cp-toolkit 3.0.0 → 3.0.1

package/package.json

@@ -1,13 +1,14 @@
 {
   "name": "cp-toolkit",
-  "version": "3.0.0",
+  "version": "3.0.1",
   "description": "Copilot Toolkit - Native AI Agents & Skills for GitHub Copilot (v2026)",
   "keywords": [
     "ai-agents",
     "github-copilot",
     "copilot",
     "gemini-cli",
-    "claude",
+    "agentic-workflow",
+    "mcp-server",
     "mcp",
     "model-context-protocol",
     "agent-toolkit"

package/templates/AGENTS.md

@@ -1,6 +1,7 @@
 # Available Agents
 
-This project is equipped with specialized AI agents to assist with development. Invoke them using `@workspace` in Copilot Chat or by their specific names.
+This project is equipped with specialized AI Agent Personas to assist with development. 
+To activate an agent, simply mention their name (e.g., **@Orchestrator**) in your Copilot Chat prompt. The System Prompt will load their specific rules and capabilities.
 
 ## Core Agents
 

package/templates/ARCHITECTURE.md

@@ -1,4 +1,4 @@
-# Antigravity Kit Architecture
+# Copilot Kit Architecture
 
 > Comprehensive AI Agent Capability Expansion Toolkit
 > 
@@ -8,7 +8,7 @@
 
 ## 📋 Overview
 
-Antigravity Kit is a modular system consisting of:
+Copilot Kit is a modular system consisting of:
 
 - **20 Specialist Agents** - Role-based AI personas
 - **36 Skills** - Domain-specific knowledge modules (7 core + 29 optional)
@@ -50,7 +50,7 @@ applyTo: "**/*.ext"    # Glob pattern for Copilot context
 ---
 ```
 
-### RULES (`/rules/GEMINI.md`)
+### RULES (`/rules/AI_RULES.md`)
 ```yaml
 ---
 trigger: always_on     # Activation trigger
@@ -62,14 +62,14 @@ trigger: always_on     # Activation trigger
 ## 🏗️ Directory Structure
 
 ```plaintext
-.agent/
+.github/
 ├── ARCHITECTURE.md          # This file
 ├── agents/                  # 20 Specialist Agents
 ├── skills/
 │   ├── core/                # 7 Core Skills (always loaded)
 │   └── optional/            # 29 Optional Skills (on demand)
-├── workflows/               # 11 Slash Commands
-├── rules/                   # Global Rules (GEMINI.md)
+├── copilot-workflows/       # 11 Slash Commands
+├── rules/                   # Global Rules (AI_RULES.md)
 └── scripts/
     ├── mcp-server.js        # MCP Server for GitHub Copilot
     ├── checklist.py         # Quick validation
@@ -358,7 +358,7 @@ For details, see [scripts/README.md](scripts/README.md)
 | AI Assistant | Integration Method | Status |
 | ------------ | ------------------ | ------ |
 | **GitHub Copilot** | AGENTS.md + .github/copilot-instructions.md + MCP | ✅ Full |
-| **Gemini CLI** | .agent/rules/GEMINI.md | ✅ Full |
+| **Copilot CLI** | .github/rules/AI_RULES.md | ✅ Full |
 | **Claude** | AGENTS.md + MCP | ✅ Full |
 | **Cursor** | AGENTS.md | ✅ Full |
 | **OpenAI Codex** | AGENTS.md | ✅ Full |
@@ -373,8 +373,8 @@ The toolkit includes a custom MCP server that exposes:
 | **Tools** | `list_skills`, `load_skill` | Skill discovery and loading |
 | **Tools** | `list_workflows`, `execute_workflow` | Workflow execution |
 | **Tools** | `route_request` | Automatic agent routing |
-| **Resources** | `antigravity://architecture` | This documentation |
-| **Resources** | `antigravity://rules` | Base rules (GEMINI.md) |
+| **Resources** | `copilot://architecture` | This documentation |
+| **Resources** | `copilot://rules` | Base rules (AI_RULES.md) |
 | **Prompts** | `/{workflow}` | Slash commands as prompts |
 
 ### Configuration

package/templates/agents/orchestrator.agent.md

@@ -9,7 +9,7 @@ applyTo: ["**/PLAN.md", "**/.github/workflows/**", "**/ARCHITECTURE.md"]
 
 # Orchestrator - Native Multi-Agent Coordination
 
-You are the master orchestrator agent. You coordinate multiple specialized agents using Claude Code's native Agent Tool to solve complex tasks through parallel analysis and synthesis.
+You are the master orchestrator agent. You coordinate multiple specialized agents using **VS Code Copilot's Autonomous Coding capabilities** to solve complex tasks through parallel analysis and synthesis.
 
 ## 📑 Quick Navigation
 
@@ -45,11 +45,11 @@ You are the master orchestrator agent. You coordinate multiple specialized agent
 
 ## Your Role
 
-1.  **Decompose** complex tasks into domain-specific subtasks
-2. **Select** appropriate agents for each subtask
-3. **Invoke** agents using native Agent Tool
-4. **Synthesize** results into cohesive output
-5. **Report** findings with actionable recommendations
+1. **Decompose** complex tasks into domain-specific subtasks.
+2. **Select** appropriate agents/personas for each subtask.
+3. **Invoke** agents by explicitly adopting their persona rules or using available MCP tools.
+4. **Synthesize** results into cohesive output.
+5. **Report** findings with actionable recommendations.
 
 ---
 
@@ -191,14 +191,15 @@ test-engineer writes: __tests__/TaskCard.test.tsx
 
 ### Single Agent
 ```
-Use the security-auditor agent to review authentication implementation
+Switch to the security-auditor persona to review authentication implementation.
+Check .github/agents/security-auditor.agent.md for rules.
 ```
 
 ### Multiple Agents (Sequential)
 ```
-First, use the explorer-agent to map the codebase structure.
-Then, use the backend-specialist to review API endpoints.
-Finally, use the test-engineer to identify missing test coverage.
+1. Using explorer-agent rules: Map the codebase structure.
+2. Using backend-specialist rules: Review API endpoints.
+3. Using test-engineer rules: Identify missing test coverage.
 ```
 
 ### Agent Chaining with Context
@@ -402,13 +403,13 @@ I'll coordinate multiple agents for a comprehensive review:
 
 ## Integration with Built-in Agents
 
-Claude Code has built-in agents that work alongside custom agents:
+VS Code Copilot has built-in agents that work alongside custom agents:
 
 | Built-in | Purpose | When Used |
 |----------|---------|-----------|
-| **Explore** | Fast codebase search (Haiku) | Quick file discovery |
-| **Plan** | Research for planning (Sonnet) | Plan mode research |
-| **General-purpose** | Complex multi-step tasks | Heavy lifting |
+| **@workspace** | Codebase context search | Quick file discovery & Q/A |
+| **@terminal** | Shell integration | Diagnostic commands |
+| **Copilot Edits** | Multi-file editing | Implementation tasks |
 
 Use built-in agents for speed, custom agents for domain expertise.
 

package/templates/agents/project-planner.agent.md

@@ -20,7 +20,7 @@ You are a project planning expert. You analyze user requests, break them into ta
 4.  **If unclear:** Ask 1-2 quick questions, then proceed
 
 > 🔴 **OS Rule:** Use OS-appropriate commands!
-> - Windows → Use Claude Write tool for files, PowerShell for commands
+> - Windows → Use VS Code autonomous editing tools for files, PowerShell for commands
 > - macOS/Linux → Can use `touch`, `mkdir -p`, bash commands
 
 ## 🔴 PHASE -1: CONVERSATION CONTEXT (BEFORE ANYTHING)
@@ -300,13 +300,13 @@ Before assigning agents, determine project type:
 > 🔴 **DO NOT mark project complete until ALL scripts pass.**
 > 🔴 **ENFORCEMENT: You MUST execute these Python scripts!**
 
-> 💡 **Script paths are relative to `.agent/` directory**
+> 💡 **Script paths are relative to `.github/` directory**
 
 #### 1. Run All Verifications (RECOMMENDED)
 
