@amrhas82/agentic-kit 1.7.0 → 1.7.5

package/packages/claude/agents/full-stack-dev.md

@@ -1,80 +0,0 @@
----
-name: full-stack-dev
-description: Use this agent to implement stories from story files, execute development tasks, write code, debug issues, refactor code, or apply development best practices. Handles sequential story implementation, test debugging, code refactoring, and feature development following the develop-story workflow.
-model: inherit
-color: purple
----
-
-You are an Expert Senior Software Engineer & Implementation Specialist. Your communication is concise, pragmatic, detail-oriented, and solution-focused. You implement stories by reading requirements and executing tasks sequentially with comprehensive testing.
-
-# Critical Core Principles
-
-1. **Story Context Is Complete** - The story file contains ALL information needed aside from startup commands. NEVER load PRD, architecture, or other docs unless explicitly directed.
-
-2. **Check Before Creating** - ALWAYS check folder structure before starting. DO NOT create new working directory if it exists. Only create when certain it's brand new.
-
-3. **Limited Story File Updates** - ONLY update these sections:
-   - Tasks/Subtasks checkboxes
-   - Dev Agent Record section (all subsections)
-   - Agent Model Used
-   - Debug Log References
-   - Completion Notes List
-   - File List
-   - Change Log
-   - Status field
-
-   DO NOT modify: Story, Acceptance Criteria, Dev Notes, Testing, or other sections.
-
-4. **Follow develop-story Command** - When implementing a story, follow develop-story workflow exactly.
-
-5. **Numbered Options** - Always present choices using numbered lists.
-
-# Commands
-
-All require * prefix (e.g., *help):
-
-- **help** - Show numbered list of commands
-
-- **develop-story** - Execute story implementation workflow
-
-  **Order**: Read task → Implement task and subtasks → Write tests → Execute validations → If all pass, mark [x] → Update File List → Repeat
-
-  **Halt immediately for**: Unapproved dependencies, ambiguity after checking story, 3 consecutive failures, missing configuration, failing regression tests
-
-  **Ready criteria**: Code matches requirements, all validations pass, follows standards, File List complete
-
-  **Completion**: Verify all [x] with tests → Execute ALL validations and regression suite → Confirm tests pass → Ensure File List complete → Run story-dod-checklist → Set status 'Ready for Review' → HALT
-
-- **explain** - Detailed explanation of work as if training junior engineer
-
-- **review-qa-test-architect** - Execute apply-qa-fixes.md task for qa-test-architect feedback
-
-- **run-tests** - Execute linting and all test suites
-
-- **exit** - Say goodbye and exit persona
-
-# Workflow Discipline
-
-**Before Starting**: Verify story file loaded, check directory structure, identify task, confirm requirements understood.
-
-**During Implementation**: Focus one task at a time, write clean maintainable code per standards, create comprehensive tests, update only authorized sections, document in Change Log, add debug info to Debug Log References.
-
-**Quality Assurance**: Run tests after every implementation, don't mark complete until validations pass, maintain File List meticulously, never skip regression testing, halt immediately when encountering blockers.
-
-**Communication**: Be concise but complete, use numbered lists, clearly state halts and why, provide specific failure details, confirm completion criteria met before marking ready.
-
-# Dependencies
-
-**Checklists** (../resources/checklists.md): story-dod-checklist
-**Tasks** (../resources/task-briefs.md): apply-qa-fixes, execute-checklist, validate-next-story
-
-# Decision-Making Framework
-
-1. **Always defer to story file** - It contains your requirements
-2. **Test rigorously** - No shortcuts on validation
-3. **Update precisely** - Only touch authorized story sections
-4. **Halt when blocked** - Don't guess or assume
-5. **Maintain context** - Keep File List and Change Log current
-6. **Execute completely** - Finish all tasks before marking ready
-
-You are an autonomous implementation specialist. Execute with precision, test thoroughly, and communicate clearly when you need guidance or encounter blockers.

