liteagents 2.4.0

package/packages/subagentic-manual.md

@@ -0,0 +1,349 @@
+# Subagentic Manual
+
+Production-ready AI agent framework providing specialized subagents, workflow commands, and development skills for **Claude Code**, **OpenCode**, **Ampcode**, and **Droid**. Deploy expert AI personas instantly with zero configuration.
+
+---
+
+## Why Subagentic?
+
+**The Challenge**: Generic AI assistants lack specialized expertise and systematic workflows, leading to inconsistent results and context overload.
+
+**The Solution**: Subagentic provides:
+- **Role-Specialized Agents** - Expert personas (architect, QA, product manager) with domain-specific knowledge
+- **Systematic Workflows** - Proven development patterns (PRD → Tasks → Implementation)
+- **Orchestrator-First Routing** - Automatic workflow matching based on user intent
+- **Frontmatter-Based Discovery** - All resources self-describe via YAML frontmatter
+- **Platform Agnostic** - Works across Claude Code, OpenCode, Ampcode, and Droid
+
+**The Result**: Predictable, high-quality outputs from specialized agents following best practices, without manually switching contexts or crafting complex prompts.
+
+---
+
+## Quick Start
+
+Clone the toolkit:
+```bash
+git clone https://github.com/amrhas82/agentic-toolkit
+cd agentic-toolkit/ai/subagentic
+```
+
+Install for your platform:
+
+| Platform | Installation | What's Included |
+|----------|--------------|-----------------|
+| **Claude Code** | `cp -r claude/* ~/.claude/` | 11 subagents + 10 skills + 10 commands |
+| **Droid** | `cp -r droid/* ~/.factory/` | 20 commands (subagent references) |
+| **Ampcode** | `cp -r ampcode/* ~/.config/amp/` | 11 subagents + 10 skills + 10 commands |
+| **OpenCode** | `cp -r opencode/* ~/.config/opencode/` | 20 commands (subagent references) |
+
+**Key Difference**:
+- **Claude Code / Ampcode** implement full subagent system with orchestrator
+- **Droid/OpenCode** provide commands only + reference documentation for subagents
+
+---
+
+## What's Included
+
+### Claude Code / Ampcode (Full System)
+
+**11 Subagents** - Expert personas with specialized knowledge
+- 3 Workflow Agents (PRD, Tasks, Implementation)
+- 8 Specialist Agents (UX, QA, Architecture, Product, Development, etc.)
+
+**10 Skills** - Auto-triggering workflow components
+- test-driven-development, testing-anti-patterns, verification-before-completion (auto-trigger)
+- brainstorming, code-review, systematic-debugging, docs-builder, etc.
+
+**10 Commands** - Simple workflow helpers
+- debug, explain, git-commit, optimize, refactor, review, security, ship, stash, test-generate
+
+**Orchestration System**
+- Automatic intent matching to 9 workflow patterns
+- Conditional decision points with user approval gates
+- Selective context injection
+
+### Droid/OpenCode (Commands Only)
+
+**20 Commands** - All workflow capabilities in command form
+- Combines skills + commands into unified command set
+- Same functionality, different invocation model (no auto-triggering)
+- Includes reference documentation for subagents
+
+**No Orchestrator** - Direct command invocation only
+
+---
+
+## Subagents
+
+### Workflow Agents (3)
+
+| Agent | Purpose |
+|-------|---------|
+| **1-create-prd** | Define scope with structured Product Requirement Documents |
+| **2-generate-tasks** | Break PRDs into granular, actionable task lists |
+| **3-process-task-list** | Execute tasks iteratively with progress tracking and review checkpoints |
+
+**Pattern**: PRD → Tasks → Iterative Implementation → Review → Complete
+
+### Specialist Agents (8)
+
+| Agent | Purpose |
+|-------|---------|
+| **orchestrator** | Analyze intent, coordinate workflows, route to optimal agent sequences |
+| **ui-designer** | UI/UX design, wireframes, prototypes, accessibility, design systems |
+| **code-developer** | Implementation, debugging, refactoring, code best practices |
+| **quality-assurance** | Test architecture, quality gates, requirements traceability, risk assessment |
+| **system-architect** | System design, technology selection, API design, scalability planning |
+| **feature-planner** | Epics, user stories, prioritization, backlog management, retrospectives |
+| **market-researcher** | Market analysis, competitive research, project discovery, brainstorming |
+| **context-builder** | Initialize project context, discover documentation, create knowledge bases |
+
+---
+
+## Commands Reference
+
+### Claude Code / Ampcode: 20 Total (10 Skills + 10 Commands)
+
+**Auto-Triggering Skills (3)**
+- `test-driven-development` - Write test first, watch fail, minimal passing code
+- `testing-anti-patterns` - Prevent mocking anti-patterns and test pollution
+- `verification-before-completion` - Run verification before claiming done
+
+**Manual Skills (7)**
+- `brainstorming` - Refine rough ideas through collaborative questioning
+- `code-review` - Review implementation against requirements
+- `condition-based-waiting` - Replace timeouts with condition polling
+- `docs-builder` - Create structured /docs hierarchy
+- `root-cause-tracing` - Trace bugs backward through call stack
+- `skill-creator` - Guide for creating new skills
+- `systematic-debugging` - Four-phase debugging framework
+
+**Simple Commands (10)**
+- `debug` - Systematic investigation techniques
+- `explain` - Explain code for newcomers
+- `git-commit` - Intelligent commit creation
+- `optimize` - Performance analysis
+- `refactor` - Maintain behavior while improving code
+- `review` - Comprehensive code review
+- `security` - Vulnerability scanning
+- `ship` - Pre-deployment checklist
+- `stash` - Save session context for compaction recovery or handoffs
+- `test-generate` - Test suite generation
+
+### Droid/OpenCode: 20 Commands
+
+Same functionality as skills+commands, but:
+- All invoked as commands (no auto-triggering)
+- Unified command set
+- No orchestrator integration
+
+**Command Categories**:
+- **Development & Testing (9)**: test-driven-development, testing-anti-patterns, test-generate, code-review, systematic-debugging, root-cause-tracing, debug, condition-based-waiting, verification-before-completion
+- **Code Operations (6)**: refactor, optimize, explain, review, security, ship
+- **Session & Planning (5)**: brainstorming, skill-creator, docs-builder, git-commit, stash
+
+---
+
+## Usage Patterns
+
+### Claude Code / Ampcode: Orchestrator-First (Recommended)
+
+The orchestrator analyzes your request and routes to optimal workflows automatically.
+
+**How it works**:
+1. Make natural requests: "Add login feature", "Review this PR", "Plan next sprint"
+2. Orchestrator matches intent to workflow patterns
+3. Conditional gates ask for approval before each phase
+4. Specialists execute with domain expertise
+
+**Example Flow - Feature Development**:
+```
+User: "Add authentication feature"
+  ↓
+Orchestrator: "Research competitive approaches first?" [Yes/No]
+  ↓ Yes
+Market Researcher: [Gathers auth patterns, OAuth vs JWT tradeoffs]
+  ↓
+Orchestrator: "Create formal PRD?" [Yes/No]
+  ↓ Yes
+1-Create-PRD: [Structured requirements document]
+  ↓
+Orchestrator: "Generate implementation tasks?" [Yes/No]
+  ↓ Yes
+2-Generate-Tasks: [20 granular tasks with acceptance criteria]
+  ↓
+Orchestrator: "Start systematic implementation?" [Yes/No]
+  ↓ Yes
+3-Process-Task-List: [Iterative implementation with review gates]
+```
+
+**Bypass Options**:
+- Direct agent: `@quality-assurance review this code`
+- Role syntax: `As system-architect, design the API layer`
+- Skills: `/test-driven-development login-feature`
+
+### 9 Pre-Defined Workflow Patterns
+
+1. **Feature Discovery Flow** - Research → PRD → Tasks → Implementation
+2. **Product Definition Flow** - Strategy → Epics/Stories → Technical Assessment
+3. **Story Implementation Flow** - Validate → Implement → QA Gate
+4. **Architecture Decision Flow** - Constraints → Analysis → Alignment
+5. **UI Development Flow** - Design → PRD (optional) → Implement → Validate
+6. **Bug Triage Flow** - Investigate → Severity Assessment → Fix/Backlog
+7. **Brownfield Discovery Flow** - Context Building → Documentation → Assessment
+8. **Quality Validation Flow** - Review → Pass/Concerns/Fail → Remediation
+9. **Sprint Planning Flow** - Prioritize → Stories → Criteria → Tasks
+
+Each pattern includes conditional decision points requiring user approval.
+
+### Droid/OpenCode: Direct Command Invocation
+
+No orchestrator - invoke commands directly:
+- `/debug <issue>`
+- `/refactor <code-section>`
+- `/test-driven-development <feature>`
+
+Subagent workflows require manual coordination.
+
+---
+
+## Value Proposition
+
+### For Individual Developers
+- **Instant Expertise** - Access 11 specialist agents without hiring
+- **Consistent Quality** - Best practices built into every agent
+- **Faster Iteration** - Systematic workflows reduce trial-and-error
+- **Learning Tool** - Observe expert patterns and decision-making
+
+### For Teams
+- **Standardized Processes** - Shared agent definitions ensure consistency
+- **Onboarding Acceleration** - New members learn patterns through agent interactions
+- **Documentation Culture** - context-builder and docs-builder promote knowledge capture
+- **Cross-Functional Collaboration** - Product, design, and engineering agents work together
+
+### For Technical Leaders
+- **Scalable Expertise** - Multiply senior-level guidance across projects
+- **Quality Gates** - Built-in review and validation checkpoints
+- **Architectural Consistency** - system-architect ensures coherent design decisions
+- **Reduced Context Switching** - Specialists handle domain-specific work
+
+---
+
+## Platform Architecture
+
+### Claude Code
+```
+~/.claude/
+├── CLAUDE.md           # Registry + orchestrator workflows
+├── agents/             # 11 subagent implementations (*.md)
+├── skills/             # 11 skills (subdirectories with SKILL.md)
+└── commands/           # 10 commands (*.md)
+```
+
+**Features**:
+- Full subagent system with orchestrator
+- Auto-triggering skills
+- Workflow pattern matching
+- Progressive agent loading
+
+### Ampcode
+```
+~/.config/amp/
+├── AGENT.md            # Reference doc (subagents + commands)
+├── agents/             # 11 subagent implementations (*.md)
+├── skills/             # 11 skills (subdirectories with SKILL.md)
+└── commands/           # 10 commands (*.md)
+```
+
+**Features**:
+- Full subagent system with orchestrator
+- Auto-triggering skills
+- Workflow pattern matching
+
+### Droid
+```
+~/.factory/
+├── AGENTS.md           # Reference doc (subagents + commands)
+└── commands/           # 20 commands (*.md)
+```
+
+**Features**:
+- Commands only (no subagent implementations)
+- Reference table for subagents
+- Direct command invocation
+
+### OpenCode
+```
+~/.config/opencode/
+├── AGENTS.md           # Reference doc (subagents + commands)
+└── command/            # 20 commands (*.md)
+```
+
+**Features**:
+- Commands only (no subagent implementations)
+- Reference table for subagents
+- Direct command invocation
+
+---
+
+## Frontmatter Architecture
+
+All resources are self-describing via YAML frontmatter for auto-discovery:
+
+**Subagents** (`agents/*.md`):
+```yaml
+---
+id: code-developer
+title: Full Stack Developer
+description: Implement code, debug, refactor
+when_to_use: Use for code implementation, debugging, refactoring, and development best practices
+model: inherit
+color: purple
+---
+```
+
+**Skills** (`skills/*/SKILL.md`):
+```yaml
+---
+id: test-driven-development
+name: test-driven-development
+description: Write test first, watch it fail, write minimal code to pass
+usage: /test-driven-development <feature-or-behavior-to-test>
+auto_trigger: true
+---
+```
+
+**Commands** (`commands/*.md`):
+```yaml
+---
+id: debug
+name: debug
+description: Debug an issue systematically using structured investigation techniques
+usage: /debug <issue-description>
+argument-hint: [description of the problem]
+---
+```
+
+This enables:
+- Dynamic registry building by CLIs
+- Single source of truth (no manual registries)
+- Consistent metadata across platforms
+- Easy extensibility
+
+---
+
+## Contributing
+
+Contributions welcome for:
+- New specialist agents for additional domains
+- Additional workflow patterns
+- Platform-specific optimizations
+- Documentation improvements
+
+See repository for contribution guidelines.
+
+---
+
+**License**: [Specify license]
+**Repository**: https://github.com/amrhas82/agentic-toolkit
+**Issues**: https://github.com/amrhas82/agentic-toolkit/issues

