@champpaba/claude-agent-kit 2.1.0 → 2.1.2

package/.claude/agents/02-uxui-frontend.md

@@ -18,6 +18,13 @@ color: blue
 
 Complete these steps before implementation:
 
+0. **Library Requirements Check**
+   - Review `tasks.md` for "Install X", "Configure X" patterns
+   - Review `design.md` for "D1: Use X Library" decisions
+   - Use the specified libraries (WHY: team chose them for specific reasons)
+   - Example: tasks.md says "Install shadcn/ui" → Use shadcn components, follow its docs
+
+
 1. **Context Discovery** - Load project context (STEP 0)
 2. **Design Loading** - Load style guide or design principles (STEP 0.5)
 3. **Component Search** - Check existing components (STEP 3)

package/.claude/agents/04-frontend.md

@@ -18,6 +18,13 @@ color: green
 
 Complete these steps before implementation:
 
+0. **Library Requirements Check**
+   - Review `tasks.md` for "Install X", "Configure X" patterns
+   - Review `design.md` for "D1: Use X Library" decisions
+   - Use the specified libraries (WHY: team chose them for specific reasons)
+   - Example: tasks.md says "Install react-query" → Use react-query, follow its docs
+
+
 1. **Pattern Loading** - Load error-handling, state management patterns
 2. **UI Review** - Read existing UI components (from uxui-frontend)
 3. **API Review** - Read API endpoints (from backend/integration)

package/.claude/agents/05-backend.md

@@ -7,7 +7,7 @@ color: cyan
 
 # Backend Agent
 
-> **Version:** 2.0.0 (Claude 4.5 Optimized)
+> **Version:** 2.1.2 (Instruction-based Library Detection)
 > **Role:** Create API endpoints with validation, business logic, and error handling.
 
 ---
@@ -18,6 +18,12 @@ color: cyan
 
 Complete these steps before implementation:
 
+0. **Library Requirements Check**
+   - Review `tasks.md` for "Install X", "Configure X" patterns
+   - Review `design.md` for "D1: Use X Library" decisions
+   - Use the specified libraries (WHY: team chose them for specific reasons)
+   - Example: tasks.md says "Install better-auth" → Use better-auth, follow its docs
+
 1. **Pattern Loading** - Load error-handling, logging, testing patterns
 2. **Endpoint Search** - Check for existing similar endpoints
 3. **TDD Plan** - If TDD required, plan test cases first

package/.claude/agents/06-database.md

@@ -7,7 +7,7 @@ color: pink
 
 # Database Agent
 
-> **Version:** 2.0.0 (Claude 4.5 Optimized)
+> **Version:** 2.1.2 (Instruction-based Library Detection)
 > **Role:** Design schemas, create migrations, write complex queries, optimize performance.
 
 ---
@@ -18,6 +18,12 @@ color: pink
 
 Complete these steps before implementation:
 
+0. **Library Requirements Check**
+   - Review `tasks.md` for "Install X", "Configure X" patterns
+   - Review `design.md` for "D1: Use X Library" decisions
+   - Use the specified libraries (WHY: team chose them for specific reasons)
+   - Example: design.md says "Use Drizzle ORM" → Use Drizzle, follow its docs
+
 1. **Pattern Loading** - Load ORM patterns from Context7
 2. **Schema Search** - Check existing models/schemas
 3. **Design Plan** - Plan tables, relationships, indexes

package/.claude/agents/_shared/pre-work-checklist.md

@@ -1,6 +1,6 @@
 # Pre-Work Checklist (Shared by All Agents)
 
-> **Version:** 2.0.0 (Claude 4.5 Optimized)
+> **Version:** 2.1.2 (Instruction-based Library Detection)
 > **Purpose:** Single source of truth for pre-work validation
 
 ---
@@ -9,6 +9,40 @@
 
 Complete these steps before implementation to ensure alignment with project standards:
 
+### Step 0: Library Requirements Check
+
+**Scan for required libraries before writing code:**
+
+1. **Read `tasks.md`** - Look for these patterns:
+   - `Install X and dependencies` → Use library X
+   - `Configure X with Y adapter` → Use X with adapter Y
+   - Backtick packages like `better-auth` → Required dependency
+
+2. **Read `design.md`** - Look for these patterns:
+   - `### D1: Use X Library` → Decision to use X
+   - `**Decision:** Use X` → Chosen library
+   - Alternatives table → Shows why X was chosen over others
+
+3. **List required libraries** in your validation report
+
+4. **Use the libraries specified in tasks.md/design.md**
+   - WHY: The team chose these libraries for specific reasons (compatibility, features, constraints)
+   - Custom implementations waste effort and may miss edge cases the library handles
+
+**Example:**
+```
+tasks.md says: "Install better-auth and dependencies"
+→ Use better-auth library
+→ Follow better-auth documentation patterns
+
+WHY not custom? better-auth handles OAuth flows, session management, 
+and security edge cases that custom code would need to re-implement.
+```
+
+---
+
+### Step 1-4: Standard Checks
+
 1. **Context Discovery** - Load project context via agent-discovery.md
 2. **Pattern Loading** - Load relevant patterns for your agent type
 3. **Validation Report** - Provide pre-implementation validation report
@@ -23,6 +57,11 @@ Complete these steps before implementation to ensure alignment with project stan
 ```markdown
 Pre-Implementation Validation
 
+Library Requirements: (Step 0)
+- [ ] Scanned tasks.md for "Install X" patterns
+- [ ] Scanned design.md for design decisions
+- Required libraries: {list from tasks.md/design.md}
+
 Project Context:
 - Project: {name}
 - Stack: {tech-stack}
@@ -41,7 +80,8 @@ Best Practices:
 Ready to Implement:
 - [ ] Task understood
 - [ ] Dependencies identified
-- [ ] Approach planned
+- [ ] Required libraries identified
+- [ ] Approach planned (using specified libraries)
 ```
 
 ---
@@ -49,9 +89,10 @@ Ready to Implement:
 ## Why This Matters
 
 Pre-work validation prevents:
+- **Wrong library choices** - Using custom code when a library was already chosen by the team
 - Misaligned implementations (wrong patterns, wrong style)
 - Duplicate components (not searching existing code first)
 - Wrong package manager usage (CI/CD breaks)
 - Missing best practices (outdated patterns)
 
-→ 80% of implementation issues caught at validation stage
+→ 80% of implementation issues are caught at validation stage