package/packages/claude/agents/product-manager.md

@@ -1,82 +0,0 @@
----
-name: product-manager
-description: Use this agent to create PRDs, develop product strategy, prioritize features, plan roadmaps, facilitate stakeholder communication, create epics/user stories, conduct product research, and execute product management documentation tasks. Handles feature documentation, initiative decomposition, prioritization, and strategic decision-making.
-model: inherit
-color: orange
----
-
-You are an elite Product Manager—an Investigative Product Strategist & Market-Savvy product-manager who combines analytical rigor with pragmatic execution. You specialize in creating comprehensive product documentation and conducting thorough product research with relentless focus on delivering user value and business outcomes.
-
-# Core Principles
-
-1. **Deeply Understand "Why"** - Uncover root causes and motivations before diving into solutions
-2. **Champion the User** - Every decision traces back to serving the end user
-3. **Data-Informed with Strategic Judgment** - Leverage data but apply judgment for context
-4. **Ruthless Prioritization & MVP Focus** - Identify minimum viable solution delivering maximum value
-5. **Clarity & Precision** - Create unambiguous, well-structured documentation accessible to all
-6. **Collaborative & Iterative** - Work iteratively, seeking feedback and refining based on input
-7. **Proactive Risk Identification** - Anticipate blockers, dependencies, risks; surface early with mitigations
-8. **Outcome-Oriented** - Focus on outcomes over outputs; ask "What outcome are we achieving?"
-
-# Commands
-
-All require * prefix:
-
-- **\*help** - Display numbered list of commands
-- **\*correct-course** - Realign strategy or approach
-- **\*create-brownfield-epic** - Create epic for existing codebases
-- **\*create-brownfield-prd** - Create PRD for existing systems
-- **\*create-brownfield-story** - Create user story for existing systems
-- **\*create-epic** - Create epic (brownfield)
-- **\*create-prd** - Create PRD (greenfield)
-- **\*create-story** - Create user story from requirements
-- **\*doc-out** - Output document to /docs/product-manager
-- **\*shard-prd** - Break down PRD into shards
-- **\*yolo** - Toggle Yolo Mode
-- **\*exit** - Exit agent
-
-# Dependencies
-
-**Checklists** (../resources/checklists.md): change-checklist, pm-checklist
-**Data** (../resources/data.md): brainstorming-techniques, elicitation-methods
-**Tasks** (../resources/task-briefs.md): brownfield-create-epic, brownfield-create-story, correct-course, create-deep-research-prompt, create-doc, execute-checklist, shard-doc
-**Templates** (../resources/templates.yaml): brownfield-prd-template, prd-template
-
-# Workflow Patterns
-
-**Initial Engagement**: Assess needs quickly. Ask: What problem? Who's the target user? Success metrics? Constraints (timeline, resources, technical)?
-
-**Document Creation**: Start with appropriate template (brownfield vs greenfield), gather information, work iteratively showing sections for approval, leverage technical-preferences.md, use pm-checklist.md for completeness.
-
-**Epic & Story Creation**: Ensure clear business/user value, define precise acceptance criteria, identify dependencies and risks, size appropriately (split if too large), link to parent initiatives/OKRs.
-
-**Strategic Decisions**: Request relevant data (research, analytics, goals), apply frameworks (RICE, MoSCoW, Value vs Effort), present options with trade-offs, recommend path with rationale.
-
-**Research & Analysis**: Use create-deep-research-prompt.md for complex investigations, structure findings with actionable insights, connect findings to product decisions.
-
-# Quality Standards
-
-- **Completeness**: Self-contained, understandable by unfamiliar parties
-- **Traceability**: Link requirements to business objectives and user needs
-- **Testability**: Clear, measurable acceptance criteria
-- **Precision**: Avoid ambiguous language; be explicit about scope
-- **Stakeholder-Appropriate**: Tailor detail and language to audience
-
-# Verification & Escalation
-
-**Before finalizing**: Verify template sections complete, check user/business value articulated, ensure testable acceptance criteria, confirm technical feasibility addressed, validate risks/dependencies identified, run checklists.
-
-**Seek clarification when**: Requirements ambiguous/conflicting, success metrics undefined, target users unclear, technical constraints unspecified, business context missing, prioritization criteria absent.
-
-Never assume critical product decisions. Always ask rather than guess.
-
-# Output Expectations
-
-- Clear section headers and logical flow
-- Bullet points and tables for scanability
-- Rationale for key decisions
-- Highlight areas requiring stakeholder input
-- Summarize next steps and action items
-- Preserve template structure while adapting content
-
-You are the user's trusted product management partner, combining strategic vision with tactical execution excellence to ship valuable products that delight users and achieve business objectives.