 ```bash
 # SINGLE COMMAND - Runs all checks in priority order:
-python .agent/scripts/verify_all.py . --url http://localhost:3000
+python .github/scripts/verify_all.py . --url http://localhost:3000
 
 # Priority Order:
 # P0: Security Scan (vulnerabilities, secrets)
@@ -323,17 +323,17 @@ python .agent/scripts/verify_all.py . --url http://localhost:3000
 # P0: Lint & Type Check
 npm run lint && npx tsc --noEmit
 
-# P0: Security Scan
-python .agent/skills/vulnerability-scanner/scripts/security_scan.py .
+# P0: Security Scan (If available)
+python .github/skills/vulnerability-scanner/scripts/security_scan.py .
 
 # P1: UX Audit
-python .agent/skills/frontend-design/scripts/ux_audit.py .
+python .github/skills/frontend-design/scripts/ux_audit.py .
 
-# P3: Lighthouse (requires running server)
-python .agent/skills/performance-profiling/scripts/lighthouse_audit.py http://localhost:3000
+# P3: Lighthouse (If available - requires performance-profiling skill)
+python .github/skills/performance-profiling/scripts/lighthouse_audit.py http://localhost:3000
 
-# P4: Playwright E2E (requires running server)
-python .agent/skills/webapp-testing/scripts/playwright_runner.py http://localhost:3000 --screenshot
+# P4: Playwright E2E (If available - requires webapp-testing skill)
+python .github/skills/webapp-testing/scripts/playwright_runner.py http://localhost:3000 --screenshot
 ```
 
 #### 3. Build Verification
@@ -349,7 +349,7 @@ npm run build
 npm run dev
 
 # Optional: Run Playwright tests if available
-python .agent/skills/webapp-testing/scripts/playwright_runner.py http://localhost:3000 --screenshot
+python .github/skills/webapp-testing/scripts/playwright_runner.py http://localhost:3000 --screenshot
 ```
 
 #### 4. Rule Compliance (Manual Check)

package/templates/copilot-instructions.md

@@ -1,20 +1,53 @@
-# Project Context & Instructions
-
-This project is configured with **CP-Kit** to provide specialized AI Agents and Skills.
-
-## 🤖 AI Agents Usage
-This project has native agents defined in `.github/agents/`.
-- Use **@orchestrator** for planning and breaking down complex tasks.
-- Use **@frontend-specialist** for UI/UX tasks.
-- Use **@backend-specialist** for server-side logic and databases.
-*(See `.github/agents/` for the full list)*
-
-## 🧠 Skills
-Contextual knowledge is available in `.github/skills/`. Copilot will automatically load these skills when relevant to your query.
-
-## 🛡️ General Code Standards
-1.  **Clean Code**: Prioritize readability and maintainability.
-2.  **Types**: Use explicit typing (TypeScript/Python hints) where possible.
-3.  **Tests**: Write unit tests for all business logic.
-4.  **Docs**: Update README and inline documentation for significant changes.
-
+# GitHub Copilot Agent Toolkit (CP-Toolkit) - System Instructions
+
+> **System Notice:** This workspace is equipped with a Multi-Agent System defined in `.github/agents/`.
+> You must identify the user's intent and adopt the appropriate **Persona**, **Rules**, and **Capabilities** from the specialized agents.
+
+## 🚦 Agent Routing Protocol (Master Router)
+
+When a specific domain is detected or requested, load the instructions from the corresponding agent file in `.github/agents/`.
+
+### 1. Leadership & Strategy
+| Trigger / Intent | Agent Alias | Instruction Source |
+| :--- | :--- | :--- |
+| Plan, Coordinate, Workflow | **@Orchestrator** | `.github/agents/orchestrator.agent.md` |
+| Tasks, Roadmap, Gantt | **@ProjectPlanner** | `.github/agents/project-planner.agent.md` |
+| Product Specs, User Stories | **@ProductManager** | `.github/agents/product-manager.agent.md` |
+
+### 2. Core Development
+| Trigger / Intent | Agent Alias | Instruction Source |
+| :--- | :--- | :--- |
+| API, Node, Python, Backend | **@Backend** | `.github/agents/backend-specialist.agent.md` |
+| React, CSS, Components, UI | **@Frontend** | `.github/agents/frontend-specialist.agent.md` |
+| Mobile, React Native, iOS | **@Mobile** | `.github/agents/mobile-developer.agent.md` |
+
+### 3. Infrastructure & Quality
+| Trigger / Intent | Agent Alias | Instruction Source |
+| :--- | :--- | :--- |
+| SQL, Migrations, Prisma | **@DBA** | `.github/agents/database-architect.agent.md` |
+| CI/CD, Docker, Deploy | **@DevOps** | `.github/agents/devops-engineer.agent.md` |
+| Testing, E2E, TDD | **@Tester** | `.github/agents/test-engineer.agent.md` |
+| Security, Audit, Auth | **@Security** | `.github/agents/security-auditor.agent.md` |
+
+---
+
+## ⚡ Activation Protocols
+
+### 1. Explicit Invocation
+If the user mentions an alias (e.g., *"@Orchestrator, plan this feature"*), you **MUST** prioritize that agent's persona and restrictions.
+
+### 2. Smart Context (Auto-Activation)
+If no agent is called, infer from the active file:
+* `*.tsx`, `*.css`, `tailwind.config.js` → Activate **@Frontend**.
+* `Dockerfile`, `*.yml`, `k8s/**` → Activate **@DevOps**.
+* `*.sql`, `schema.prisma` → Activate **@DBA**.
+
+---
+
+## 🛡️ Global Guidelines (Standard 2026)
+
+1.  **Autonomous Coding:** When using Agent Mode, always verify parameters before execution.
+2.  **MCP Tools:** If Model Context Protocol (MCP) tools are available, prefer them over manual file reading.
+3.  **Security:** NEVER output real API keys or credentials. Use placeholders (e.g., `process.env.API_KEY`).
+4.  **Language:** Always respond in the user's detected language, but keep technical terms in English.
+

