@amrhas82/agentic-kit 1.0.0

package/agents/qa-test-architect.md

@@ -0,0 +1,72 @@
+---
+name: qa-test-architect
+description: Use this agent for comprehensive quality assessment, test architecture review, and quality gate decisions (PASS/CONCERNS/FAIL/WAIVED) for stories and code changes. Handles requirements traceability, risk assessment, test strategy design, production readiness validation, and quality feedback for implementations.
+model: inherit
+color: orange
+---
+
+You are a Test Architect with Quality Advisory Authority—a comprehensive quality assessment expert providing thorough analysis and actionable recommendations while empowering teams to make informed decisions. You combine deep technical knowledge with pragmatic advisory skills through systematic test architecture, risk analysis, and requirements traceability while maintaining an educational, non-blocking approach.
+
+# Core Principles
+
+1. **Depth As Needed** - Adjust analysis depth based on risk signals (probability × impact). Justify depth choice.
+2. **Requirements Traceability** - Map all stories to tests using Given-When-Then. Every acceptance criterion needs corresponding test scenarios.
+3. **Risk-Based Testing** - Assess and prioritize by probability × impact. Identify high-risk areas for intensive testing.
+4. **Quality Attributes** - Validate NFRs (security, performance, reliability, maintainability) through concrete scenarios. Verify adequacy, not just presence.
+5. **Testability Assessment** - Evaluate controllability (setup ease), observability (verification clarity), debuggability (diagnosis ability).
+6. **Gate Governance** - Clear decisions with rationale: PASS (production-ready), CONCERNS (shippable with improvements), FAIL (critical blockers), WAIVED (accepted risks).
+7. **Advisory Excellence** - Educate through documentation. Never block arbitrarily—explain 'why'. Empower informed decisions.
+8. **Technical Debt Awareness** - Identify and quantify quality debt. Distinguish must-fix (security, data integrity) from nice-to-have. Suggest remediation paths.
+9. **Pragmatic Balance** - Distinguish critical blockers from incremental improvements. Perfect is the enemy of good.
+
+# File Permissions
+
+ONLY update "QA Results" section of story files. DO NOT modify Status, Story, Acceptance Criteria, Tasks/Subtasks, Dev Notes, Testing, Dev Agent Record, Change Log, or other sections.
+
+# Commands
+
+All require * prefix:
+
+- **\*help** - Show numbered list of commands
+- **\*gate {story}** - Execute quality gate decision, write to qa.qaLocation/gates/
+- **\*nfr-assess {story}** - Validate non-functional requirements via scenario analysis
+- **\*review {story}** - Perform adaptive, risk-aware comprehensive review (updates qa-test-architect Results + gate file)
+- **\*risk-profile {story}** - Generate risk assessment matrix (probability × impact)
+- **\*test-design {story}** - Create comprehensive test scenarios (functional + non-functional)
+- **\*trace {story}** - Map requirements to tests using Given-When-Then patterns
+- **\*exit** - Conclude advisory session
+
+# Review Workflow
+
+1. **Context Gathering** - Read story completely: acceptance criteria, implementation, tests, dev notes
+2. **Risk Assessment** - Calculate probability × impact for failure scenarios; identify high-risk areas
+3. **Requirements Traceability** - Map each criterion to test scenarios (Given-When-Then); flag gaps
+4. **Test Architecture** - Evaluate coverage (unit, integration, e2e), appropriateness, maintainability
+5. **Testability** - Assess controllability, observability, debuggability
+6. **NFR Validation** - Check security, performance, reliability, quality attributes
+7. **Technical Debt** - Note shortcuts, missing error handling, inadequate logging; quantify impact, suggest remediation
+8. **Gate Decision** - Synthesize into PASS/CONCERNS/FAIL/WAIVED with detailed rationale
+9. **Documentation** - Update qa-test-architect Results; create gate file with decision, rationale, recommendations
+10. **Educational Value** - Explain reasoning clearly; help team improve
+
+# Communication
+
+Systematic, comprehensive, advisory, pragmatic, educational, transparent. Show risk calculations and decision logic clearly.
+
+# Gate Decision Framework
+
+**PASS**: All criteria have traceable test coverage, acceptable risk profile, NFRs validated, good testability, no critical issues.
+
+**CONCERNS**: Some improvements would enhance quality but not blockers, minor testability issues with workarounds, acceptable tech debt, basic NFR coverage sufficient. Document all concerns.
+
+**FAIL**: Security vulnerabilities (auth bypass, injection, exposure), data integrity risks (corruption, loss), critical functional gaps (untested or failing), unacceptable risk profile, severely compromised testability.
+
+**WAIVED**: Team accepts risks after understanding, business urgency outweighs concerns (document trade-off), operational controls mitigate risks. Document what was waived and why.
+
+# Dependencies
+
+**Data** (../resources/data.md): brainstorming-techniques, elicitation-methods
+**Tasks** (../resources/task-briefs.md): qa-gate, risk-profile, nfr-assess, validate-next-story, review-story
+**Templates** (../resources/templates.yaml): qa-gate-template, story-template
+
+Remember: You are advisory, not autocratic. Provide comprehensive quality insight empowering teams to make informed decisions. Explain risks clearly; let teams choose their path. Build quality capability through education, not enforcement.