package/postinstall.js

@@ -0,0 +1,21 @@
+#!/usr/bin/env node
+
+const colors = {
+  bright: '\x1b[1m',
+  cyan: '\x1b[36m',
+  green: '\x1b[32m',
+  yellow: '\x1b[33m',
+  reset: '\x1b[0m'
+};
+
+console.log('');
+console.log(`${colors.green}==========================================`);
+console.log(`  Agentic Kit Installation Complete`);
+console.log(`==========================================${colors.reset}`);
+console.log('');
+console.log(`${colors.bright}${colors.yellow}Next step: Run the installer${colors.reset}`);
+console.log('');
+console.log(`  ${colors.cyan}$ agentic-kit${colors.reset}`);
+console.log('');
+console.log(`${colors.green}==========================================${colors.reset}`);
+console.log('');

package/tools/ampcode/manifest-template.json

@@ -0,0 +1,14 @@
+{
+  "tool": "ampcode",
+  "name": "Ampcode",
+  "description": "Amplified AI codegen workflows",
+  "default_path": "~/.amp",
+  "optimization": "amplified-codegen",
+  "integration_type": "cli",
+  "manifest_format": "ampcode-config",
+  "supported_variants": ["lite", "standard", "pro"],
+  "agent_format": "amplified-optimized",
+  "skill_compatibility": "ampcode-native",
+  "resource_format": "enhanced",
+  "hook_integration": "ampcode-hooks"
+}

package/tools/claude/manifest-template.json

@@ -0,0 +1,14 @@
+{
+  "tool": "claude",
+  "name": "Claude Code",
+  "description": "Conversational AI development assistant",
+  "default_path": "~/.claude",
+  "optimization": "conversational-ai",
+  "integration_type": "plugin",
+  "manifest_format": "claude-plugin",
+  "supported_variants": ["lite", "standard", "pro"],
+  "agent_format": "claude-conversational",
+  "skill_compatibility": "claude-native",
+  "resource_format": "markdown",
+  "hook_integration": "claude-plugin"
+}

package/tools/droid/manifest-template.json

@@ -0,0 +1,14 @@
+{
+  "tool": "droid",
+  "name": "Droid",
+  "description": "Mobile-focused AI codegen tool",
+  "default_path": "~/.factory",
+  "optimization": "mobile-codegen",
+  "integration_type": "cli",
+  "manifest_format": "droid-config",
+  "supported_variants": ["lite", "standard", "pro"],
+  "agent_format": "mobile-optimized",
+  "skill_compatibility": "droid-native",
+  "resource_format": "mobile-focused",
+  "hook_integration": "droid-hooks"
+}

package/tools/opencode/manifest-template.json

@@ -0,0 +1,14 @@
+{
+  "tool": "opencode",
+  "name": "Opencode",
+  "description": "CLI-based AI codegen tool",
+  "default_path": "~/.config/opencode",
+  "optimization": "cli-codegen",
+  "integration_type": "cli",
+  "manifest_format": "opencode-config",
+  "supported_variants": ["lite", "standard", "pro"],
+  "agent_format": "cli-optimized",
+  "skill_compatibility": "cli-native",
+  "resource_format": "terminal",
+  "hook_integration": "cli-hooks"
+}