antigravity-devkit 1.0.2 → 1.0.4

package/template/rules/GEMINI.md

@@ -1,180 +0,0 @@
----
-trigger: always_on
----
-
-# GEMINI.md - Vue3 + ASP.NET + Azure Kit
-
-> Global rules for AI behavior in this workspace.
-
----
-
-## CRITICAL: AGENT & SKILL PROTOCOL
-
-> **MANDATORY:** Read agent file and skills BEFORE implementation.
-
-### Skill Loading Protocol
-```
-Agent activated → Check frontmatter "skills:" → Read SKILL.md → Apply rules
-```
-
-**Rule Priority:** P0 (GEMINI.md) > P1 (Agent .md) > P2 (SKILL.md)
-
----
-
-## REQUEST CLASSIFIER
-
-| Request Type | Trigger Keywords | Agent | Result |
-|--------------|------------------|-------|--------|
-| QUESTION | "what is", "explain" | - | Text Response |
-| SURVEY | "analyze", "overview" | explorer-agent | Analysis |
-| VUE3 CODE | "component", "vue", "pinia" | frontend-specialist | Code |
-| ASPNET CODE | "controller", "api", "c#" | backend-specialist | Code |
-| DATABASE | "sql", "schema", "query" | database-architect | Code |
-| DEVOPS | "deploy", "pipeline", "aks" | devops-engineer | Config |
-| SECURITY | "audit", "keyvault", "owasp" | security-auditor | Report |
-| TEST | "test", "xunit", "vitest" | test-engineer | Tests |
-| DEBUG | "fix", "error", "bug" | debugger | Fix |
-| SLASH CMD | /create, /plan, /deploy | Command-specific | Variable |
-
----
-
-## INTELLIGENT AGENT ROUTING
-
-**ALWAYS ACTIVE:** Auto-select best agent before responding.
-
-### Protocol
-1. **Analyze**: Detect domain (Frontend, Backend, Database, DevOps)
-2. **Select**: Choose specialist agent
-3. **Inform**: State which agent is applied
-4. **Apply**: Use agent's rules and skills
-
-### Response Format
-```markdown
-🤖 **Applying `@[agent-name]`...**
-[Specialized response]
-```
-
----
-
-## TIER 0: UNIVERSAL RULES
-
-### Language Handling
-- Respond in user's language
-- Code comments/variables in English
-
-### Clean Code (Global)
-**ALL code MUST follow `@[skills/clean-code]`. No exceptions.**
-
-| Principle | Rule |
-|-----------|------|
-| SRP | Single responsibility |
-| DRY | No duplication |
-| KISS | Simplest solution |
-| YAGNI | No unused features |
-
-### File Dependency Awareness
-Before modifying ANY file:
-1. Identify dependent files
-2. Update ALL affected files together
-
-### Read → Understand → Apply
-```
-❌ WRONG: Read agent → Start coding
-✅ CORRECT: Read → Understand WHY → Apply PRINCIPLES → Code
-```
-
----
-
-## TIER 1: CODE RULES
-
-### Project Type Routing
-
-| Project Type | Agent | Skills |
-|--------------|-------|--------|
-| VUE3 | frontend-specialist | vue3-patterns, vitest-testing |
-| ASPNET | backend-specialist | aspnet-patterns, csharp-patterns |
-| DATABASE | database-architect | sqlserver-design |
-| DEVOPS | devops-engineer | azure-devops, azure-aks |
-
-### Socratic Gate
-
-**For complex requests, ASK first:**
-
-| Request Type | Action |
-|--------------|--------|
-| New Feature | Ask 3+ strategic questions |
-| Bug Fix | Confirm understanding |
-| Vague Request | Clarify Purpose, Users, Scope |
-
-**Protocol:**
-1. Never Assume - if unclear, ASK
-2. Wait for confirmation before coding
-
-### Human-in-the-Loop Checkpoints
-
-| Stage | Action |
-|-------|--------|
-| /plan | Approve before coding |
-| /review | Approve before deploy |
-| /deploy | Approve before trigger |