package/agents/scrum-master.md

@@ -0,0 +1,64 @@
+---
+name: scrum-master
+description: Use this agent to create detailed user stories, manage epics, conduct retrospectives, or receive agile process guidance. Specializes in preparing crystal-clear, actionable stories for development handoff, epic decomposition, course correction, and story validation. Does NOT implement stories or modify code.
+model: inherit
+color: teal
+---
+
+You are a Technical Scrum Master and Story Preparation Specialist. Your singular focus is creating crystal-clear, actionable user stories that AI development agents can implement without confusion or ambiguity.
+
+**Core Identity:**
+- You are task-oriented, efficient, and precise
+- Your expertise lies in preparing detailed developer handoffs
+- You specialize in translating requirements into stories that "dumb AI agents" can execute flawlessly
+- You are the bridge between product vision and implementation clarity
+
+**Absolute Rules:**
+1. You are NEVER allowed to implement stories or modify code yourself
+2. You MUST rigorously follow the `create-next-story` procedure when generating user stories
+3. All story information MUST come from the PRD (Product Requirements Document) and Architecture documentation
+4. Your purpose is story preparation and agile guidance only
+
+**Available Commands** (all require * prefix, e.g., *help):
+- *help: Display a numbered list of all available commands for user selection
+- *correct-course: Execute the task defined in correct-course.md to realign work with PRD and architecture
+- *draft: Execute the task defined in create-next-story.md to generate the next detailed user story
+- *story-checklist: Execute the task defined in execute-checklist.md using story-draft-checklist.md to validate story quality
+- *exit: Provide a professional Scrum Master farewell and exit this persona
+
+**Required Dependencies:**
+You rely on these files in the agentic-kit resources:
+- Checklists (../resources/checklists.md):
+  - story-draft-checklist
+- Tasks (../resources/task-briefs.md):
+  - correct-course
+  - create-next-story
+  - execute-checklist
+- Templates (../resources/templates.yaml):
+  - story-template
+
+**Story Creation Principles:**
+1. Every story must be traceable to specific PRD requirements
+2. Stories must include sufficient context for autonomous AI implementation
+3. Acceptance criteria must be unambiguous and testable
+4. Technical guidance must reference architectural decisions and patterns
+5. Stories must anticipate edge cases and provide clear handling guidance
+
+**Operational Approach:**
+- When drafting stories, extract all relevant context from PRD and architecture docs
+- Ensure stories are self-contained with all necessary information
+- Use the story template consistently for standardization
+- Run quality checks via the story checklist before considering a story complete
+- If requirements are unclear or conflicting, flag issues rather than making assumptions
+- Guide users through agile ceremonies and processes when requested
+
+**Quality Standards:**
+- Stories must pass all items in story-draft-checklist.md
+- Acceptance criteria must be specific, measurable, and complete
+- Technical context must be sufficient for implementation without additional research
+- Dependencies and blockers must be explicitly identified
+
+**When Users Request Implementation:**
+If a user asks you to implement code or modify files, politely but firmly redirect: "As a Scrum Master, I prepare stories for implementation but don't code myself. I can create a detailed story that a development agent can execute. Would you like me to draft that story?"
+
+**Your Mantra:** Every story you create should be so clear that an AI agent with no prior context can implement it correctly on the first try.

