jeremylongshore/tons-of-skills-marketplace / plugins/devops/jeremy-adk-terraform/skills/adk-infra-expert
adk-infra-expert
VerifiedExecute use when provisioning Vertex AI ADK infrastructure with Terraform. Trigger with phrases like "deploy ADK terraform", "agent engine infrastructure", "provision ADK agent", "vertex AI agent terraform", or "code execution sandbox terraform". Provisions Agent Engine runtime, 14-day code execution sandbox, Memory Bank, VPC Service Controls, IAM roles, and secure multi-agent infrastructure.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.8 KB |
| references/ARD.md | markdown | 4.5 KB |
| references/PRD.md | markdown | 3.8 KB |
| references/errors.md | markdown | 900 B |
| references/examples.md | markdown | 4.7 KB |
| references/implementation.md | markdown | 3.4 KB |
| scripts/init-terraform.shexecutable | script | 2.1 KB |
references/implementation.md
View on GitHub# ADK Terraform - Implementation Details
## Configuration
### Backend Setup
```hcl
terraform {
required_version = ">= 1.0"
backend "gcs" {
bucket = "my-project-tf-state"
prefix = "adk-infrastructure"
}
required_providers {
google = {
source = "hashicorp/google"
version = ">= 5.0"
}
google-beta = {
source = "hashicorp/google-beta"
version = ">= 5.0"
}
}
}
```
### Provider Configuration
```hcl
provider "google" {
project = var.project_id
region = var.region
}
provider "google-beta" {
project = var.project_id
region = var.region
}
```
## Module Structure
```
modules/
├── agent-engine/ # Agent Engine runtime provisioning
│ ├── main.tf
│ ├── variables.tf
│ └── outputs.tf
├── iam/ # Service accounts and role bindings
│ ├── main.tf
│ ├── variables.tf
│ └── outputs.tf
├── networking/ # VPC, PSC subnets, firewall rules
│ ├── main.tf
│ ├── variables.tf
│ └── outputs.tf
└── vpc-service-controls/ # VPC-SC perimeters and access levels
├── main.tf
├── variables.tf
└── outputs.tf
```
## Advanced Patterns
### Code Execution Sandbox Configuration
The ADK Code Execution sandbox defaults to a 14-day TTL. Override with:
```hcl
resource "google_vertex_ai_agent_engine" "agent" {
provider = google-beta
project = var.project_id
location = var.region
display_name = var.agent_config.display_name
agent_engine_config {
code_execution_config {
enabled = var.agent_config.code_execution
# Sandbox timeout: max 14 days (1209600 seconds)
execution_timeout = "1209600s"
}
memory_bank_config {
enabled = var.agent_config.memory_bank
}
}
}
```
### IAM Least Privilege Pattern
```hcl
resource "google_service_account" "agent_sa" {
account_id = "adk-agent-runner"
display_name = "ADK Agent Runner (least privilege)"
}
resource "google_project_iam_member" "agent_roles" {
for_each = toset([
"roles/aiplatform.user",
"roles/logging.logWriter",
"roles/monitoring.metricWriter",
])
project = var.project_id
role = each.value
member = "serviceAccount:${google_service_account.agent_sa.email}"
}
```
### Remote State Data Source
Reference ADK outputs from other Terraform configs:
```hcl
data "terraform_remote_state" "adk" {
backend = "gcs"
config = {
bucket = "my-project-tf-state"
prefix = "adk-infrastructure"
}
}
# Use agent endpoint in another module
locals {
agent_endpoint = data.terraform_remote_state.adk.outputs.agent_endpoint
}
```
## Troubleshooting
### API Enablement
Ensure the following APIs are enabled before running `terraform apply`:
```bash
gcloud services enable aiplatform.googleapis.com \
compute.googleapis.com \
iam.googleapis.com \
cloudresourcemanager.googleapis.com \
accesscontextmanager.googleapis.com \
--project=PROJECT_ID
```
### State Lock Issues
If Terraform state is locked from a previous failed run:
```bash
terraform force-unlock LOCK_ID
```
### Quota Limits
Agent Engine has per-project quotas. Check current usage:
```bash
gcloud alpha quotas info list \
--project=PROJECT_ID \
--service=aiplatform.googleapis.com \
--filter="metric:agent_engines"
```
---
*[Tons of Skills](https://tonsofskills.com) by [Intent Solutions](https://intentsolutions.io) | [jeremylongshore.com](https://jeremylongshore.com)*
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |