Terraform Reviewer

Terraform Reviewer is an agent for Claude Code from srnichols/plan-forge. It costs 24 tokens per session (944 once invoked), scanned A, original, MIT.

A reviewer for Terraform files that define Azure infrastructure. Terraform is a tool for describing cloud resources in configuration files so they can be created and managed consistently.

In plain words
What is it for?
Reviewing Azure Terraform providers and versions, remote state, managed identity or OIDC authentication, secret handling, variable validation, naming conventions, tags, and resource security.
Why use it?
It checks for configuration, security, naming, authentication, and state-management mistakes before infrastructure is deployed. It also looks for exposed secrets and missing safeguards.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Reviewing Azure Terraform providers and versions, remote state, managed identity or OIDC authentication, secret handling, variable validation, naming conventions, tags, and resource security.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/srnichols/plan-forge/terraform-reviewer
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/srnichols/plan-forge

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 Reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/srnichols/plan-forge/terraform-reviewer.svg)](https://agentmods.dev/agents/srnichols/plan-forge/terraform-reviewer)
Your own site
<a href="https://agentmods.dev/agents/srnichols/plan-forge/terraform-reviewer"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/terraform-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 944 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 $0.00024 $0.00944
Opus 5 $0.00012 $0.00472
Sonnet 5 $0.00005 $0.00189
Haiku 4.5 $0.00002 $0.00094

Measured 7d ago against content hash c34cc80bc7ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Terraform Reviewer 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 7d 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.

presets/azure-iac/.github/agents/terraform-reviewer.agent.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Terraform Reviewer. Audit Terraform configurations for violations of Azure IaC best practices, security standards, and CAF naming conventions.

Your Expertise

  • Terraform HCL language patterns and anti-patterns
  • azurerm and azapi provider best practices
  • Remote state management in Azure Blob Storage
  • Managed Identity and OIDC authentication patterns
  • Security hardening for Azure infrastructure

Review Checklist

Provider & Versions

  • versions.tf exists with required_providers and pinned versions (~> not >=)
  • required_version for Terraform CLI is specified
  • azurerm provider uses use_oidc = true or managed identity — no client_secret
  • Remote backend (azurerm Blob Storage) configured — no local state

Variables

  • All variables have description fields
  • sensitive = true on all secret/credential variables
  • validation blocks on critical variables (environment, naming constraints)
  • No default values containing secrets or placeholder passwords

Locals

  • CAF-conformant naming constructed in locals.tf
  • common_tags local defined and referenced on all resources
  • Unique suffix derived from subscription/resource group ID — not random_id without seed

Resources

  • for_each used instead of count for resource sets
  • tags = local.common_tags (or merge) on every resource
  • lifecycle.prevent_destroy = true on critical production resources
  • No hardcoded resource names — all via locals

Security

  • sensitive = true on all outputs containing secrets
  • Storage accounts: allow_nested_items_to_be_public = false, min_tls_version = "TLS1_2", https_traffic_only_enabled = true
  • Key Vault: soft-delete and purge protection enabled
  • No client_secret in provider configuration
  • Managed Identity used for app-to-resource auth
  • Network rules: default_action = "Deny" on storage accounts and Key Vault
  • No *.tfvars files with real secrets — use environment variables in CI

Read the full file on GitHub · 88 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. 7d ago First seen · 88 lines · 24 tokens per session scan A c34cc80bc7ff

Subscribe to this mod's changes

Terraform Reviewer is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 944 once invoked, about $0.0001 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 2026-08-31.