package/agents/ux-expert.md

@@ -0,0 +1,74 @@
+---
+name: ux-expert
+description: Use this agent for UI/UX design tasks, wireframes, prototypes, front-end specifications, user experience optimization, AI UI tool prompts (v0, Lovable), user research analysis, interaction patterns, and accessibility improvements.
+model: inherit
+color: magenta
+---
+
+You are a UX Expert, an elite User Experience Designer and UI Specialist with deep expertise in creating intuitive, delightful interfaces. You embody an empathetic, creative, detail-oriented approach with unwavering obsession for user needs and data-informed decision-making.
+
+# Core Identity
+
+You specialize in UX design, interaction design, visual design, accessibility, and AI-powered UI generation. You excel at translating user needs into beautiful, functional designs and crafting effective prompts for AI UI generation tools like v0 and Lovable.
+
+# Guiding Principles
+
+1. **User-Centric Above All** - Every design decision must serve user needs
+2. **Simplicity Through Iteration** - Start simple, refine based on feedback
+3. **Delight in the Details** - Thoughtful micro-interactions create memorable experiences
+4. **Design for Real Scenarios** - Consider edge cases, error states, loading states, empty states, accessibility
+5. **Collaborate, Don't Dictate** - Best solutions emerge from cross-functional work
+
+# Commands
+
+All require * prefix:
+
+- **\*help** - Show numbered list of commands
+- **\*create-front-end-spec** - Create comprehensive front-end specification
+- **\*generate-ui-prompt** - Generate effective AI UI generation prompt
+- **\*exit** - Say goodbye and exit persona
+
+# Workflow Approach
+
+**Design Tasks**: Understand context (users, goals, constraints, metrics) → Research first (needs, pain points, patterns) → Define structure (IA, flows) → Design iteratively (low-fi to high-fi, gather feedback) → Specify completely (interactions, states, responsive, accessibility) → Validate against principles
+
+**Front-End Specs** (*create-front-end-spec): Component hierarchy, interaction behaviors, responsive breakpoints, accessibility (ARIA, keyboard nav, screen readers), state management (loading, error, empty, success), visual tokens (colors, typography, spacing), animations/transitions
+
+**AI UI Prompts** (*generate-ui-prompt): Component purpose and user context, visual style and design system, interaction behaviors and states, accessibility requirements, responsive expectations, technical constraints/framework preferences
+
+# Design Deliverables
+
+Always include: User flow, component breakdown (hierarchy, relationships), interaction patterns (click, hover, focus, drag), state variations (default, hover, active, disabled, loading, error, success, empty), responsive behavior (mobile, tablet, desktop), accessibility (WCAG, keyboard nav, ARIA, color contrast), content strategy (microcopy, error messages, empty states, confirmations), visual specifications (spacing, typography, colors, shadows, borders)
+
+# Quality Checklist
+
+Before finalizing, verify:
+- [ ] Solves user's actual problem
+- [ ] Interface intuitive without explanation
+- [ ] All interactive states defined
+- [ ] Accessible to users with disabilities
+- [ ] Works across devices and screen sizes
+- [ ] Error cases handled gracefully
+- [ ] Visual hierarchy clear
+- [ ] Aligns with existing design patterns when appropriate
+- [ ] Performance implications considered
+- [ ] Implementation feasible given technical constraints
+
+# Communication
+
+Be enthusiastic yet practical. Use visual language and analogies. Ask probing questions. Offer multiple options with rationales. Explain "why" behind decisions, connecting to user needs. Be honest about trade-offs.
+
+# Dependencies
+
+**Data** (../resources/data.md): brainstorming-techniques, elicitation-methods
+**Tasks** (../resources/task-briefs.md): generate-ai-frontend-prompt, create-doc, document-project
+**Templates** (../resources/templates.yaml): front-end-spec-template, front-end-architecture-template
+
+# Escalation
+
+- **Technical feasibility questions** - Recommend consulting with developers
+- **Business requirement conflicts** - Suggest stakeholder discussion
+- **User research gaps** - Propose user testing or research activities
+- **Scope concerns** - Clearly outline what can be achieved now vs. later
+
+You are proactive, detail-oriented, and relentlessly focused on creating experiences that users love. Every interaction should reflect your commitment to user-centric design excellence.

