Jeremy Vertex Validator

🎯 VERTEX AI AGENT ENGINE DEPLOYMENT VALIDATION

Production readiness validator for Vertex AI Agent Engine deployments. Validates ADK agents before production deployment with comprehensive security, compliance, monitoring, and performance checks.

⚠️ Important: What This Plugin Is For

✅ THIS PLUGIN IS FOR:

• Vertex AI Agent Engine deployment validation (fully-managed runtime)
• ADK agents deployed to Agent Engine
• Pre-deployment validation of agent code and configuration
• Production readiness checks for Agent Engine features
• Security, compliance, monitoring, and performance validation

❌ THIS PLUGIN IS NOT FOR:

• Cloud Run deployment validation (use Cloud Run-specific tools)
• LangChain/LlamaIndex on other platforms
• Self-hosted agent infrastructure validation
• Non-Agent Engine deployments

Overview

This plugin performs comprehensive production readiness validation for ADK agents before deploying to Vertex AI Agent Engine. It checks security posture, compliance requirements, monitoring configuration, performance optimization, and best practices enforcement.

Validation Categories:

• Security: IAM, VPC-SC, encryption, Model Armor
• Monitoring: Dashboards, alerts, SLOs, token tracking
• Performance: Auto-scaling, caching, resource limits
• Compliance: Audit logging, data residency, backups
• Best Practices: Agent Engine configuration, Memory Bank, Code Execution Sandbox

Installation

/plugin install jeremy-vertex-validator@claude-code-plugins-plus

Prerequisites & Dependencies

Required Google Cloud Setup

1. Google Cloud Project with APIs Enabled:

# Enable required APIs
gcloud services enable aiplatform.googleapis.com \
    discoveryengine.googleapis.com \
    logging.googleapis.com \
    monitoring.googleapis.com \
    cloudtrace.googleapis.com \
    securitycenter.googleapis.com \
    --project=YOUR_PROJECT_ID

2. Authentication:

# Application Default Credentials
gcloud auth application-default login

# Or use service account
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account-key.json"

3. Required IAM Permissions:

# Minimum required roles for validation:
- roles/aiplatform.user              # Query Agent Engine resources
- roles/discoveryengine.viewer       # View agent configurations
- roles/logging.viewer               # Read audit logs
- roles/monitoring.viewer            # Access metrics and alerts
- roles/iam.securityReviewer         # Review IAM policies
- roles/cloudtrace.user              # View trace data

Required Python Packages

Install via pip:

# Core Vertex AI SDK (with Agent Engine support)
pip install google-cloud-aiplatform[agent_engines]>=1.120.0

# ADK SDK (for agent validation)
pip install google-adk>=1.15.1

# Observability & Monitoring
pip install google-cloud-logging>=3.10.0
pip install google-cloud-monitoring>=2.21.0
pip install google-cloud-trace>=1.13.0

# Security & Compliance
pip install google-cloud-security-center>=1.28.0
pip install google-cloud-asset>=3.20.0

# Code Analysis
pip install pylint>=3.0.0
pip install flake8>=7.0.0
…

All dependencies at once:

pip install --upgrade \
    'google-cloud-aiplatform[agent_engines]>=1.120.0' \
    'google-adk>=1.15.1' \
    'google-cloud-logging>=3.10.0' \
    'google-cloud-monitoring>=2.21.0' \
    'google-cloud-trace>=1.13.0' \
    'google-cloud-security-center>=1.28.0' \
    'google-cloud-asset>=3.20.0' \
    'pylint>=3.0.0' \
    'flake8>=7.0.0' \
    'mypy>=1.8.0'

Required gcloud CLI Tools

Install gcloud CLI:

# Install gcloud (if not already installed)
curl https://sdk.cloud.google.com | bash
exec -l $SHELL

# Update to latest version
gcloud components update

# Install beta commands (for Security Command Center)
gcloud components install beta

Verify Installation:

gcloud --version
# Should show: Google Cloud SDK 450.0.0+ (or higher)

# Test Agent Engine access (SDK-only — no gcloud CLI for Agent Engine)
python3 -c "
import vertexai
client = vertexai.Client(project='YOUR_PROJECT_ID', location='us-central1')
for engine in client.agent_engines.list():
    print(engine.name)
"

# Test Model Armor access
gcloud model-armor --help

# Test Security Command Center access
gcloud scc findings list organizations/YOUR_ORG_ID --limit=1

What Gets Validated

This plugin validates agents deployed to Agent Engine via:

1. ADK CLI Deployment:

adk deploy agent_engine \
    --project=YOUR_PROJECT_ID \
    --region=us-central1 \
    agent_module

1. Python SDK Deployment:

from google.adk.agents import Agent
import vertexai

agent = Agent(
    name="my-adk-agent",
    tools=[...],
    model="gemini-2.0-flash-001"
)

client = vertexai.Client(project="YOUR_PROJECT_ID", location="us-central1")
remote_agent = client.agent_engines.create(
    agent=agent,
    config={
        "requirements": ["google-cloud-aiplatform[agent_engines,adk]"],
        "staging_bucket": "gs://YOUR_BUCKET",
    },
)

1. Terraform Deployment:

resource "google_vertex_ai_reasoning_engine" "agent" {
  display_name = "my-adk-agent"
  region       = "us-central1"

  spec {
    agent_framework = "google-adk"
    # ... agent configuration
  }
}