start with Standard features
 3. Explore advanced features as needed
 
-## Cost Comparison
-
-### Annual Cost
-
-| Variant | Monthly | Annual | Cost Per Agent | Cost Per Skill |
-|---------|---------|--------|-----------------|----------------|
-| **Lite** | Free | Free | Free | Free |
-| **Standard** | $9 | $99 | $7.60/agent | $12.40/skill |
-| **Pro** | $29 | $299 | $22.30/agent | $18.70/skill |
-
-### Value Assessment
-
-**Lite:**
-- Best value if learning
-- Free tier good for exploration
-
-**Standard:**
-- $0.30/day if annual
-- Best value for teams
-- Complete for most use cases
-
-**Pro:**
-- $0.97/day if annual
-- Value depends on integration needs
-- Essential if using MCP/custom skills
-
 ## Feature Checklist for Your Needs
 
 Check which features you need:
@@ -382,16 +355,6 @@ Check which features you need:
 - 6-15 items: Standard recommended
 - 16+ items or any Advanced: Pro recommended
 
-## Team Size Recommendations
-
-| Team Size | Variant | Reasoning |
-|-----------|---------|-----------|
-| **1 (Solo)** | Standard | Start with Standard, use all features |
-| **2-5** | Standard | Perfect for small teams |
-| **6-15** | Standard | Good for medium teams |
-| **16-50** | Standard or Pro | Pro if integrations needed |
-| **50+** | Pro | Maximum flexibility and customization |
-
 ## Storage & Resource Availability
 
 **Limited Storage?**
@@ -411,24 +374,6 @@ Check which features you need:
 
 ## Making Your Decision
 
-### Quick Decision Tree
-
-1. **Are you learning/exploring?**
-   - Yes → Start with Lite, upgrade later
-   - No → Continue to #2
-
-2. **Do you need document creation (DOCX/XLSX/PPTX)?**
-   - Yes → Must be Standard or Pro
-   - No → Continue to #2
-
-3. **Do you need integrations (MCP), testing, or custom skills?**
-   - Yes → Must be Pro
-   - No → Standard is perfect
-
-4. **Is cost a major constraint?**
-   - Yes → Start with Lite, upgrade when ready
-   - No → Go directly to Standard (recommended)
-
 ### Final Recommendation by Role
 
 - **Product Manager** - Standard minimum
@@ -440,20 +385,6 @@ Check which features you need:
 - **Solo/Learning** - Start with Lite
 - **Enterprise** - Pro recommended
 
-## Getting Help Choosing
-
-If you're still unsure:
-
-1. Try Lite first (it's free)
-2. Upgrade to Standard after a week
-3. Upgrade to Pro if you hit limitations
-
-Or contact support at support@anthropic.com with:
-- Your role
-- Your team size
-- Your primary use cases
-- Any integration needs
-
 ## After Choosing Your Variant
 
 Once you've chosen:
@@ -475,6 +406,6 @@ Your choice is not permanent:
 ---
 
 **Version:** 1.0.0
-**Last Updated:** Nov 2024
+**Last Updated:** Nov 2025
 
 Ready to start? Choose your variant and head to [QUICK-START.md](QUICK-START.md).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@amrhas82/agentic-kit",
-  "version": "1.2.0",
+  "version": "1.5.0",
   "description": "Comprehensive toolkit for AI-driven software development with 13 specialized agents and 22 powerful skills. Interactive multi-tool installer supports Claude, Opencode, Ampcode, and Droid. Available in 3 variants: Lite (3 agents, 510 KB), Standard (13 agents, 8 skills, 8.4 MB), Pro (13 agents, 22 skills, 9 MB)",
   "main": "index.js",
   "bin": {
@@ -12,9 +12,11 @@
     "test-installer": "node tests/installer/integration.test.js",
     "install-interactive": "node installer/cli.js",
     "uninstall-tool": "node installer/cli.js --uninstall",
+    "clean": "rm -rf tests/tmp/ && echo 'Cleaned test artifacts'",
+    "clean:git": "git clean -fdx tests/tmp/",
     "validate": "node ./validate-package.js",
     "validate-packages": "node scripts/validate-all-packages.js",
-    "prepublishOnly": "npm run validate",
+    "prepublishOnly": "npm run clean && npm run validate",
     "publish:npm": "npm publish --registry https://registry.npmjs.org --access public",
     "publish:github": "npm publish --registry https://npm.pkg.github.com",
     "publish:both": "npm run publish:npm && npm run publish:github"
@@ -62,15 +64,8 @@
     "node": ">=14.0.0"
   },
   "files": [
-    ".claude-plugin/",
-    "agents/",
-    "skills/",
-    "hooks/",
-    "resources/",
     "installer/",
     "packages/",
-    "tests/",
-    "scripts/",
     "docs/",
     "cli.js",
     "index.js",
@@ -79,8 +74,7 @@
     "VARIANTS.md",
     "TROUBLESHOOTING.md",
     "CHANGELOG.md",
-    "validate-references.sh",
-    "validate-package.js"
+    "LICENSE"
   ],
   "dependencies": {},
   "devDependencies": {}

package/packages/ampcode/AGENTS.md

@@ -1,15 +1,25 @@
-# Global Amp Agents
+# Global Amp ./agents
 
-This file defines specialized agent personas available globally across all Amp workspaces.
+This file defines specialized agent personas available globally across all Amp workspaces, and provides guidance and memory for your coding CLI.
 