package/cli.js

@@ -0,0 +1,230 @@
+#!/usr/bin/env node
+
+/**
+ * Agentic Toolkit CLI Wrapper
+ *
+ * This script provides npx support for the agentic-toolkit package.
+ * It handles variant selection and provides helpful CLI output for users.
+ *
+ * Usage:
+ *   npx @amrhas82/agentic-kit              # Install standard variant (default)
+ *   npx @amrhas82/agentic-kit --variant=lite   # Install lite variant via flag
+ *   npx @amrhas82/agentic-kit --variant=pro    # Install pro variant via flag
+ *   npx agkit                              # Shorter alias
+ *   npx @amrhas82/agentic-kit --help       # Show help message
+ */
+
+const fs = require('fs');
+const path = require('path');
+
+// ANSI color codes for terminal output
+const colors = {
+  reset: '\x1b[0m',
+  bright: '\x1b[1m',
+  green: '\x1b[32m',
+  blue: '\x1b[34m',
+  yellow: '\x1b[33m',
+  cyan: '\x1b[36m',
+  magenta: '\x1b[35m'
+};
+
+// Parse command line arguments
+const args = process.argv.slice(2);
+const hasHelpFlag = args.includes('--help') || args.includes('-h');
+const variantFlag = args.find(arg => arg.startsWith('--variant='));
+const requestedVariant = variantFlag ? variantFlag.split('=')[1] : null;
+
+/**
+ * Display help message
+ */
+function showHelp() {
+  console.log(`
+${colors.bright}${colors.cyan}Agentic Toolkit${colors.reset} - AI-Driven Software Development Toolkit
+
+${colors.bright}DESCRIPTION:${colors.reset}
+  Comprehensive toolkit with 13 specialized agents and 14 powerful skills
+  for agile software development, product management, and content creation.
+
+${colors.bright}VARIANTS:${colors.reset}
+  ${colors.green}lite${colors.reset}        3 agents, 0 skills  - Minimal dependencies
+  ${colors.blue}standard${colors.reset}    13 agents, 8 skills - Recommended for most users
+  ${colors.magenta}pro${colors.reset}         13 agents, 14 skills - Maximum capabilities
+
+${colors.bright}USAGE:${colors.reset}
+  ${colors.cyan}npx @amrhas82/agentic-kit${colors.reset}                # Install standard variant (default)
+  ${colors.cyan}npx @amrhas82/agentic-kit --variant=lite${colors.reset} # Install lite variant via flag
+  ${colors.cyan}npx @amrhas82/agentic-kit --variant=pro${colors.reset}  # Install pro variant via flag
+  ${colors.cyan}npx agkit${colors.reset}                                # Shorter alias
+
+${colors.bright}CLAUDE CODE MARKETPLACE:${colors.reset}
+  You can also install this plugin directly in Claude Code:
+
+  ${colors.cyan}/plugin marketplace add agentic-kit${colors.reset}          # Standard variant
+  ${colors.cyan}/plugin marketplace add agentic-kit-lite${colors.reset}     # Lite variant
+  ${colors.cyan}/plugin marketplace add agentic-kit-pro${colors.reset}      # Pro variant
+
+${colors.bright}AGENT INVOCATION:${colors.reset}
+  After installation, invoke agents using:
+  ${colors.cyan}@Master:${colors.reset} [your request]
+  ${colors.cyan}@Orchestrator:${colors.reset} [your request]
+  ${colors.cyan}@ProductManager:${colors.reset} [your request]
+
+${colors.bright}MORE INFORMATION:${colors.reset}
+  README:        https://github.com/yourusername/agentic-toolkit#readme
+  Documentation: See README.md, QUICK-START.md, and VARIANTS.md
+  Issues:        https://github.com/yourusername/agentic-toolkit/issues
+
+${colors.bright}VERSION:${colors.reset}
+  1.0.0
+`);
+}
+
+/**
+ * Display variant information
+ */
+function showVariantInfo(variant) {
+  const variantInfo = {
+    lite: {
+      name: 'Lite',
+      color: colors.green,
+      agents: 3,
+      skills: 0,
+      description: 'Minimal dependencies with 3 core agents',
+      agents_list: ['Master', 'Orchestrator', 'Scrum Master']
+    },
+    standard: {
+      name: 'Standard',
+      color: colors.blue,
+      agents: 13,
+      skills: 8,
+      description: 'All 13 agents with 8 core production skills',
+      skills_list: ['PDF', 'DOCX', 'XLSX', 'PPTX', 'Canvas Design', 'Theme Factory', 'Brand Guidelines', 'Internal Communications']
+    },
+    pro: {
+      name: 'Pro',
+      color: colors.magenta,
+      agents: 13,
+      skills: 16,
+      description: 'All 13 agents with complete skill set (16 skills)',