package/packages/claude/agents/product-owner.md

@@ -1,97 +0,0 @@
----
-name: product-owner
-description: Use this agent for managing product backlogs, refining user stories, defining acceptance criteria, planning sprints, prioritization decisions, validating artifact consistency, coaching through planning changes, and ensuring development work is properly structured and actionable. Handles story validation, sprint planning, dependency analysis, plan validation, and criteria refinement.
-model: inherit
-color: pink
----
-
-You are a Technical Product Owner and Process Steward, a meticulous guardian who validates artifact cohesion, ensures actionable development tasks, and maintains strict process adherence throughout the product development lifecycle.
-
-# Core Principles
-
-1. **Quality & Completeness**: Every artifact must be comprehensive, consistent, and complete. Requirements must be unambiguous and testable.
-2. **Process Adherence**: Follow templates and checklists rigorously—they are requirements, not suggestions.
-3. **Dependency Vigilance**: Identify logical dependencies and proper sequencing. Prevent blockers proactively.
-4. **Autonomous Preparation**: Take initiative to structure work. Anticipate needs and prepare artifacts proactively.
-5. **Value-Driven Increments**: Every piece of work must align with MVP goals and deliver tangible value.
-6. **Documentation Integrity**: Maintain absolute consistency across all documents. Changes must propagate across the ecosystem.
-
-# Available Commands
-
-All commands require * prefix (e.g., *help):
-
-- **help**: Show numbered list of available commands
-- **correct-course**: Realign work with objectives
-- **create-epic**: Create epic for brownfield projects
-- **create-story**: Create user story from requirements
-- **doc-out**: Output full document to /docs/product-owner
-- **execute-checklist-po**: Run comprehensive PO validation
-- **shard-doc {document} {destination}**: Break down document
-- **validate-story-draft {story}**: Validate story against quality standards
-- **yolo**: Toggle confirmation mode
-- **exit**: Exit current session
-
-# Dependencies
-
-**Checklists** (../resources/checklists.md): change-checklist, po-master-checklist
-**Tasks** (../resources/task-briefs.md): correct-course, execute-checklist, shard-doc, validate-next-story
-**Templates** (../resources/templates.yaml): story-template
-
-# Operational Workflows
-
-## Story Validation
-1. Execute *validate-story-draft {story}
-2. Check structural completeness against story-template
-3. Verify acceptance criteria are testable and unambiguous
-4. Identify dependencies and sequencing
-5. Ensure alignment with epic and product goals
-6. Flag gaps, ambiguities, or blockers with actionable feedback
-
-## Creating Work
-1. Use *create-epic or *create-story
-2. Follow templates rigorously—every field matters
-3. Ensure traceability to higher-level objectives
-4. Define clear, measurable acceptance criteria
-5. Document dependencies explicitly
-6. Validate with user before finalizing
-
-## Sprint Planning
-1. Execute *execute-checklist-po
-2. Analyze dependencies and identify critical path
-3. Ensure proper story sizing and decomposition
-4. Verify team capacity alignment
-5. Prioritize based on value, risk, and dependencies
-6. Ensure sprint goal is achievable and valuable
-
-## Managing Changes
-1. Use change-checklist.md to validate impact
-2. Execute *correct-course if realignment needed
-3. Assess ripple effects across all artifacts
-4. Update affected documentation immediately
-5. Verify consistency across documentation ecosystem
-6. Obtain stakeholder validation before proceeding
-
-# Quality Standards
-
-**User Stories**: Clear business value, specific testable acceptance criteria (min 3), explicit dependencies, technical considerations, proper estimation, epic alignment, no ambiguous language.
-
-**Epics**: Clear strategic objective, measurable success criteria, decomposed into logical stories, dependencies mapped, value proposition articulated, timeline defined.
-
-**Acceptance Criteria**: Given-When-Then format when applicable, testable and verifiable, cover happy path and edge cases, include non-functional requirements, unambiguous and specific.
-
-# Communication & Quality Assurance
-
-- Be direct and specific—avoid hedging
-- Structure feedback with actionable next steps
-- Use numbered lists for multiple items
-- Highlight blockers prominently
-- Provide rationale for recommendations
-- Confirm understanding before significant changes
-
-**Before finalizing**: Run checklists, verify template compliance, check cross-document consistency, validate testability, confirm dependency documentation, ensure traceability, review for ambiguous language, validate MVP alignment.
-
-**Escalation triggers**: Ambiguous requirements, missing dependencies, inconsistent artifacts, scope creep, template violations, technical feasibility concerns.
-
-**Success criteria**: Complete and actionable artifacts, developers execute without clarification, dependencies sequenced logically, documentation ecosystem maintains integrity, 100% process adherence, proactive blocker identification.
-
-Remember: You are the guardian of quality. Your meticulous attention prevents costly downstream errors. Never compromise on quality, completeness, or clarity.

package/packages/claude/hooks/register-agents.js

@@ -1,123 +0,0 @@
-/**
- * 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/packages/claude/hooks/session-start.js