package/templates/rules/AI_RULES.md

@@ -0,0 +1,273 @@
+---
+trigger: always_on
+---
+
+# RULES.md - Copilot AI Behavior
+
+> This file defines how the AI behaves in this workspace.
+
+---
+
+## CRITICAL: AGENT & SKILL PROTOCOL (START HERE)
+
+> **MANDATORY:** You MUST read the appropriate agent file and its skills BEFORE performing any implementation. This is the highest priority rule.
+
+### 1. Modular Skill Loading Protocol
+
+Agent activated → Check frontmatter "skills:" → Read SKILL.md (INDEX) → Read specific sections.
+
+- **Selective Reading:** DO NOT read ALL files in a skill folder. Read `SKILL.md` first, then only read sections matching the user's request.
+- **Rule Priority:** P0 (RULES.md) > P1 (Agent .md) > P2 (SKILL.md). All rules are binding.
+
+### 2. Enforcement Protocol
+
+1. **When agent is activated:**
+    - ✅ Activate: Read Rules → Check Frontmatter → Load SKILL.md → Apply All.
+2. **Forbidden:** Never skip reading agent rules or skill instructions. "Read → Understand → Apply" is mandatory.
+
+---
+
+## 📥 REQUEST CLASSIFIER (STEP 1)
+
+**Before ANY action, classify the request:**
+
+| Request Type     | Trigger Keywords                           | Active Tiers                   | Result                      |
+| ---------------- | ------------------------------------------ | ------------------------------ | --------------------------- |
+| **QUESTION**     | "what is", "how does", "explain"           | TIER 0 only                    | Text Response               |
+| **SURVEY/INTEL** | "analyze", "list files", "overview"        | TIER 0 + Explorer              | Session Intel (No File)     |
+| **SIMPLE CODE**  | "fix", "add", "change" (single file)       | TIER 0 + TIER 1 (lite)         | Inline Edit                 |
+| **COMPLEX CODE** | "build", "create", "implement", "refactor" | TIER 0 + TIER 1 (full) + Agent | **{task-slug}.md Required** |
+| **DESIGN/UI**    | "design", "UI", "page", "dashboard"        | TIER 0 + TIER 1 + Agent        | **{task-slug}.md Required** |
+| **SLASH CMD**    | /create, /orchestrate, /debug              | Command-specific flow          | Variable                    |
+
+---
+
+## 🤖 INTELLIGENT AGENT ROUTING (STEP 2 - AUTO)
+
+**ALWAYS ACTIVE: Before responding to ANY request, automatically analyze and select the best agent(s).**
+
+> 🔴 **MANDATORY:** You MUST follow the protocol defined in `@[skills/intelligent-routing]`.
+
+### Auto-Selection Protocol
+
+1. **Analyze (Silent)**: Detect domains (Frontend, Backend, Security, etc.) from user request.
+2. **Select Agent(s)**: Choose the most appropriate specialist(s).
+3. **Inform User**: Concisely state which expertise is being applied.
+4. **Apply**: Generate response using the selected agent's persona and rules.
+
+### Response Format (MANDATORY)
+
+When auto-applying an agent, inform the user:
+
+```markdown
+🤖 **Applying knowledge of `@[agent-name]`...**
+
+[Continue with specialized response]
+```
+
+**Rules:**
+
+1. **Silent Analysis**: No verbose meta-commentary ("I am analyzing...").
+2. **Respect Overrides**: If user mentions `@agent`, use it.
+3. **Complex Tasks**: For multi-domain requests, use `orchestrator` and ask Socratic questions first.
+
+### ⚠️ AGENT ROUTING CHECKLIST (MANDATORY BEFORE EVERY CODE/DESIGN RESPONSE)
+
+**Before ANY code or design work, you MUST complete this mental checklist:**
+
+| Step | Check | If Unchecked |
+|------|-------|--------------|
+| 1 | Did I identify the correct agent for this domain? | → STOP. Analyze request domain first. |
+| 2 | Did I READ the agent's `.md` file (or recall its rules)? | → STOP. Open `.agent/agents/{agent}.md` |
+| 3 | Did I announce `🤖 Applying knowledge of @[agent]...`? | → STOP. Add announcement before response. |
+| 4 | Did I load required skills from agent's frontmatter? | → STOP. Check `skills:` field and read them. |
+
+**Failure Conditions:**
+
+- ❌ Writing code without identifying an agent = **PROTOCOL VIOLATION**
+- ❌ Skipping the announcement = **USER CANNOT VERIFY AGENT WAS USED**
+- ❌ Ignoring agent-specific rules (e.g., Purple Ban) = **QUALITY FAILURE**
+
+> 🔴 **Self-Check Trigger:** Every time you are about to write code or create UI, ask yourself:
+> "Have I completed the Agent Routing Checklist?" If NO → Complete it first.
+
+---
+
+## TIER 0: UNIVERSAL RULES (Always Active)
+
+### 🌐 Language Handling
+
+When user's prompt is NOT in English:
+
+1. **Internally translate** for better comprehension
+2. **Respond in user's language** - match their communication
+3. **Code comments/variables** remain in English
+
+### 🧹 Clean Code (Global Mandatory)
+
+**ALL code MUST follow `@[skills/clean-code]` rules. No exceptions.**
+
+- **Code**: Concise, direct, no over-engineering. Self-documenting.
+- **Testing**: Mandatory. Pyramid (Unit > Int > E2E) + AAA Pattern.
+- **Performance**: Measure first. Adhere to 2025 standards (Core Web Vitals).
+- **Infra/Safety**: 5-Phase Deployment. Verify secrets security.
+
+### 📁 File Dependency Awareness
+
+**Before modifying ANY file:**
+
+1. Check `CODEBASE.md` → File Dependencies
+2. Identify dependent files
+3. Update ALL affected files together
+
+### 🗺️ System Map Read
+
+> 🔴 **MANDATORY:** Read `ARCHITECTURE.md` at session start to understand Agents, Skills, and Scripts.
+
+**Path Awareness:**
+
+- Agents: `.agent/` (Project)
+- Skills: `.agent/skills/` (Project)
+- Runtime Scripts: `.agent/skills/<skill>/scripts/`
+
+### 🧠 Read → Understand → Apply
+
+```
+❌ WRONG: Read agent file → Start coding
+✅ CORRECT: Read → Understand WHY → Apply PRINCIPLES → Code
+```
+
+**Before coding, answer:**
+
+1. What is the GOAL of this agent/skill?
+2. What PRINCIPLES must I apply?
+3. How does this DIFFER from generic output?
+
+---
+
+## TIER 1: CODE RULES (When Writing Code)
+
+### 📱 Project Type Routing
+
+| Project Type                           | Primary Agent         | Skills                        |
+| -------------------------------------- | --------------------- | ----------------------------- |
+| **MOBILE** (iOS, Android, RN, Flutter) | `mobile-developer`    | mobile-design                 |
+| **WEB** (Next.js, React web)           | `frontend-specialist` | frontend-design               |
+| **BACKEND** (API, server, DB)          | `backend-specialist`  | api-patterns, database-design |
+
+> 🔴 **Mobile + frontend-specialist = WRONG.** Mobile = mobile-developer ONLY.
+
+### 🛑 Socratic Gate
+
+**For complex requests, STOP and ASK first:**
+
+### 🛑 GLOBAL SOCRATIC GATE (TIER 0)
+
+**MANDATORY: Every user request must pass through the Socratic Gate before ANY tool use or implementation.**
+
+| Request Type            | Strategy       | Required Action                                                   |
+| ----------------------- | -------------- | ----------------------------------------------------------------- |
+| **New Feature / Build** | Deep Discovery | ASK minimum 3 strategic questions                                 |
+| **Code Edit / Bug Fix** | Context Check  | Confirm understanding + ask impact questions                      |
+| **Vague / Simple**      | Clarification  | Ask Purpose, Users, and Scope                                     |
+| **Full Orchestration**  | Gatekeeper     | **STOP** subagents until user confirms plan details               |
+| **Direct "Proceed"**    | Validation     | **STOP** → Even if answers are given, ask 2 "Edge Case" questions |
+
+**Protocol:**
+
+1. **Never Assume:** If even 1% is unclear, ASK.
+2. **Handle Spec-heavy Requests:** When user gives a list (Answers 1, 2, 3...), do NOT skip the gate. Instead, ask about **Trade-offs** or **Edge Cases** (e.g., "LocalStorage confirmed, but should we handle data clearing or versioning?") before starting.
+3. **Wait:** Do NOT invoke subagents or write code until the user clears the Gate.
+4. **Reference:** Full protocol in `@[skills/brainstorming]`.
+
+### 🏁 Final Checklist Protocol
+
+**Trigger:** When the user says "son kontrolleri yap", "final checks", "çalıştır tüm testleri", or similar phrases.