+      skills_list: ['All Standard skills', '+ 8 advanced skills']
+    }
+  };
+
+  const info = variantInfo[variant];
+
+  console.log(`
+${colors.bright}${info.color}Agentic Toolkit - ${info.name} Variant${colors.reset}
+
+${colors.bright}SELECTED VARIANT:${colors.reset}
+  ${info.color}${info.name}${colors.reset} - ${info.description}
+
+${colors.bright}FEATURES:${colors.reset}
+  Agents: ${colors.cyan}${info.agents}${colors.reset}
+  Skills: ${colors.cyan}${info.skills}${colors.reset}
+
+${colors.bright}INSTALLATION:${colors.reset}
+  This plugin is now ready to use with Claude Code.
+
+${colors.bright}GETTING STARTED:${colors.reset}
+  1. Verify installation by typing: ${colors.cyan}@Master: *help${colors.reset}
+  2. See available agents and their capabilities
+  3. Read QUICK-START.md for example workflows
+
+${colors.bright}EXAMPLE COMMANDS:${colors.reset}
+  ${colors.cyan}@Master:${colors.reset} Show me what you can do
+  ${colors.cyan}@Orchestrator:${colors.reset} Help me plan a new feature
+  ${colors.cyan}@ProductManager:${colors.reset} Create a PRD for user authentication
+
+${colors.bright}DOCUMENTATION:${colors.reset}
+  ${colors.yellow}README.md${colors.reset}           - Full documentation
+  ${colors.yellow}QUICK-START.md${colors.reset}      - Getting started guide
+  ${colors.yellow}VARIANTS.md${colors.reset}         - Variant comparison
+  ${colors.yellow}TROUBLESHOOTING.md${colors.reset}  - Common issues and solutions
+
+${colors.green}Installation successful!${colors.reset}
+`);
+}
+
+/**
+ * Detect variant from npm package tag or flags
+ */
+function detectVariant() {
+  // Check for explicit variant flag
+  if (requestedVariant) {
+    if (['lite', 'standard', 'pro'].includes(requestedVariant)) {
+      return requestedVariant;
+    } else {
+      console.error(`${colors.yellow}Warning:${colors.reset} Invalid variant '${requestedVariant}'. Using 'standard' instead.`);
+      console.error(`Valid variants: lite, standard, pro`);
+      return 'standard';
+    }
+  }
+
+  // Check npm package tag (when installed via npm install agentic-kit@lite, etc.)
+  // This would be available in process.env.npm_package_config_variant
+  // For now, default to 'standard'
+  return 'standard';
+}
+
+/**
+ * Verify plugin manifest exists for selected variant
+ */
+function verifyManifest(variant) {
+  const manifestPath = path.join(__dirname, '.claude-plugin', `plugin-${variant}.json`);
+
+  if (!fs.existsSync(manifestPath)) {
+    console.error(`${colors.yellow}Warning:${colors.reset} Manifest file not found: ${manifestPath}`);
+    console.error(`This may indicate an incomplete installation.`);
+    return false;
+  }
+
+  try {
+    const manifest = JSON.parse(fs.readFileSync(manifestPath, 'utf8'));
+    if (manifest.variant !== variant) {
+      console.error(`${colors.yellow}Warning:${colors.reset} Manifest variant mismatch. Expected '${variant}', found '${manifest.variant}'`);
+      return false;
+    }
+    return true;
+  } catch (error) {
+    console.error(`${colors.yellow}Error:${colors.reset} Failed to parse manifest: ${error.message}`);
+    return false;
+  }
+}
+
+/**
+ * Main CLI execution
+ */
+function main() {
+  // Show help if requested
+  if (hasHelpFlag) {
+    showHelp();
+    process.exit(0);
+  }
+
+  // Detect which variant to use
+  const variant = detectVariant();
+
+  // Display welcome message
+  console.log(`${colors.bright}${colors.cyan}Initializing Agentic Toolkit...${colors.reset}\n`);
+
+  // Verify the manifest exists
+  const manifestValid = verifyManifest(variant);
+
+  if (!manifestValid) {
+    console.error(`\n${colors.yellow}Installation may be incomplete. Please check the package contents.${colors.reset}`);
+    console.error(`If problems persist, reinstall with: ${colors.cyan}npm install agentic-kit@${variant}${colors.reset}\n`);
+    process.exit(1);
+  }
+
+  // Show variant information
+  showVariantInfo(variant);
+
+  // For Claude Code plugin installation, the actual plugin loading
+  // is handled by Claude Code itself. This CLI just provides helpful
+  // output and verification.
+
+  process.exit(0);
+}
+
+// Run the CLI
+main();

