jeremy-vertex-engine
Vertex AI Agent Engine deployment inspector and runtime validator
Installation
Open Claude Code and run this command:
/plugin install jeremy-vertex-engine@claude-code-plugins-plus
Use --global to install for all projects, or --project for current project only.
What It Does
This plugin provides comprehensive inspection and validation capabilities for agents deployed to the Vertex AI Agent Engine managed runtime. It acts as a quality assurance layer ensuring agents are properly configured, secure, performant, and production-ready on Google's fully-managed agent infrastructure.
Features
✅ Runtime Configuration Inspection: Validate model, tools, VPC settings
✅ Code Execution Sandbox Validation: Check security, state persistence, IAM
✅ Memory Bank Configuration: Verify retention, indexing, query performance
✅ A2A Protocol Compliance: Ensure AgentCard and API endpoints functional
✅ Security Audits: IAM, VPC-SC, encryption, Model Armor checks
✅ Performance Monitoring: Latency, error rates, token usage, costs
✅ Production Readiness Scoring: Comprehensive 28-point checklist
✅ Health Monitoring: Real-time metrics and alerting
Skills (1)
Inspect and validate Vertex AI Agent Engine deployments including Code Execution Sandbox, Memory Bank, A2A protocol compliance, and security posture.
How It Works
Natural Language Activation
Simply mention what you need:
"Inspect my Vertex AI Engine agent deployment"
"Validate the Code Execution Sandbox configuration"
"Check Memory Bank settings for my agent"
"Monitor agent health over the last 24 hours"
"Production readiness check for agent-id-123"
The skill auto-activates and performs comprehensive inspection.
What Gets Inspected
- Runtime Configuration
- Model selection and settings
- Enabled tools (Code Execution, Memory Bank)
- VPC and networking configuration
- Resource allocation and scaling
- Code Execution Sandbox
- Security isolation validation
- State persistence TTL (1-14 days)
- IAM least privilege verification
- Performance settings
- Memory Bank
- Persistent memory configuration
- Retention policies
- Query performance (indexing, caching)
- Storage backend validation
- A2A Protocol
- AgentCard availability and structure
- Task API functionality
- Status API accessibility
- Protocol version compliance
- Security Posture
- IAM roles and permissions
- VPC Service Controls
- Model Armor (prompt injection protection)
- Encryption at rest and in transit
- Performance Metrics
- Error rates and latency
- Token usage and costs
- Throughput and scaling
- SLO compliance
- Production Readiness
- 28-point comprehensive checklist
- Weighted scoring across 5 categories
- Overall readiness status
- Actionable recommendations
Use Cases
Pre-Production Validation
Before deploying to production:
"Run production readiness check on staging agent"
Post-Deployment Verification
After deployment:
"Validate agent-xyz deployment was successful"
Ongoing Health Monitoring
Regular health checks:
"Monitor agent health for the last 7 days"
Security Audits
Compliance validation:
"Perform security audit on production agents"
Troubleshooting
When issues occur:
"Why is my agent responding slowly?"
"Investigate high error rate on agent-abc"