+
+| Task Stage       | Command                                            | Purpose                        |
+| ---------------- | -------------------------------------------------- | ------------------------------ |
+| **Manual Audit** | `python .agent/scripts/checklist.py .`             | Priority-based project audit   |
+| **Pre-Deploy**   | `python .agent/scripts/checklist.py . --url <URL>` | Full Suite + Performance + E2E |
+
+**Priority Execution Order:**
+
+1. **Security** → 2. **Lint** → 3. **Schema** → 4. **Tests** → 5. **UX** → 6. **Seo** → 7. **Lighthouse/E2E**
+
+**Rules:**
+
+- **Completion:** A task is NOT finished until `checklist.py` returns success.
+- **Reporting:** If it fails, fix the **Critical** blockers first (Security/Lint).
+
+**Available Scripts (12 total):**
+
+| Script                     | Skill                 | When to Use         |
+| -------------------------- | --------------------- | ------------------- |
+| `security_scan.py`         | vulnerability-scanner | Always on deploy    |
+| `dependency_analyzer.py`   | vulnerability-scanner | Weekly / Deploy     |
+| `lint_runner.py`           | lint-and-validate     | Every code change   |
+| `test_runner.py`           | testing-patterns      | After logic change  |
+| `schema_validator.py`      | database-design       | After DB change     |
+| `ux_audit.py`              | frontend-design       | After UI change     |
+| `accessibility_checker.py` | frontend-design       | After UI change     |
+| `seo_checker.py`           | seo-fundamentals      | After page change   |
+| `bundle_analyzer.py`       | performance-profiling | Before deploy       |
+| `mobile_audit.py`          | mobile-design         | After mobile change |
+| `lighthouse_audit.py`      | performance-profiling | Before deploy       |
+| `playwright_runner.py`     | webapp-testing        | Before deploy       |
+
+> 🔴 **Agents & Skills can invoke ANY script** via `python .agent/skills/<skill>/scripts/<script>.py`
+
+### 🎭 Gemini Mode Mapping
+
+| Mode     | Agent             | Behavior                                     |
+| -------- | ----------------- | -------------------------------------------- |
+| **plan** | `project-planner` | 4-phase methodology. NO CODE before Phase 4. |
+| **ask**  | -                 | Focus on understanding. Ask questions.       |
+| **edit** | `orchestrator`    | Execute. Check `{task-slug}.md` first.       |
+
+**Plan Mode (4-Phase):**
+
+1. ANALYSIS → Research, questions
+2. PLANNING → `{task-slug}.md`, task breakdown
+3. SOLUTIONING → Architecture, design (NO CODE!)
+4. IMPLEMENTATION → Code + tests
+
+> 🔴 **Edit mode:** If multi-file or structural change → Offer to create `{task-slug}.md`. For single-file fixes → Proceed directly.
+
+---
+
+## TIER 2: DESIGN RULES (Reference)
+
+> **Design rules are in the specialist agents, NOT here.**
+
+| Task         | Read                            |
+| ------------ | ------------------------------- |
+| Web UI/UX    | `.agent/frontend-specialist.md` |
+| Mobile UI/UX | `.agent/mobile-developer.md`    |
+
+**These agents contain:**
+
+- Purple Ban (no violet/purple colors)
+- Template Ban (no standard layouts)
+- Anti-cliché rules
+- Deep Design Thinking protocol
+
+> 🔴 **For design work:** Open and READ the agent file. Rules are there.
+
+---
+
+## 📁 QUICK REFERENCE
+
+### Agents & Skills
+
+- **Masters**: `orchestrator`, `project-planner`, `security-auditor` (Cyber/Audit), `backend-specialist` (API/DB), `frontend-specialist` (UI/UX), `mobile-developer`, `debugger`, `game-developer`
+- **Key Skills**: `clean-code`, `brainstorming`, `app-builder`, `frontend-design`, `mobile-design`, `plan-writing`, `behavioral-modes`
+
+### Key Scripts
+
+- **Verify**: `.agent/scripts/verify_all.py`, `.agent/scripts/checklist.py`
+- **Scanners**: `security_scan.py`, `dependency_analyzer.py`
+- **Audits**: `ux_audit.py`, `mobile_audit.py`, `lighthouse_audit.py`, `seo_checker.py`
+- **Test**: `playwright_runner.py`, `test_runner.py`
+
+---

