terraform-infra
Terraform infrastructure operations with safety controls
How do I install this agent skill?
npx skills add https://github.com/oimiragieo/agent-studio --skill terraform-infraIs this agent skill safe to install?
- Gen Agent Trust Hubwarn
The skill provides infrastructure management via Terraform but fails to enforce the safety restrictions it claims in its documentation. Specifically, it lists destructive operations as blocked, yet the execution script allows any Terraform command to be run without validation or filtering.
- Socketpass
No alerts
- Snykfail
Risk: CRITICAL · 1 issue
- Runlayerwarn
2/10 files flagged
What does this agent skill do?
Terraform Infrastructure Skill
Installation
The skill invokes the Terraform CLI. Install:
- macOS:
brew tap hashicorp/tap && brew install hashicorp/tap/terraform - Windows:
choco install terraformor download from HashiCorp - Linux (apt): Add HashiCorp repo then
sudo apt update && sudo apt install terraform(see HashiCorp install)
Verify: terraform --version
Cheat Sheet & Best Practices
Workflow: terraform init → terraform fmt → terraform validate → terraform plan -out=tfplan → review → terraform apply tfplan. Use terraform show tfplan to inspect.
Hacks: Always run plan before apply; never apply blind. Use remote state (e.g. S3 + lock) for team work. Prefer -auto-approve only in CI with reviewed plans. Use terraform state list and terraform state show <resource> to debug. Use service accounts / workload identity in pipelines; avoid static keys.
Certifications & Training
HashiCorp Terraform Associate (004): IaC concepts, Terraform fundamentals, state, modules, Terraform Cloud. Learning path. Skill data: init → fmt → validate → plan -out → apply; remote state; no blind apply.
Hooks & Workflows
Suggested hooks: Pre-apply: run terraform plan -out=tfplan and gate on review. CI: apply only after plan approval. Use with devops (primary).
Workflows: Use with devops (primary). Flow: init → plan → review → apply; use state commands for debugging. See ci-cd-implementation-rule for pipeline integration.
Overview
Provides 90%+ context savings vs raw Terraform MCP server. Includes critical safety controls for infrastructure operations.
Requirements
- Terraform CLI (v1.0+)
- Cloud provider credentials configured
- Working directory with .tf files
Tools (Progressive Disclosure)
Planning & Validation
| Tool | Description | Confirmation |
|---|---|---|
| plan | Generate terraform plan | No |
| validate | Validate configuration | No |
| fmt | Format terraform files | No |
State Operations
| Tool | Description | Confirmation |
|---|---|---|
| show | Display current state | No |
| list | List state resources | No |
| state-mv | Move resource in state | Yes |
Workspace Operations
| Tool | Description | Confirmation |
|---|---|---|
| workspace-list | List workspaces | No |
| workspace-select | Select workspace | No |
| workspace-new | Create workspace | Yes |
Execution (⚠️ Dangerous)
| Tool | Description | Confirmation |
|---|---|---|
| apply | Apply changes | REQUIRED |
Blocked Operations
| Tool | Status |
|---|---|
| destroy | BLOCKED |
| state-rm | BLOCKED |
Quick Reference
# Initialize
terraform init
# Plan changes
terraform plan -out=tfplan
# Validate
terraform validate
# Apply (requires -auto-approve for automation)
terraform apply tfplan
Configuration
- Working directory: Must contain terraform files
- TFVAR*: Variable values via environment
- TF_WORKSPACE: Active workspace
Safety Controls
⚠️ terraform apply ALWAYS requires confirmation ⚠️ terraform destroy is BLOCKED by default ⚠️ State modifications require confirmation ⚠️ Review plan output before apply
Agent Integration
- devops (primary): Infrastructure management
- architect (secondary): Infrastructure design
- cloud-integrator (secondary): Cloud provisioning
Troubleshooting
| Issue | Solution |
|---|---|
| Init failed | Check provider credentials |
| State locked | Check for other operations |
| Plan failed | Review error output carefully |
Module Development
Creating Reusable Modules
Structure modules following HashiCorp conventions:
modules/
vpc/
main.tf # Resource definitions
variables.tf # Input variables
outputs.tf # Output values
versions.tf # Required provider versions
README.md # Module documentation
Module Best Practices
| Practice | Description |
|---|---|
| Single responsibility | Each module manages one logical resource group |
| Typed variables | Use type constraints on all variables |
| Validation blocks | Add validation {} for input constraints |
| Sensitive outputs | Mark secrets with sensitive = true |
| Version constraints | Pin module source versions |
Module Source Patterns
# Local module
module "vpc" {
source = "./modules/vpc"
}
# Terraform Registry
module "vpc" {
source = "terraform-aws-modules/vpc/aws"
version = "~> 5.0"
}
# Git source (pinned tag)
module "vpc" {
source = "git::https://github.com/org/modules.git//vpc?ref=v1.2.0"
}
Provider Development Patterns
Custom Provider Skeleton
package provider
import (
"github.com/hashicorp/terraform-plugin-sdk/v2/helper/schema"
)
func Provider() *schema.Provider {
return &schema.Provider{
Schema: map[string]*schema.Schema{
"api_key": {
Type: schema.TypeString,
Required: true,
Sensitive: true,
DefaultFunc: schema.EnvDefaultFunc("API_KEY", nil),
},
},
ResourcesMap: map[string]*schema.Resource{
"myservice_resource": resourceMyServiceResource(),
},
}
}
Testing Modules
# Validate module syntax
cd modules/vpc && terraform validate
# Run module tests (Terraform 1.6+)
terraform test
# Plan with module
terraform plan -var-file=examples/basic.tfvars
Iron Laws
- ALWAYS run
terraform planand review the output before executingterraform apply - NEVER hardcode credentials or secrets in
.tffiles — use secret managers (AWS Secrets Manager, Azure Key Vault, HashiCorp Vault) - ALWAYS use remote state with encryption and state locking to prevent concurrent modifications
- NEVER edit state files directly — use
terraform statecommands exclusively - ALWAYS pin provider and module versions for fully reproducible infrastructure deployments
Anti-Patterns
| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Hardcoded credentials in .tf files | Secret exposure in VCS, compliance failure | Use variables with secret manager backend |
| No state locking | Concurrent applies corrupt state | Enable backend locking (S3+DynamoDB, Azure Blob, GCS) |
terraform apply without plan review | Unexpected resource deletion or recreation | Always plan first, review diff, then apply |
| Unversioned providers and modules | Non-reproducible builds and breaking changes | Pin versions: version = "~> 4.0" |
| Untagged resources | Untrackable costs and compliance failure | Tag all resources with env, owner, cost-center |
Memory Protocol (MANDATORY)
Before starting:
Read .claude/context/memory/learnings.md
After completing:
- New pattern ->
.claude/context/memory/learnings.md - Issue found ->
.claude/context/memory/issues.md - Decision made ->
.claude/context/memory/decisions.md
ASSUME INTERRUPTION: If it's not in memory, it didn't happen.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/oimiragieo/agent-studio/terraform-infra">View terraform-infra on skillZs</a>