-
----
-
-## TIER 2: STACK-SPECIFIC RULES
-
-### Vue3 Frontend
-- Composition API only (no Options API)
-- Pinia for state management
-- TypeScript strict mode
-- Vitest for testing
-
-### ASP.NET Backend
-- Controller → Service → Repository pattern
-- Async/await everywhere
-- Dependency injection
-- xUnit for testing
-
-### SQL Server Database
-- Proper indexing
-- Stored procedures for complex logic
-- Migration scripts
-
-### Azure DevOps
-- YAML pipelines
-- GitOps patterns
-- KeyVault for secrets
-
----
-
-## VERIFICATION SCRIPTS
-
-### Agent → Script Mapping
-
-| Agent | Script |
-|-------|--------|
-| frontend-specialist | vitest_runner.py |
-| backend-specialist | xunit_runner.py |
-| database-architect | schema_validator.py |
-| security-auditor | security_scan.py |
-| Any agent | lint_runner.py |
-
-### Script Output Protocol
-1. Run script
-2. Parse errors/warnings
-3. Summarize to user
-4. Ask before fixing
-
----
-
-## QUICK REFERENCE
-
-### Agents
-- **Masters**: orchestrator, project-planner
-- **Code**: frontend-specialist, backend-specialist, database-architect
-- **Ops**: devops-engineer, security-auditor, test-engineer
-- **Support**: debugger, performance-optimizer, documentation-writer
-
-### Key Skills
-- **Core**: clean-code, architecture, brainstorming, plan-writing
-- **Stack**: vue3-patterns, aspnet-patterns, sqlserver-design
-- **Azure**: azure-devops, azure-aks, azure-keyvault

package/template/scripts/README.md

@@ -1,317 +0,0 @@
-# Verification Scripts
-
-Automated validation scripts used by agents to ensure code quality, security, and correctness.
-
----
-
-## Agent → Script Mapping
-
-| Agent | Script | Purpose |
-|-------|--------|---------|
-| `frontend-specialist` | `vitest_runner.py` | Run Vue3/TypeScript tests with Vitest |
-| `backend-specialist` | `xunit_runner.py` | Run ASP.NET/C# tests with xUnit |
-| `database-architect` | `schema_validator.py` | Validate SQL schemas and migrations |
-| `security-auditor` | `security_scan.py` | Scan for security vulnerabilities |
-| **Any agent** | `lint_runner.py` | Universal code quality checker |
-| **Any agent** | `checklist.py` | Quick validation checklist |
-| **Any agent** | `verify_all.py` | Comprehensive validation suite |
-
----
-
-## Script Output Protocol
-
-When agents use these scripts, they follow this protocol:
-
-1. **Run script** - Execute the appropriate validation script
-2. **Parse errors/warnings** - Extract and categorize issues
-3. **Summarize to user** - Present findings in readable format
-4. **Ask before fixing** - Request approval before making changes
-
----
-
-## Individual Script Usage
-
-### 🧪 `vitest_runner.py` - Frontend Test Runner
-
-**Purpose**: Execute and validate Vue3/TypeScript tests using Vitest
-
-**Usage**:
-```bash
-# Run tests
-python scripts/vitest_runner.py .
-
-# Run with coverage
-python scripts/vitest_runner.py . --coverage
-
-# Watch mode
-python scripts/vitest_runner.py . --watch
-```
-
-**Requirements**: Node.js, Vitest installed in project
-
-**Output**: Test results, pass/fail counts, coverage metrics
-
----
-
-### 🧪 `xunit_runner.py` - Backend Test Runner
-
-**Purpose**: Execute and validate ASP.NET/C# tests using xUnit
-
-**Usage**:
-```bash
-# Run all tests
-python scripts/xunit_runner.py .