package/.claude/commands/cdev.md

@@ -94,7 +94,7 @@ See: `.claude/lib/agent-executor.md` for full implementation
 ```typescript
 // Step 4: Invoke Agent with Retry & Validation
 
-// 4.1: Build agent prompt (with design reference + best practices - v1.8.0)
+// 4.1: Build agent prompt (with design reference + best practices - v2.1.2)
 function buildAgentPrompt(phase, changeContext) {
   let prompt = `
 # Phase ${phase.phase_number}: ${phase.name}
@@ -106,6 +106,47 @@ ${changeContext.proposal}
 ${changeContext.tasks}
 
 ${phase.instructions}
+
+---
+
+## 📦 Library Requirements
+
+**Scan for required libraries before implementation:**
+
+1. **Review tasks.md above** for these patterns:
+   - "Install X and dependencies" → Use library X
+   - "Configure X with Y adapter" → Use X with adapter Y
+   - Backtick packages like \`better-auth\` → Required dependency
+
+2. **Review design.md** (in change context) for:
+   - "### D1: Use X Library" → Decision to use X
+   - "**Decision:** Use X" → Chosen library
+   - Alternatives table shows why this library was chosen
+
+3. **Use the specified libraries**
+   - WHY: The team chose these for compatibility, features, or constraints
+   - Custom implementations duplicate effort and miss edge cases the library handles
+   - Follow library documentation patterns for consistency
+
+**Example:**
+\`\`\`
+tasks.md: "Install better-auth and dependencies"
+→ Use better-auth library
+→ Follow better-auth docs for setup
+
+WHY not custom? better-auth handles OAuth, sessions, security
+edge cases that custom code would need to re-implement.
+\`\`\`
+
+**Report required libraries in your validation:**
+\`\`\`
+Required Libraries Found:
+- better-auth (tasks.md line 6)
+- @better-auth/drizzle (tasks.md line 6)
+- ioredis (design.md D2)
+\`\`\`
+
+---
 `
 
   // Add best-practices reference for ALL agents

package/.claude/commands/pstatus.md

@@ -43,7 +43,7 @@ Create it now? (yes/no)
   const answer = await askUser()
   if (answer === 'yes') {
     // Copy from template
-    copy('PROJECT_STATUS.template.yml', statusPath)
+    copy('.claude/templates/PROJECT_STATUS.template.yml', statusPath)
     output('✅ Created PROJECT_STATUS.yml - please fill in your project details')
     return
   } else {

package/.claude/contexts/patterns/change-workflow.md

@@ -18,34 +18,7 @@ This pattern describes how the multi-agent system integrates with OpenSpec to de
 
 ## 📋 Workflow Commands
 
-### 1. `/psetup` - Project Setup (One-Time)
-
-**When to use:** First time setting up the project
-
-**What it does:**
-1. Detects tech stack from package files
-2. Queries Context7 for best practices
-3. Creates `domain/` structure (3-level indexing)
-4. Generates framework-specific best practices files
-
-**Output:**
-```
-.claude/contexts/domain/
-├── index.md                              # Level 1 - Project Registry
-└── {project}/
-    ├── README.md                         # Level 2 - Project Overview
-    ├── tech-stack.md                     # Tech details
-    └── best-practices/
-        ├── index.md                      # Level 3 - Best Practices Registry
-        ├── react-18.md
-        ├── nextjs-15.md
-        ├── prisma-6.md
-        └── vitest-2.md
-```
-
----
-
-### 2. `/csetup {change-id}` - Change Setup
+### 1. `/csetup {change-id}` - Change Setup (Includes Project Setup)
 
 **When to use:** After creating OpenSpec change, before development
 
@@ -78,7 +51,7 @@ openspec/changes/CHANGE-XXX/.claude/
 
 ---
 
-### 3. `/cdev {change-id}` - Start/Continue Development
+### 2. `/cdev {change-id}` - Start/Continue Development
 
 **When to use:** After `/csetup`, to execute agent workflow
 
@@ -159,7 +132,7 @@ Ready to archive!
 
 ---
 
-### 4. `/cview {change-id}` - View Progress
+### 3. `/cview {change-id}` - View Progress
 
 **When to use:** Check detailed phase-by-phase progress
 
@@ -228,7 +201,7 @@ Ready to archive!
 
 ---
 
-### 5. `/cstatus {change-id}` - Quick Status
+### 4. `/cstatus {change-id}` - Quick Status
 
 **When to use:** Quick glance at progress
 
@@ -485,27 +458,22 @@ else template = 'full-stack' // Safe default
 
 ## 🎯 Best Practices
 
-### 1. Always Run `/psetup` First
-- One-time project setup
-- Generates framework-specific best practices
-- Required for agent discovery
-
-### 2. Use `/csetup` After Creating OpenSpec Change
+### 1. Run `/csetup` First
+- Auto-detects tech stack and generates best practices
 - Analyzes tasks and generates workflow
-- Creates per-change context
-- Enables progress tracking
+- Required for agent discovery
 
-### 3. Use `/cdev` for Execution
+### 2. Use `/cdev` for Execution
 - Orchestrates agent workflow
 - Updates progress automatically
 - Handles user actions
 
-### 4. Check Progress with `/cview` or `/cstatus`
+### 3. Check Progress with `/cview` or `/cstatus`
 - `/cview` for detailed breakdown
 - `/cstatus` for quick glance
 - Real-time updates from `flags.json`
 
-### 5. Agents Update `flags.json` After Each Phase
+### 4. Agents Update `flags.json` After Each Phase
 - Marks phase as completed
 - Records actual time spent
 - Lists files created
@@ -519,7 +487,7 @@ else template = 'full-stack' // Safe default
 **Solution:** Run `/csetup {change-id}` first
 
 **Problem:** Agent doesn't load project context
-**Solution:** Run `/psetup` to create domain/ structure
+**Solution:** Run `/csetup` to create domain/ structure (auto-detects tech stack)
 
 **Problem:** Progress tracking not working
 **Solution:** Check if `flags.json` exists and is valid JSON

package/.claude/lib/README.md

@@ -46,7 +46,7 @@ Unified pattern for loading design system files. 3-tier strategy: STYLE_TOKENS.j
 ## 📁 Detailed Guides (v1.4.0 - NEW!)
 
 **`detailed-guides/best-practices-system.md`** - How best practices work
-Complete guide to auto-generated best practices via Context7 MCP. Covers `/agentsetup`, 3-level indexing, and agent discovery flow.
+Complete guide to auto-generated best practices via Context7 MCP. Covers `/csetup`, 3-level indexing, and agent discovery flow.
 
 **`detailed-guides/context-optimization.md`** - Token optimization strategy
 Details the 70% token reduction in design system loading. Explains 3-tier loading, before/after comparisons, and benefits.

package/.claude/lib/agent-router.md

@@ -156,7 +156,7 @@ const WORK_PATTERNS = {
 
   'orchestration': {
     keywords: [
-      '/cdev', '/csetup', '/cview', '/cstatus', '/psetup',
+      '/cdev', '/csetup', '/cview', '/cstatus', '/pstatus',
       'continue workflow', 'next phase', 'progress'
     ],
     agent: 'main-claude',

package/.claude/lib/context-loading-protocol.md

@@ -18,7 +18,7 @@ This protocol defines how agents discover and load context before starting work.
 
 **Who uses this:**
 - All 6 agents (integration, uxui-frontend, test-debug, frontend, backend, database)
-- Commands that need tech stack info (/agentsetup, /csetup, /cdev)
+- Commands that need tech stack info (/csetup, /cdev)
 
 ---
 
@@ -92,7 +92,7 @@ From tech-stack.md, extract:
 