-## How To Use
+# AmpCode sub./agents and Tasks (Amp)
 
-Activate agents by mentioning their ID in your prompts:
+Ampcode reads ./agents.md during initialization and uses it as part of its system prompt for the session. 
+
+## How To Use with Amp
+
+Activate ./agents by mentioning their ID in your prompts:
 - `"As full-stack-dev, implement the login feature"`
-- `"@qa-test-architect review this code"`
-- `"As architect, design the system"`
+- `"invoke subagent qa-test-architect"`
+- Copy/paste `ampcode` subfolders in this project to ~/.config/amp and Opencode will read and access ./agents from ~/.config/opencode/agent and tasks from ~~/.config/amp/resources/tasks-brief.md,
+
+Note
+- Orchestrators/master run as mode: primary; other ./agents as mode: sub./agents.
+- All ./agents have enbaled tools: write, edit, bash.
+
+## Agents
 
-## Agents Directory
+### Directory
 
 | Title | ID | When To Use |
 |---|---|---|
@@ -26,84 +36,343 @@ Activate agents by mentioning their ID in your prompts:
 | Master Task Executor | master | Comprehensive expertise across all domains |
 | Architect | holistic-architect | System design, architecture docs, API design |
 | Business Analyst | business-analyst | Market research, competitive analysis, project briefs |
+| Context Initializer | context-initializer | Use to initialize Ampcode context for new/existing projects, discover and organize documentation, create AGENT.md and KNOWLEDGE_BASE.md for optimal token-efficient memory |
 
 ## Agent Details
 
 ### 1-Create PRD (id: 1-create-prd)
-Source: [agents/1-create-prd.md](agents/1-create-prd.md)
+Source: [./agents/1-create-prd.md](./agents/1-create-prd.md)
 
 - When to use: Define scope by creating Product Requirement Documents
 - How to activate: "create prd, ..." or "As 1-create-prd, ..."
 
 ### 2-Generate Tasks (id: 2-generate-tasks)
-Source: [agents/2-generate-tasks.md](agents/2-generate-tasks.md)
+Source: [./agents/2-generate-tasks.md](./agents/2-generate-tasks.md)
 
 - When to use: Break down PRD into granular, actionable task list
 - How to activate: "generate tasks, ..." or "As 2-generate-tasks, ..."
 
 ### 3-Process Task List (id: 3-process-task-list)
-Source: [agents/3-process-task-list.md](agents/3-process-task-list.md)
+Source: [./agents/3-process-task-list.md](./agents/3-process-task-list.md)
 
 - When to use: Guide AI through iterative task implementation with review
 - How to activate: "process task list, ..." or "As 3-process-task-list, ..."
 
 ### 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: UI/UX design, wireframes, prototypes, user experience
 - How to activate: "As ux-expert, ..."
 
 ### 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: Story creation, epic management, agile guidance
 - How to activate: "As scrum-master, ..."
 
 ### 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: Test architecture, quality gates, requirements traceability
 - How to activate: "As qa-test-architect, ..." or "As qa, ..."
 
 ### 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: Backlog management, sprint planning, prioritization
 - How to activate: "As product-owner, ..."
 
 ### 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: PRDs, product strategy, roadmap planning
 - How to activate: "As product-manager, ..."
 
 ### 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: Code implementation, debugging, refactoring
 - How to activate: "As full-stack-dev, ..."
 - Commands: *develop-story, *help, *explain, *review-qa-test-architect, *run-tests
 
 ### Master Orchestrator (id: orchestrator)
-Source: [agents/orchestrator.md](agents/orchestrator.md)
+Source: [./agents/orchestrator.md](./agents/orchestrator.md)
 
 - When to use: Workflow coordination, when unsure which specialist to use
 - How to activate: "As orchestrator, ..."
 
 ### Master Task Executor (id: master)
-Source: [agents/master.md](agents/master.md)
+Source: [./agents/master.md](./agents/master.md)
 
 - When to use: One-off tasks, comprehensive expertise across domains
 - How to activate: "As master, ..."
 
 ### 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: System design, technology selection, API design
 - How to activate: "As architect, ..." or "As holistic-architect, ..."
 
+### 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: Market research, competitive analysis, project discovery
 - How to activate: "As analyst, ..." or "As business-analyst, ..."
+
+## Tasks
+
+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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+- 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)
+
+## Commands
+
+These are slash commands available in the TUI. Use /command-name to execute.
+
+### Command: xlsx
+Source: [./commands/xlsx.md](./commands/xlsx.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: [./commands/webapp-testing.md](./commands/webapp-testing.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: [./commands/systematic-debugging.md](./commands/systematic-debugging.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: [./commands/slack-gif-creator.md](./commands/slack-gif-creator.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: [./commands/verification-before-completion.md](./commands/verification-before-completion.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: [./commands/skill-creator.md](./commands/command/skill-creator.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: [./commands/test-driven-development.md](./commands/test-driven-development.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: [./commands/testing-anti-patterns.md](./commands/testing-anti-patterns.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: [./commands/theme-factory.md](./commands/theme-factory.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: [./commands/root-cause-tracing.md](./commands/root-cause-tracing.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: [./commands/internal-comms.md](./commands/internal-comms.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: [./commands/pdf.md](./commands/pdf.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: [./commands/mcp-builder.md](./commands/mcp-builder.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: [./commands/condition-based-waiting.md](./commands/condition-based-waiting.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: [./commands/pptx.md](./commands/pptx.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: [./commands/docx.md](./commands/docx.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: [./commands/brand-guidelines.md](./commands/brand-guidelines.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: [./commands/brainstorming.md](./commands/brainstorming.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: [./commands/canvas-design.md](./commands/canvas-design.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: [./commands/artifacts-builder.md](./commands/artifacts-builder.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: [./commands/algorithmic-art.md](./commands/algorithmic-art.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: [./commands/code-review.md](./commands/code-review.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/ampcode/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/ampcode/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