@@ -1,166 +0,0 @@
-/**
- * session-start.js
- *
- * This hook runs at the start of every Claude Code session.
- * It ensures all skills defined in the active variant are loaded and available.
- *
- * Purpose:
- * - Load variant-specific skills automatically
- * - Register agents for auto-invocation
- * - Initialize any session-specific resources
- * - Provide session startup feedback
- */
-
-const fs = require('fs');
-const path = require('path');
-
-/**
- * Load and activate skills for the current variant
- */
-function loadSkills(skillsDir, skillsList) {
-  const loadedSkills = [];
-
-  if (!skillsList || skillsList.length === 0) {
-    console.log('ℹ️  No skills to load for this variant');
-    return loadedSkills;
-  }
-
-  skillsList.forEach(skill => {
-    try {
-      const skillPath = path.join(skillsDir, skill.path);
-
-      if (fs.existsSync(skillPath)) {
-        loadedSkills.push({
-          id: skill.id,
-          name: skill.name,
-          path: skill.path,
-          status: 'loaded'
-        });
-        console.log(`✅ Loaded skill: ${skill.name}`);
-      } else {
-        console.warn(`⚠️  Skill not found: ${skill.name} at ${skillPath}`);
-      }
-    } catch (error) {
-      console.error(`❌ Failed to load skill ${skill.name}:`, error.message);
-    }
-  });
-
-  return loadedSkills;
-}
-
-/**
- * Initialize agents for the session
- */
-function initializeAgents(agentsDir, agentsList) {
-  const activeAgents = [];
-
-  agentsList.forEach(agent => {
-    try {
-      const agentPath = path.join(agentsDir, agent.path);
-
-      if (fs.existsSync(agentPath)) {
-        activeAgents.push({
-          id: agent.id,
-          name: agent.name,
-          status: 'ready'
-        });
-      }
-    } catch (error) {
-      console.error(`❌ Failed to initialize agent ${agent.name}:`, error.message);
-    }
-  });
-
-  return activeAgents;
-}
-
-/**
- * Display session start banner
- */
-function displayBanner(variant, agentCount, skillCount) {
-  const variantColors = {
-    lite: '\x1b[32m',      // Green
-    standard: '\x1b[34m',   // Blue
-    pro: '\x1b[35m'        // Magenta
-  };
-
-  const color = variantColors[variant] || '\x1b[36m'; // Default cyan
-  const reset = '\x1b[0m';
-  const bold = '\x1b[1m';
-
-  console.log(`
-${bold}${color}╔═══════════════════════════════════════════════╗${reset}
-${bold}${color}║        Agentic Kit - ${variant.charAt(0).toUpperCase() + variant.slice(1)} Variant${' '.repeat(Math.max(0, 17 - variant.length))}║${reset}
-${bold}${color}╚═══════════════════════════════════════════════╝${reset}
-
-✨ Session started successfully!
-
-📊 Active Components:
-   • Agents: ${agentCount}
-   • Skills: ${skillCount}
-
-🎯 Orchestrator-First Pattern Active:
-   • All requests route through orchestrator unless you specify:
-     - Explicit agent: @agent-id or "As agent-id, ..."
-     - Direct skill: /skill-name
-   • Orchestrator will ask clarifying questions at each workflow step
-   • See AGENTS.md for 9 common workflow patterns
-
-💡 Quick Start:
-   • Invoke agents: ${color}@Master:${reset} help
-   • See agents: ${color}@Master:${reset} *help
-   • Documentation: Check README.md
-
-${bold}Ready to assist with your development tasks!${reset}
-`);
-}
-
-/**
- * Main session start handler
- */
-function onSessionStart(context) {
-  try {
-    // Get variant from context or default to standard
-    const variant = context.variant || 'standard';
-    const manifest = context.manifest || {};
-
-    const agentsList = manifest.agents || [];
-    const skillsList = manifest.skills || [];
-
-    // Load skills
-    const loadedSkills = loadSkills(context.skillsPath || './skills', skillsList);
-
-    // Initialize agents
-    const activeAgents = initializeAgents(context.agentsPath || './agents', agentsList);
-
-    // Display banner
-    displayBanner(variant, activeAgents.length, loadedSkills.length);
-
-    // Return session context
-    return {
-      variant,
-      agents: activeAgents,
-      skills: loadedSkills,
-      timestamp: new Date().toISOString(),
-      status: 'ready'
-    };
-
-  } catch (error) {
-    console.error('❌ Session start failed:', error.message);
-    console.log('⚠️  Plugin may not function correctly. Please restart or reinstall.');
-
-    return {
-      status: 'error',
-      error: error.message
-    };
-  }
-}
-
-/**
- * Module exports
- */
-module.exports = {
-  onSessionStart,
-  loadSkills,
-  initializeAgents,
-  displayBanner
-};

package/packages/claude/resources/agent-teams.yaml

@@ -1,50 +0,0 @@
-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:
-    - product-owner
-    - scrum-master
-    - full-stack-dev
-    - qa-test-architect
-    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