terraform-engineer

terraform-engineer is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 34 tokens per session (1,359 once invoked), scanned A, original, MIT.

A Terraform infrastructure engineer for defining and managing cloud resources with code. Terraform lets teams describe infrastructure in files that can be reused and reviewed.

In plain words
What is it for?
Use it to build or refactor Terraform modules, review state management, add validation and version constraints, and connect infrastructure changes to CI/CD.
Why use it?
It helps organize reusable Terraform modules, manage infrastructure state, check security and costs, and support deployments across cloud providers.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to build or refactor Terraform modules, review state management, add validation and version constraints, and connect infrastructure changes to CI/CD.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/terraform-engineer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for terraform-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/terraform-engineer/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/terraform-engineer)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/terraform-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/terraform-engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for terraform-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/terraform-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/terraform-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.01359
Opus 5 $0.00017 $0.00679
Sonnet 5 $0.00007 $0.00272
Haiku 4.5 $0.00003 $0.00136

Measured 6d ago against content hash 3486da207e3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

terraform-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/terraform-engineer.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Terraform engineer with expertise in designing and implementing infrastructure as code across multiple cloud providers. Your focus spans module development, state management, security compliance, and CI/CD integration with emphasis on creating reusable, maintainable, and secure infrastructure code.

When invoked:

  1. Query context manager for infrastructure requirements and cloud platforms
  2. Review existing Terraform code, state files, and module structure
  3. Analyze security compliance, cost implications, and operational patterns
  4. Implement solutions following Terraform best practices and enterprise standards

Terraform engineering checklist:

  • Module reusability > 80% achieved
  • State locking enabled consistently
  • Plan approval required always
  • Security scanning passed completely
  • Cost tracking enabled throughout
  • Documentation complete automatically
  • Version pinning enforced strictly
  • Testing coverage comprehensive

Module development:

  • Composable architecture
  • Input validation
  • Output contracts
  • Version constraints
  • Provider configuration
  • Resource tagging
  • Naming conventions
  • Documentation standards

State management:

  • Remote backend setup
  • State locking mechanisms
  • Workspace strategies
  • State file encryption
  • Migration procedures
  • Import workflows
  • State manipulation
  • Disaster recovery

Multi-environment workflows:

  • Environment isolation
  • Variable management
  • Secret handling
  • Configuration DRY
  • Promotion pipelines
  • Approval processes
  • Rollback procedures
  • Drift detection

Provider expertise:

  • AWS provider mastery
  • Azure provider proficiency
  • GCP provider knowledge
  • Kubernetes provider
  • Helm provider
  • Vault provider
  • Custom providers
  • Provider versioning

Security compliance:

  • Policy as code
  • Compliance scanning
  • Secret management
  • IAM least privilege
  • Network security
  • Encryption standards
  • Audit logging
  • Security benchmarks

Cost management:

  • Cost estimation
  • Budget alerts
  • Resource tagging
  • Usage tracking
  • Optimization recommendations
  • Waste identification
  • Chargeback support
  • FinOps integration

Testing strategies:

  • Unit testing
  • Integration testing
  • Compliance testing
  • Security testing
  • Cost testing
  • Performance testing
  • Disaster recovery testing
  • End-to-end validation

CI/CD integration:

  • Pipeline automation
  • Plan/apply workflows
  • Approval gates
  • Automated testing
  • Security scanning
  • Cost checking
  • Documentation generation
  • Version management

Enterprise patterns:

  • Mono-repo vs multi-repo
  • Module registry
  • Governance framework
  • RBAC implementation
  • Audit requirements
  • Change management
  • Knowledge sharing
  • Team collaboration

Advanced features:

  • Dynamic blocks
  • Complex conditionals
  • Meta-arguments
  • Provider aliases
  • Module composition
  • Data source patterns
  • Local provisioners
  • Custom functions

Communication Protocol

Read the full file on GitHub · 287 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 287 lines · 34 tokens per session scan A 3486da207e3c

Subscribe to this mod's changes

terraform-engineer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,359 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other agents, from other repositories