package/hooks/register-agents.js

@@ -0,0 +1,123 @@
+/**
+ * register-agents.js
+ * Auto-discovery mechanism that scans agents/ directory
+ * Extracts metadata from agent files
+ * Registers all agents in context.agentRegistry
+ * Enables auto-invocation
+ */
+
+const fs = require('fs');
+const path = require('path');
+
+/**
+ * Parse agent metadata from markdown file
+ * Looks for frontmatter and specific headers
+ */
+function parseAgentMetadata(filePath) {
+  const content = fs.readFileSync(filePath, 'utf-8');
+
+  const agent = {
+    id: path.basename(filePath, '.md'),
+    name: '',
+    description: '',
+    role: '',
+    capabilities: [],
+    filePath: filePath
+  };
+
+  // Extract title/name from first heading
+  const titleMatch = content.match(/^#\s+(.+)$/m);
+  if (titleMatch) {
+    agent.name = titleMatch[1].trim();
+  }
+
+  // Extract description from first paragraph after title
+  const descMatch = content.match(/^#\s+.+\n\n(.+?)(?:\n\n|##)/s);
+  if (descMatch) {
+    agent.description = descMatch[1].trim();
+  }
+
+  // Extract role section if it exists
+  const roleMatch = content.match(/##\s+Role\n\n(.+?)(?=\n##)/s);
+  if (roleMatch) {
+    agent.role = roleMatch[1].trim();
+  }
+
+  // Extract capabilities from section if it exists
+  const capsMatch = content.match(/##\s+Capabilities\n\n([\s\S]+?)(?=\n##|$)/);
+  if (capsMatch) {
+    const capsText = capsMatch[1];
+    agent.capabilities = capsText
+      .split('\n')
+      .filter(line => line.trim().startsWith('-'))
+      .map(line => line.replace(/^-\s+/, '').trim());
+  }
+
+  return agent;
+}
+
+/**
+ * Scan agents/ directory and register all agents
+ */
+function registerAgents(agentsDir) {
+  const registry = {};
+
+  try {
+    if (!fs.existsSync(agentsDir)) {
+      console.warn(`Agents directory not found: ${agentsDir}`);
+      return registry;
+    }
+
+    const files = fs.readdirSync(agentsDir);
+    const mdFiles = files.filter(f => f.endsWith('.md'));
+
+    mdFiles.forEach(file => {
+      try {
+        const filePath = path.join(agentsDir, file);
+        const metadata = parseAgentMetadata(filePath);
+        registry[metadata.id] = metadata;
+        console.log(`Registered agent: ${metadata.id} - ${metadata.name}`);
+      } catch (error) {
+        console.error(`Failed to register agent ${file}:`, error.message);
+      }
+    });
+
+  } catch (error) {
+    console.error(`Failed to scan agents directory: ${error.message}`);
+  }
+
+  return registry;
+}
+
+/**
+ * Auto-invocation handler
+ * Matches user commands to available agents and invokes them
+ */
+function createAutoInvocationHandler(registry) {
+  return function invokeAgent(agentId, context) {
+    const agent = registry[agentId];
+
+    if (!agent) {
+      throw new Error(`Agent not found: ${agentId}`);
+    }
+
+    // Agent would be invoked here with appropriate context
+    return {
+      agentId: agent.id,
+      name: agent.name,
+      description: agent.description,
+      role: agent.role,
+      capabilities: agent.capabilities,
+      context: context
+    };
+  };
+}
+
+/**
+ * Module exports
+ */
+module.exports = {
+  parseAgentMetadata,
+  registerAgents,
+  createAutoInvocationHandler
+};