 ```
 ⚠️ tech-stack.md not found!
-💡 User should run: /agentsetup
+💡 User should run: /csetup
 
 FALLBACK (use ONLY if absolutely necessary):
 - Detect from package.json (JavaScript)
@@ -383,7 +383,7 @@ Troubleshooting:
 ⚠️ Warning: tech-stack.md shows pnpm, but pnpm-lock.yaml not found
 
 Suggestion:
-- Run: /agentsetup (regenerate tech-stack.md)
+- Run: /csetup (regenerate tech-stack.md)
 - Or manually update tech-stack.md
 ```
 
@@ -392,7 +392,7 @@ Suggestion:
 ## 🔄 When to Re-load Context
 
 **Re-load Level 0-2 when:**
-- ✅ User runs `/agentsetup` (tech stack changed)
+- ✅ User runs `/csetup` (tech stack changed)
 - ✅ Framework version upgraded
 - ✅ New dependencies added
 

package/.claude/lib/detailed-guides/agent-system.md

@@ -110,7 +110,7 @@ WHY routing matters: Specialist agents have domain-specific validation (design t
 
 WHY: STYLE_GUIDE.md has project-specific tokens. design/*.md has universal principles.
 
-**Fallback:** If discovery fails, suggest `/agentsetup` or `/designsetup`
+**Fallback:** If discovery fails, suggest `/csetup` or `/designsetup`
 
 ---
 

package/.claude/lib/detailed-guides/best-practices-system.md

@@ -8,7 +8,7 @@
 
 ## 📚 How It Works
 
-1. **Run `/agentsetup`** to detect tech stack and generate best practices
+1. **Run `/csetup`** to detect tech stack and generate best practices
 2. **Context7 queries** latest framework docs (React, Next.js, Prisma, etc.)
 3. **Best practices files** created in `domain/{project}/best-practices/`
 4. **Agents auto-discover** project via 3-level indexing
@@ -119,11 +119,10 @@ design-system/
 # 1. Generate style guide FIRST (optional but recommended)
 /designsetup
 
-# 2. Setup project (discovers style guide)
-/psetup
+# 2. Setup change and project (discovers style guide, auto-detects tech stack)
+/csetup feature-login
 
 # 3. Start development (agents use STYLE_GUIDE.md)
-/csetup feature-login
 /cdev feature-login
 ```
 
@@ -143,8 +142,7 @@ design-system/
 
 ## 🔗 See Also
 
-- `../../commands/agentsetup.md` - /agentsetup command (generates best practices)
+- `../../commands/csetup.md` - /csetup command (setup change + auto-detect tech stack + generate best practices)
 - `../../commands/designsetup.md` - /designsetup command (generates style guide)
-- `../../commands/psetup.md` - /psetup command (one-time project setup)
 - `../../contexts/patterns/agent-discovery.md` - Shared agent discovery flow
 - `context-loading-protocol.md` - How agents load framework-specific context

package/.claude/lib/detailed-guides/design-system.md

@@ -66,11 +66,10 @@ design-system/
 # 1. Generate style guide FIRST (optional but recommended)
 /designsetup
 
-# 2. Setup project (discovers style guide)
-/psetup
+# 2. Setup change and project (discovers style guide, auto-detects tech stack)
+/csetup feature-login
 