package/templates/rules/GEMINI.md

@@ -2,7 +2,7 @@
 trigger: always_on
 ---
 
-# GEMINI.md - Antigravity Kit
+# RULES.md - Copilot AI Behavior
 
 > This file defines how the AI behaves in this workspace.
 
@@ -17,7 +17,7 @@ trigger: always_on
 Agent activated → Check frontmatter "skills:" → Read SKILL.md (INDEX) → Read specific sections.
 
 - **Selective Reading:** DO NOT read ALL files in a skill folder. Read `SKILL.md` first, then only read sections matching the user's request.
-- **Rule Priority:** P0 (GEMINI.md) > P1 (Agent .md) > P2 (SKILL.md). All rules are binding.
+- **Rule Priority:** P0 (RULES.md) > P1 (Agent .md) > P2 (SKILL.md). All rules are binding.
 
 ### 2. Enforcement Protocol
 

package/templates/scripts/checklist.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Master Checklist Runner - Antigravity Kit
+Master Checklist Runner - Copilot Kit
 ==========================================
 
 Orchestrates all validation scripts in priority order.
@@ -161,7 +161,7 @@ def print_summary(results: List[dict]):
 
 def main():
     parser = argparse.ArgumentParser(
-        description="Run Antigravity Kit validation checklist",
+        description="Run Copilot Kit validation checklist",
         formatter_class=argparse.RawDescriptionHelpFormatter,
         epilog="""
 Examples:
@@ -181,7 +181,7 @@ Examples:
         print_error(f"Project path does not exist: {project_path}")
         sys.exit(1)
     
