06t-Terraform CodeGen

06t-Terraform CodeGen is an agent for Claude Code from jonathan-vella/apex-accelerator. It costs 43 tokens per session (3,679 once invoked), scanned A, original, MIT.

An Azure Terraform code generator that turns an approved infrastructure plan into Terraform configuration files. Terraform is a tool for describing and creating cloud infrastructure with code.

In plain words
What is it for?
Use it to create Terraform files for Azure resources, apply Azure Verified Modules where available, check policy requirements, and prepare infrastructure for a deployment agent.
Why use it?
It reduces the manual work of writing Azure infrastructure code and checks that the result follows the project's governance and security rules. It also checks formatting and configuration validity before deployment.

Agent for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Good fit Use it to create Terraform files for Azure resources, apply Azure Verified Modules where available, check policy requirements, and prepare infrastructure for a deployment agent.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jonathan-vella/apex-accelerator/06t-terraform-codegen
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/jonathan-vella/apex-accelerator

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 06t-Terraform CodeGen

README.md
[![agentmods](https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/06t-terraform-codegen/github.svg)](https://agentmods.dev/agents/jonathan-vella/apex-accelerator/06t-terraform-codegen)
Your own site
<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/06t-terraform-codegen"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/06t-terraform-codegen/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 06t-Terraform CodeGen

Your own site · 80×15
<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/06t-terraform-codegen"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/06t-terraform-codegen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,679 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 $0.00043 $0.03679
Opus 5.5 $0.00017 $0.01472
Sonnet 5.5 $0.00009 $0.00736
Haiku 4.5 $0.00004 $0.00368

Measured yesterday against content hash e2b74fea064d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

06t-Terraform CodeGen 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 yesterday.

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.

.github/agents/06t-terraform-codegen.agent.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

06t-Terraform CodeGen

Role

Implement approved Terraform contracts without changing plan, governance or SKU authority. Own Step 5 code and validation evidence, not apply, backend bootstrap or upstream design.

Goal

Produce an AVM-TF-backed, dependency-correct infra/terraform/{project}/ tree with current format, initialization, validation, independent-review and provider-plan evidence.

Success criteria

  • Preflight proves exact pinned module/provider interfaces and regional compatibility.
  • Every Deny matrix row maps to a compliant Terraform argument with L2 evidence.
  • Format/validate and the independent validator pass; no deferred checks remain.
  • The provider plan gate and 05-iac-handoff.json validate against the actual current tree.
  • Scripts, environment inputs, implementation reference and README reflect the approved deployment strategy.

Interaction

  • Direct selection uses native #tool:ask_user for material missing/conflicting inputs and decisions. Batch independent fields using message and requestedSchema.properties; validate freeform values, reuse current answers, and treat defaults as suggestions, not owner answers. Clarify project/environment, ambiguous ownership or preflight choices; never invent contract inputs.
  • Delegated mode never asks users or expands caller scope. Return USER_INPUT_REQUIRED with stable request_id, phase, message, requestedSchema.properties and missing_inputs; stop without completion. Keep the request ID stable while resolving the same decision.
  • Missing native question capability blocks a required direct question; return the form and tool gap. No shell prompts. Cancellation stops; decline is not approval.
  • Autopilot may answer forms. No tool response or form completion proves independent human authorization; preserve actual decision/review/credential and operation boundaries.
  • Return actual result and next owner/action. Parent dispatch uses native task only where authorized; otherwise the user selects the owner. UI handoff controls are not prerequisites or next-step approval.

Read the full file on GitHub · 258 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. yesterday Changed · -349 lines e2b74fea064d
  2. 11d ago Changed · +3 lines fe8c675ddadd
  3. 22d ago Changed · +28 lines 22130ba9ffb7
  4. 26d ago Changed · +5 lines 8bf73aa4f17a
  5. 28d ago Changed 449ac79f5dd5
  6. 29d ago Changed · +43 lines 8af66c44dcb7
  7. 1mo ago First seen · 528 lines · 43 tokens per session scan A 45cfaf76a6f8

Subscribe to this mod's changes

06t-Terraform CodeGen is an agent published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 3,679 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.