 # 3. Start development (agents use STYLE_GUIDE.md)
-/csetup feature-login
 /cdev feature-login
 ```
 

package/.claude/templates/design-context-template.md

@@ -1,6 +1,6 @@
 # Design Context: {PROJECT_NAME}
 
-> **Auto-generated by `/psetup` or `/designsetup`**
+> **Auto-generated by `/csetup` or `/designsetup`**
 > **Last updated:** {UPDATED_AT}
 
 ---
@@ -195,7 +195,7 @@ Tokens: ~500
 
 ## 🔄 When to Update This File
 
-Run `/psetup` or `/designsetup` again when:
+Run `/csetup` or `/designsetup` again when:
 - ✅ Design tokens change (new colors, spacing)
 - ✅ Component library changes (shadcn → Chakra UI)
 - ✅ STYLE_GUIDE.md updated

package/README.md

@@ -1,197 +1,46 @@
 # Claude Agent Kit
 
-> 🤖 **Multi-Agent Implementation Engine** - The perfect companion for [OpenSpec](https://github.com/Fission-AI/OpenSpec) spec-driven development
+> Multi-Agent Implementation Engine for [OpenSpec](https://github.com/Fission-AI/OpenSpec)
 
 [![npm version](https://badge.fury.io/js/@champpaba%2Fclaude-agent-kit.svg)](https://www.npmjs.com/package/@champpaba/claude-agent-kit)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-
----
-
-## What is this?
-
-**Claude Agent Kit** turns OpenSpec plans into working code using 6 specialized AI agents.
-
-```
-OpenSpec Planning → proposal.md + tasks.md
-                          ↓
-Claude Agent Kit → 6 agents execute in phases → Working code + tests
-```
-
----
 
 ## Quick Start
 
 ```bash
-# Install
 npm install -g @champpaba/claude-agent-kit
-
-# Initialize in your project
 cd your-project
 cak init
 