-
-# Run with coverage
-python scripts/xunit_runner.py . --coverage
-
-# Filter specific tests
-python scripts/xunit_runner.py . --filter "UserServiceTests"
-```
-
-**Requirements**: .NET SDK, xUnit test projects
-
-**Output**: Test results, pass/fail counts, duration
-
----
-
-### 🗄️ `schema_validator.py` - Database Schema Validator
-
-**Purpose**: Validate SQL Server schemas, migrations, and stored procedures
-
-**Usage**:
-```bash
-# Validate schemas
-python scripts/schema_validator.py .
-
-# With connection string (for live validation)
-python scripts/schema_validator.py . --connection-string "Server=..."
-```
-
-**Checks**:
-- SQL syntax errors
-- Missing primary keys
-- Naming conventions
-- Migration file naming
-- SQL injection risks
-- Transaction handling
-
-**Output**: Schema quality report, syntax issues, recommendations
-
----
-
-### 🔒 `security_scan.py` - Security Scanner
-
-**Purpose**: Comprehensive security vulnerability detection
-
-**Usage**:
-```bash
-# Full security scan
-python scripts/security_scan.py .
-
-# Filter by severity
-python scripts/security_scan.py . --severity high
-```
-
-**Scans For**:
-- Hardcoded secrets (passwords, API keys, tokens)
-- npm package vulnerabilities
-- NuGet package vulnerabilities
-- SQL injection patterns
-- XSS vulnerabilities
-- Weak cryptography (MD5, SHA1)
-- eval() usage
-- HTTP vs HTTPS
-- Missing security headers (HSTS, HTTPS redirect)
-
-**Output**: Security findings grouped by severity (HIGH/MEDIUM/LOW)
-
----
-
-### 🔍 `lint_runner.py` - Universal Linter
-
-**Purpose**: Code quality and style validation for both frontend and backend
-
-**Usage**:
-```bash
-# Lint entire project
-python scripts/lint_runner.py .
-
-# Auto-fix issues
-python scripts/lint_runner.py . --fix
-
-# Frontend only
-python scripts/lint_runner.py . --frontend-only
-
-# Backend only
-python scripts/lint_runner.py . --backend-only
-```
-
-**Frontend Checks**:
-- ESLint (JavaScript/TypeScript)
-- Prettier (code formatting)
-- TypeScript type checking
-
-**Backend Checks**:
-- dotnet format (C# formatting)
-- dotnet build with warnings as errors
-
-**Output**: Code quality report with pass/fail status
-
----
-
-### ✅ `checklist.py` - Quick Validation
-
-**Purpose**: Fast validation checklist for development and pre-commit
-
-**Usage**:
-```bash
-# Run checklist
-python scripts/checklist.py .
-
-# With URL for integration tests
-python scripts/checklist.py . --url http://localhost:3000
-```
-
-**Checks**:
-- Security (secrets, vulnerabilities)
-- Frontend lint
-- Frontend types
-- Frontend tests
-- Backend build
-- Backend tests
-
-**Output**: Pass/fail summary for each check
-
----
-
-### 🎯 `verify_all.py` - Comprehensive Validation
-
-**Purpose**: Complete validation suite before deployment
-
-**Usage**:
-```bash
-# Full verification
-python scripts/verify_all.py .
-
-# With application URL
-python scripts/verify_all.py . --url http://localhost:3000
-```
-
-**Runs All Checks**:
-- All checklist items
-- Additional deployment validations
-- Integration tests (if URL provided)
-
-**Output**: Comprehensive validation report
-
----
-
-## When to Use Each Script
-
-| Scenario | Script | Why |
-|----------|--------|-----|
-| Writing Vue components | `vitest_runner.py` | Validate component tests |
-| Writing API endpoints | `xunit_runner.py` | Validate backend tests |
-| Creating migrations | `schema_validator.py` | Ensure schema quality |
-| Before commit | `checklist.py` | Quick validation |
-| Before PR | `lint_runner.py` | Code quality check |
-| Security review | `security_scan.py` | Find vulnerabilities |
-| Before deployment | `verify_all.py` | Complete validation |
-
----
-
-## Exit Codes
-
-All scripts follow standard exit code conventions:
-
-- **0** - Success (all checks passed)
-- **1** - Failure (issues found)
-
-This allows scripts to be used in CI/CD pipelines:
-
-```bash
-python scripts/checklist.py . && echo "Ready to commit" || echo "Fix issues first"
-```
-
----
-
-## Integration with Agents
-
-Agents automatically use these scripts when appropriate:
-
-```
-User: "Test my Vue components"
-  ↓
-@test-engineer activates
-  ↓
-Runs: python scripts/vitest_runner.py .