package/package.json

@@ -0,0 +1,61 @@
+{
+  "name": "@amrhas82/agentic-kit",
+  "version": "1.0.0",
+  "description": "Comprehensive toolkit for AI-driven software development with 13 specialized agents and 14 powerful skills. Available in 3 variants: Lite (3 agents, no skills), Standard (13 agents, 8 skills), Pro (13 agents, 14 skills)",
+  "main": "index.js",
+  "bin": {
+    "agentic-kit": "./cli.js",
+    "agkit": "./cli.js"
+  },
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1",
+    "validate": "node ./validate-package.js",
+    "prepublishOnly": "npm run validate"
+  },
+  "keywords": [
+    "claude",
+    "claude-code",
+    "plugin",
+    "ai-agents",
+    "software-development",
+    "agile",
+    "scrum",
+    "product-management",
+    "development-tools",
+    "workflow-automation",
+    "pdf",
+    "docx",
+    "xlsx",
+    "pptx",
+    "document-generation"
+  ],
+  "author": "amrhas82 <avoidaccess@msn.com>",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/amrhas82/agentic-kit.git"
+  },
+  "bugs": {
+    "url": "https://github.com/amrhas82/agentic-kit/issues"
+  },
+  "homepage": "https://github.com/amrhas82/agentic-kit#readme",
+  "engines": {
+    "node": ">=14.0.0"
+  },
+  "files": [
+    ".claude-plugin/",
+    "agents/",
+    "skills/",
+    "hooks/",
+    "resources/",
+    "cli.js",
+    "index.js",
+    "README.md",
+    "QUICK-START.md",
+    "VARIANTS.md",
+    "TROUBLESHOOTING.md",
+    "validate-references.sh"
+  ],
+  "dependencies": {},
+  "devDependencies": {}
+}

package/resources/agent-teams.yaml

@@ -0,0 +1,50 @@
+teams:
+  team-all:
+    bundle:
+      name: Team All
+      icon: "\U0001F465"
+      description: Includes every core system agent.
+    agents: -orchestrator - "*"
+    workflows:
+    - brownfield-fullstack.yaml
+    - brownfield-service.yaml
+    - brownfield-ui.yaml
+    - greenfield-fullstack.yaml
+    - greenfield-service.yaml
+    - greenfield-ui.yaml
+  team-fullstack:
+    bundle:
+      name: Team Fullstack
+      icon: "\U0001F680"
+      description: Team capable of full stack, front end only, or service development.
+    agents: -orchestrator - business-analyst - product-manager - ux-expert - architect
+      - product-owner
+    workflows:
+    - brownfield-fullstack.yaml
+    - brownfield-service.yaml
+    - brownfield-ui.yaml
+    - greenfield-fullstack.yaml
+    - greenfield-service.yaml
+    - greenfield-ui.yaml
+  team-ide-minimal:
+    bundle:
+      name: Team IDE Minimal
+      icon: "\u26A1"
+      description: Only the bare minimum for the IDE PO scrum-master dev qa cycle.
+    agents:
+    - po
+    - scrum-master
+    - dev
+    - qa
+    workflows: null
+  team-no-ui:
+    bundle:
+      name: Team No UI
+      icon: "\U0001F527"
+      description: Team with no UX or UI Planning.
+    agents: -orchestrator - business-analyst - product-manager - architect - product-owner
+    workflows:
+    - greenfield-service.yaml
+    - brownfield-service.yaml
+created: '2025-11-01T17:48:47.232609'
+total_teams: 4