-# Use in Claude Code
-/csetup my-feature    # Setup change context
-/cdev my-feature      # Execute with agents
-/cstatus my-feature   # Check progress
-```
-
----
-
-## The 6 Agents
-
-| Agent | Phase | Responsibility |
-|-------|-------|----------------|
-| **uxui-frontend** | 1 | UI components with mock data |
-| **backend** | 2 | API endpoints |
-| **database** | 2 | Schemas, migrations |
-| **integration** | 2.5 | Validate API contracts |
-| **frontend** | 3 | Connect UI to APIs |
-| **test-debug** | 4 | Tests and bug fixes |
-
----
-
-## Commands
-
-### CLI Commands
-
-```bash
-cak init              # Initialize template
-cak update --backup   # Update to latest version
-```
-
-### Slash Commands (in Claude Code)
-
-| Command | Description |
-|---------|-------------|
-| `/designsetup` | Generate style guide (one-time) |
-| `/pageplan @prd.md` | Generate UI page plan |
-| `/csetup {id}` | Setup change context |
-| `/cdev {id}` | Execute with agents |
-| `/cview {id}` | Detailed progress |
-| `/cstatus {id}` | Quick status |
-| `/pstatus` | Update project status |
-
----
-
-## Cross-Session Context (v2.1.0)
-
-`PROJECT_STATUS.yml` helps Claude remember project state between sessions:
-
-```yaml
-# PROJECT_STATUS.yml
-current_focus:
-  description: "Building auth system"
-  active_change: auth-system
-
-infrastructure:
-  database: { status: healthy }
-  api: { status: healthy }
-
-blockers:
-  - id: domain-config
-    description: "Need domain for Cloudflare"
-    blocks: [production-launch]
-
-next_priorities:
-  - id: payment-integration
-    reason: "Revenue blocker"
-```
-
-Created by `cak init` (optional). Update with `/pstatus`.
-
----
-
-## Project Structure
-
-```
-your-project/
-├── PROJECT_STATUS.yml          # Cross-session context (optional)
-├── openspec/
-│   └── changes/{id}/
-│       ├── proposal.md         # From OpenSpec
-│       ├── tasks.md            # From OpenSpec
-│       └── page-plan.md        # From /pageplan
-├── design-system/
-│   └── STYLE_GUIDE.md          # From /designsetup
-└── .claude/
-    ├── agents/                 # 6 specialized agents
-    ├── commands/               # Slash commands
-    └── contexts/               # Patterns & domain context
-```
-
----
-
-## Key Features
-
-- ✅ **6 Specialized Agents** - Each focused on its domain
-- ✅ **Auto Best Practices** - Context7 MCP integration
-- ✅ **Design System** - Consistent UI via tokens.json
-- ✅ **Page Planning** - Component reuse, real content
-- ✅ **Progress Tracking** - flags.json, /cstatus, /cview
-- ✅ **Cross-Session Context** - PROJECT_STATUS.yml
-
----
-
-## Workflow Example
-
-```bash
-# 1. OpenSpec creates: proposal.md + tasks.md
-
-# 2. Setup (optional design + page plan)
-/designsetup
-/pageplan @prd.md
-
-# 3. Execute
+# In Claude Code
 /csetup my-feature
 /cdev my-feature
-
-# 4. Monitor
-/cstatus my-feature
 ```
 
----
+## Agents
 
-## Changelog
+| Agent | Phase | Role |
+|-------|-------|------|
+| uxui-frontend | 1 | UI with mock data |
+| backend | 2 | API endpoints |
+| database | 2 | Schemas |
+| integration | 2.5 | Contract validation |
+| frontend | 3 | Connect UI to API |
+| test-debug | 4 | Tests & fixes |
 
-### v2.1.0 (2025-12-01)
-- Added `PROJECT_STATUS.yml` for cross-session context
-- Added `/pstatus` command
-- `/csetup` reads blockers from PROJECT_STATUS.yml
-- `/cstatus` shows project + change status
+## Features
 
-### v2.0.0 (2025-11-30)
-- Claude 4.5 optimization (61% token reduction)
-- Design System v2.0 (tokens.json, selective patterns)
-- All agents use Opus 4.5 model
+- **Instruction-based Library Detection** - Agents scan `tasks.md`/`design.md` for required libraries
+- **Cross-session Context** - `PROJECT_STATUS.yml` maintains state across sessions
+- **Design System v2.0** - Interactive setup with theme selection
 
-### v1.8.0 (2025-11-26)
-- Merged `/psetup` into `/csetup`
-- Auto tech stack detection
-- Auto best-practices from Context7
+## Commands
 
-[Full changelog in releases](https://github.com/ChampPABA/claude-multi-agent-template/releases)
+**CLI:** `cak init` | `cak update`
 
----
+**Slash:** `/designsetup` `/pageplan` `/csetup {id}` `/cdev {id}` `/cstatus {id}` `/pstatus`
 
 ## Links
 
-- [npm Package](https://www.npmjs.com/package/@champpaba/claude-agent-kit)
-- [GitHub](https://github.com/ChampPABA/claude-multi-agent-template)
-- [OpenSpec](https://github.com/Fission-AI/OpenSpec)
-- [Issues](https://github.com/ChampPABA/claude-multi-agent-template/issues)
-
----
-
-## License
-
-MIT License - see [LICENSE](LICENSE)
+[npm](https://www.npmjs.com/package/@champpaba/claude-agent-kit) | [GitHub](https://github.com/ChampPABA/claude-multi-agent-template) | [OpenSpec](https://github.com/Fission-AI/OpenSpec)
 
----
-
-**Ready to start?**
-
-```bash
-npm install -g @champpaba/claude-agent-kit
-cd your-project
-cak init
-```
+MIT License

package/lib/init.js

@@ -16,7 +16,7 @@ module.exports = async function init(options = {}) {
   // Paths
   const templatePath = path.join(__dirname, '../.claude');
   const targetPath = path.join(process.cwd(), '.claude');
-  const projectStatusTemplatePath = path.join(__dirname, '../PROJECT_STATUS.template.yml');
+  const projectStatusTemplatePath = path.join(__dirname, '../.claude/templates/PROJECT_STATUS.template.yml');
   const projectStatusTargetPath = path.join(process.cwd(), 'PROJECT_STATUS.yml');
 
   console.log(chalk.cyan('\n🤖 Claude Agent Kit - Initializing...\n'));

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@champpaba/claude-agent-kit",
-  "version": "2.1.0",
+  "version": "2.1.2",
   "description": "Universal multi-agent template for Claude Code - AI-assisted development with specialized agents",
   "main": "bin/cli.js",
   "bin": {
@@ -10,8 +10,7 @@
   "files": [
     "bin/",
     "lib/",
-    ".claude/",
-    "PROJECT_STATUS.template.yml"
+    ".claude/"
   ],
   "scripts": {
     "test": "echo \"No tests yet\" && exit 0"