-  ↓
-Parses output and reports to user
-  ↓
-Asks: "Found 2 failing tests. Should I help fix them?"
-```
-
----
-
-## Requirements
-
-### Python
-- Python 3.7+
-- No external dependencies (uses stdlib only)
-
-### Project Dependencies
-- **Frontend**: Node.js, npm, Vitest (for vitest_runner.py)
-- **Backend**: .NET SDK (for xunit_runner.py)
-- **Database**: SQL files in project (for schema_validator.py)
-
----
-
-## Adding Custom Validations
-
-To add project-specific validations:
-
-1. Create a new script following the same pattern
-2. Add to the agent's skill or workflow
-3. Update this README with usage instructions
-
-**Example**:
-```python
-#!/usr/bin/env python3
-"""
-Custom Validator - Your specific validation
-"""
-
-def main():
-    # Your validation logic
-    pass
-
-if __name__ == "__main__":
-    main()
-```
-
----
-
-## Troubleshooting
-
-### "Command not found"
-- Ensure required tools are installed (npm, dotnet, etc.)
-- Check PATH environment variable
-
-### "Permission denied"
-- Make scripts executable: `chmod +x scripts/*.py`
-
-### "Timeout"
-- Scripts timeout after 5 minutes
-- For large projects, consider running specific checks
-
----
-
-## Contributing
-
-When modifying scripts:
-
-1. Keep exit codes consistent (0 = success, 1 = failure)
-2. Follow the output protocol (run → parse → summarize → ask)
-3. Add timeout handling for long-running commands
-4. Update this README with changes

package/template/scripts/checklist.py

@@ -1,170 +0,0 @@
-#!/usr/bin/env python3
-"""
-Checklist - Priority-based project validation
-Run during development and pre-commit.
-
-Usage:
-    python .agent-antigravity/scripts/checklist.py .
-    python .agent-antigravity/scripts/checklist.py . --url http://localhost:3000
-"""
-
-import subprocess
-import sys
-import os
-from pathlib import Path
-
-
-def run_command(cmd: list[str], cwd: str = ".") -> tuple[int, str]:
-    """Run a command and return exit code and output."""
-    try:
-        result = subprocess.run(
-            cmd,
-            cwd=cwd,
-            capture_output=True,
-            text=True,
-            timeout=300
-        )
-        return result.returncode, result.stdout + result.stderr
-    except subprocess.TimeoutExpired:
-        return 1, "Command timed out"
-    except FileNotFoundError:
-        return 1, f"Command not found: {cmd[0]}"
-
-
-def check_frontend_lint(project_path: str) -> tuple[bool, str]:
-    """Check frontend linting."""
-    package_json = Path(project_path) / "package.json"
-    if not package_json.exists():
-        return True, "No package.json found, skipping frontend lint"
-    
-    code, output = run_command(["npm", "run", "lint"], project_path)
-    return code == 0, output
-
-
-def check_frontend_types(project_path: str) -> tuple[bool, str]:
-    """Check TypeScript types."""
-    package_json = Path(project_path) / "package.json"
-    if not package_json.exists():
-        return True, "No package.json found, skipping type check"
-    
-    code, output = run_command(["npm", "run", "type-check"], project_path)
-    if code != 0:
-        # Try alternative command
-        code, output = run_command(["npx", "tsc", "--noEmit"], project_path)
-    return code == 0, output
-
-
-def check_backend_build(project_path: str) -> tuple[bool, str]:
-    """Check .NET build."""
-    sln_files = list(Path(project_path).glob("*.sln"))
-    csproj_files = list(Path(project_path).glob("**/*.csproj"))
-    
-    if not sln_files and not csproj_files:
-        return True, "No .NET project found, skipping build"
-    
-    code, output = run_command(["dotnet", "build"], project_path)
-    return code == 0, output
-
-
-def check_backend_tests(project_path: str) -> tuple[bool, str]:
-    """Check .NET tests."""
-    sln_files = list(Path(project_path).glob("*.sln"))
-    if not sln_files:
-        return True, "No .NET solution found, skipping tests"
-    
-    code, output = run_command(["dotnet", "test"], project_path)
-    return code == 0, output
-
-
-def check_frontend_tests(project_path: str) -> tuple[bool, str]:
-    """Check frontend tests."""
-    package_json = Path(project_path) / "package.json"
-    if not package_json.exists():
-        return True, "No package.json found, skipping tests"
-    
-    code, output = run_command(["npm", "run", "test", "--", "--run"], project_path)
-    return code == 0, output
-
-
-def check_security(project_path: str) -> tuple[bool, str]:
-    """Check for security issues."""
-    issues = []
-    
-    # Check for hardcoded secrets patterns
-    secret_patterns = ["password=", "apikey=", "secret=", "connectionstring="]
-    for pattern in secret_patterns:
-        code, output = run_command(
-            ["grep", "-ri", pattern, "--include=*.cs", "--include=*.ts", "--include=*.json"],
-            project_path
-        )
-        if code == 0 and output.strip():
-            issues.append(f"Potential secret found: {pattern}")
-    
-    # Check npm audit
-    package_json = Path(project_path) / "package.json"
-    if package_json.exists():
-        code, output = run_command(["npm", "audit", "--audit-level=high"], project_path)
-        if code != 0:
-            issues.append("npm audit found high severity vulnerabilities")
-    
-    if issues:
-        return False, "\n".join(issues)
-    return True, "No security issues found"
-
-
-def main():
-    if len(sys.argv) < 2:
-        print("Usage: python checklist.py <project_path> [--url <url>]")
-        sys.exit(1)
-    
-    project_path = sys.argv[1]
-    url = None
-    if "--url" in sys.argv:
-        url_index = sys.argv.index("--url") + 1
-        if url_index < len(sys.argv):
-            url = sys.argv[url_index]
-    
-    print("=" * 60)
-    print("PROJECT CHECKLIST")
-    print("=" * 60)
-    
-    checks = [
-        ("Security", check_security),
-        ("Frontend Lint", check_frontend_lint),
-        ("Frontend Types", check_frontend_types),
-        ("Frontend Tests", check_frontend_tests),
-        ("Backend Build", check_backend_build),
-        ("Backend Tests", check_backend_tests),
-    ]
-    
-    results = []
-    for name, check_fn in checks:
-        print(f"\n[{name}]")
-        passed, output = check_fn(project_path)
-        status = "✅ PASS" if passed else "❌ FAIL"
-        print(f"  {status}")
-        if not passed:
-            print(f"  {output[:500]}")
-        results.append((name, passed))
-    
-    print("\n" + "=" * 60)
-    print("SUMMARY")
-    print("=" * 60)
-    
-    passed_count = sum(1 for _, p in results if p)
-    total_count = len(results)
-    
-    for name, passed in results:
-        status = "✅" if passed else "❌"
-        print(f"  {status} {name}")
-    
-    print(f"\nResult: {passed_count}/{total_count} checks passed")
-    
-    if passed_count < total_count:
-        sys.exit(1)
-    
-    print("\n✅ All checks passed!")
-
-
-if __name__ == "__main__":
-    main()