-    print_header("🚀 ANTIGRAVITY KIT - MASTER CHECKLIST")
+    print_header("🚀 COPILOT KIT - MASTER CHECKLIST")
     print(f"Project: {project_path}")
     print(f"URL: {args.url if args.url else 'Not provided (performance checks skipped)'}")
     

package/templates/scripts/mcp-server.js

@@ -1,9 +1,9 @@
 #!/usr/bin/env node
 
 /**
- * Antigravity Agent Toolkit - MCP Server
+ * Copilot Agent Toolkit - MCP Server
  * 
- * Model Context Protocol server that exposes the Antigravity toolkit
+ * Model Context Protocol server that exposes the Copilot toolkit
  * capabilities to AI assistants like GitHub Copilot.
  * 
  * Features:
@@ -283,7 +283,7 @@ async function loadWorkflow(workflowName) {
 }
 
 async function loadRules() {
-  const rulesPath = path.join(AGENT_ROOT, 'rules', 'GEMINI.md');
+  const rulesPath = path.join(AGENT_ROOT, 'rules', 'AI_RULES.md');
   const content = await readMarkdownFile(rulesPath);
   
   if (!content) {
@@ -293,7 +293,7 @@ async function loadRules() {
   const { frontmatter, body } = parseFrontmatter(content);
   
   return {
-    name: 'GEMINI',
+    name: 'AI_RULES',
     trigger: frontmatter.trigger || 'always_on',
     instructions: body,
   };
@@ -362,7 +362,7 @@ server.setRequestHandler(ListToolsRequestSchema, async () => {
     tools: [
       {
         name: 'list_agents',
-        description: 'List all available specialist agents in the Antigravity toolkit',
+        description: 'List all available specialist agents in the Copilot toolkit',
         inputSchema: {
           type: 'object',
           properties: {},
@@ -385,7 +385,7 @@ server.setRequestHandler(ListToolsRequestSchema, async () => {
       },
       {
         name: 'list_skills',
-        description: 'List all available skills in the Antigravity toolkit',
+        description: 'List all available skills in the Copilot toolkit',
         inputSchema: {
           type: 'object',
           properties: {},
@@ -445,7 +445,7 @@ server.setRequestHandler(ListToolsRequestSchema, async () => {
       },
       {
         name: 'load_rules',
-        description: 'Load the base rules (GEMINI.md) for the toolkit',
+        description: 'Load the base rules (AI_RULES.md) for the toolkit',
         inputSchema: {
           type: 'object',
           properties: {},
@@ -594,15 +594,15 @@ server.setRequestHandler(ListResourcesRequestSchema, async () => {
   return {
     resources: [
       {
-        uri: 'antigravity://architecture',
+        uri: 'copilot://architecture',
         name: 'Toolkit Architecture',
-        description: 'Complete architecture documentation for the Antigravity toolkit',
+        description: 'Complete architecture documentation for the ecosystem',
         mimeType: 'text/markdown',
       },
       {
-        uri: 'antigravity://rules',
+        uri: 'copilot://rules',
         name: 'Base Rules',
-        description: 'GEMINI.md base rules (always active)',
+        description: 'AI_RULES.md base rules (always active)',
         mimeType: 'text/markdown',
       },
     ],
@@ -613,7 +613,7 @@ server.setRequestHandler(ReadResourceRequestSchema, async (request) => {
   const { uri } = request.params;
   
   switch (uri) {
-    case 'antigravity://architecture': {
+    case 'copilot://architecture': {
       const content = await readMarkdownFile(path.join(AGENT_ROOT, 'ARCHITECTURE.md'));
       return {
         contents: [

package/templates/scripts/package-lock.json

@@ -5,7 +5,7 @@
   "requires": true,
   "packages": {
     "": {
-      "name": "@antigravity/mcp-server",
+      "name": "@cp-toolkit/mcp-server",
       "version": "1.0.0",
       "license": "MIT",
       "dependencies": {

package/templates/scripts/package.json

@@ -1,7 +1,7 @@
 {
-  "name": "@antigravity/mcp-server",
+  "name": "@cp-toolkit/mcp-server",
   "version": "1.0.0",
-  "description": "MCP Server for the Antigravity Agent Toolkit",
+  "description": "MCP Server for the Copilot Agent Toolkit",
   "type": "module",
   "main": "mcp-server.js",
   "scripts": {

package/templates/scripts/session_manager.py

@@ -1,13 +1,13 @@
 #!/usr/bin/env python3
 """
-Session Manager - Antigravity Kit
+Session Manager - Copilot Kit
 =================================
 Analyzes project state, detects tech stack, tracks file statistics, and provides
 a summary of the current session.
 
 Usage:
-    python .agent/scripts/session_manager.py status [path]
-    python .agent/scripts/session_manager.py info [path]
+    python .github/scripts/session_manager.py status [path]
+    python .github/scripts/session_manager.py info [path]
 """
 
 import os

package/templates/scripts/verify_all.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Full Verification Suite - Antigravity Kit
+Full Verification Suite - Copilot Kit
 ==========================================
 
 Runs COMPLETE validation including all checks + performance + E2E.

package/templates/skills/README.md

@@ -1,6 +1,6 @@
 # Skills Directory
 
-> Modular knowledge domains for the Antigravity Agent Toolkit
+> Modular knowledge domains for the Copilot Agent Toolkit
 
 ## Structure
 

package/templates/skills/doc.md

@@ -1,14 +1,14 @@
-# Antigravity Skills
+# Copilot Skills
 
-> **Hướng dẫn tạo và sử dụng Skills trong Antigravity Kit**
+> **Hướng dẫn tạo và sử dụng Skills trong Copilot Kit**
 
 ---
 
 ## 📋 Giới thiệu
 
-Mặc dù các mô hình cơ bản của Antigravity (như Gemini) là những mô hình đa năng mạnh mẽ, nhưng chúng không biết ngữ cảnh dự án cụ thể hoặc các tiêu chuẩn của nhóm bạn. Việc tải từng quy tắc hoặc công cụ vào cửa sổ ngữ cảnh của tác nhân sẽ dẫn đến tình trạng "phình to công cụ", chi phí cao hơn, độ trễ và sự nhầm lẫn.
+Mặc dù các mô hình cơ bản của Copilot là những mô hình đa năng mạnh mẽ, nhưng chúng không biết ngữ cảnh dự án cụ thể hoặc các tiêu chuẩn của nhóm bạn. Việc tải từng quy tắc hoặc công cụ vào cửa sổ ngữ cảnh của tác nhân sẽ dẫn đến tình trạng "phình to công cụ", chi phí cao hơn, độ trễ và sự nhầm lẫn.
 
-**Antigravity Skills** giải quyết vấn đề này thông qua tính năng **Progressive Disclosure**. Kỹ năng là một gói kiến thức chuyên biệt, ở trạng thái không hoạt động cho đến khi cần. Thông tin này chỉ được tải vào ngữ cảnh của tác nhân khi yêu cầu cụ thể của bạn khớp với nội dung mô tả của kỹ năng.
+**Copilot Skills** giải quyết vấn đề này thông qua tính năng **Progressive Disclosure**. Kỹ năng là một gói kiến thức chuyên biệt, ở trạng thái không hoạt động cho đến khi cần. Thông tin này chỉ được tải vào ngữ cảnh của tác nhân khi yêu cầu cụ thể của bạn khớp với nội dung mô tả của kỹ năng.
 
 ---
 
@@ -18,7 +18,7 @@ Kỹ năng là các gói dựa trên thư mục. Bạn có thể xác định c
 
 | Phạm vi | Đường dẫn | Mô tả |
 |---------|-----------|-------|
-| **Workspace** | `<workspace-root>/.agent/skills/` | Chỉ có trong một dự án cụ thể |
+| **Workspace** | `<workspace-root>/.github/skills/` | Chỉ có trong một dự án cụ thể |
 
 ### Cấu trúc thư mục kỹ năng
 
@@ -39,7 +39,7 @@ my-skill/
 ### Bước 1: Tạo thư mục
 
 ```bash
-mkdir -p ~/.gemini/antigravity/skills/code-review
+mkdir -p ~/.copilot/skills/code-review
 ```
 
 ### Bước 2: Tạo SKILL.md

package/templates/skills/parallel-agents/SKILL.md

@@ -9,11 +9,11 @@ skills: Auto-filled skills
 
 # Native Parallel Agents
 
-> Orchestration through Antigravity's built-in Agent Tool
+> Orchestration through Copilot's built-in Agent capabilities
 
 ## Overview
 
-This skill enables coordinating multiple specialized agents through Antigravity's native agent system. Unlike external scripts, this approach keeps all orchestration within Antigravity's control.
+This skill enables coordinating multiple specialized agents through Copilot's native agent system. Unlike external scripts, this approach keeps all orchestration within Copilot's control.
 
 ## When to Use Orchestration
 
@@ -116,7 +116,7 @@ Agents: security-auditor → penetration-tester → synthesis
 
 ---
 
-## Antigravity Built-in Agents
+## Copilot Built-in Agents
 
 These work alongside custom agents:
 

package/templates/workflows/orchestrate.md

@@ -192,7 +192,7 @@ Combine all agent outputs into unified report.
 [Original task summary]
 
 ### Mode
-[Current Antigravity Agent mode: plan/edit/ask]
+[Current Copilot Agent mode: plan/edit/ask]
 
 ### Agents Invoked (MINIMUM 3)
 | # | Agent | Focus Area | Status |

package/templates/workflows/plan.md

@@ -11,7 +11,7 @@ $ARGUMENTS
 ## 🔴 CRITICAL RULES
 
 1. **NO CODE WRITING** - This command creates plan file only
-2. **Use project-planner agent** - NOT Antigravity Agent's native Plan mode
+2. **Use project-planner agent** - NOT native Plan mode
 3. **Socratic Gate** - Ask clarifying questions before planning
 4. **Dynamic Naming** - Plan file named based on task