Files
Jonathan Boniface c84dbdea20 feat: the solution architecture agent on the shared Execution engine
The reference agent's subject, cloud solution architecture, as an agent in
the operating model agent's pattern: the Execution engine (from
orchestration_engine) and one Workflow in app/solution_architecture,
built for the settings and provider bundle by assembly.workflow_for.

Copied from gcp_solution_architecture_agent at 8b397cd without its own
engine: its role files, Skills, provider bundle, ADRs, vocabulary, scripts
and evaluation datasets. The image takes the engine from a named build
context and installs Terraform. It is called through the Orchestration
engine, and its files are what the operating model agent digests.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-21 19:49:28 +01:00

4.1 KiB

name, description, metadata
name description metadata
iac-validation Checks Terraform infrastructure-as-code without provisioning anything, using the local terraform_fmt, terraform_validate, terraform_plan and terraform_schema tools. Use when writing deployment guidance or validating it before deployment.
scope
deployment-guidance validation

IaC validation

Every check runs on a scratch copy of your Terraform files. Nothing is applied, and no state is written.

The files are your working copy: the files you wrote with write_file, or, when you are validating, the files that were submitted. Pass the tools no files.

Tools

  • terraform_fmt(): formats your working copy in place and names the files it changed.

  • terraform_validate(): runs init -backend=false and validate offline. It reports syntax errors, unknown references, missing variables and invalid arguments.

  • terraform_plan(variables): previews the changes against the live cloud environment. It reads live state, so the first call may pause for the user's permission. Pass every variable the configuration requires.

  • terraform_schema(resource_type, block, find, resource_types): what a resource type accepts, from the provider's own schema. With resource_types, a list, it outlines every argument and block of each in one call; use that when you need several. With resource_type alone it lists the top-level arguments and outlines every block. With block, such as template.containers, it gives that block's arguments in full. With find, it says where an argument or block of that name sits, or that the resource type has none; give several names separated by commas to check them in one call.

  • terraform_module(source, version, find), only when the Execution opted into published modules: what a published module accepts, from the registry: its inputs with their types, its outputs and its submodules. It says when a module cannot be used with the pinned provider. find narrows the inputs to those matching the words given. Only modules from the namespaces the Cloud provider allows can be looked up or used.

When writing deployment guidance

  1. Run terraform_fmt, then terraform_validate.
  2. Fix each error with edit_file, changing only the lines concerned, and run terraform_validate again until it passes.
  3. A refusal about a module means one of two things. The Execution writes plain resources, so write them directly. Or the module is not from an approved namespace or not pinned to one exact version, so use an approved module at an exact version or write the resources directly.
  4. On "An argument named X is not expected here" or "Unsupported block type", call terraform_schema with find set to the name. It is either in a different block, which the reply names, or it does not exist on that resource type. Never move it around by trial.

When validating deployment guidance

  1. Run terraform_validate, and report its verdict and output.

  2. When permission to read the live environment is granted, run terraform_plan with the variable values from the requirements, or clearly marked placeholders. Summarise the resources to add, change and destroy, and flag any destroy or replace.

  3. When a check can't run (a missing CLI, a refused permission or a provider download failure), give the user the exact commands to run themselves:

    terraform init -backend=false
    terraform validate
    terraform plan -lock=false -var-file=<your.tfvars>
    

Reporting verdicts

Give a verdict on every Check in the Target architecture. Record them with verdict_put, a few Checks per call; they are attached as verdicts.json, in the format the requirements-chain Skill gives, when you submit. The dry-run's result goes in its dry_run entry: pass when terraform_validate passes, fail with the error when it does not, and not_run when the tool could not run.

A Check fails when the code could meet it and does not. When terraform_schema shows the resource type has no such setting, no code could meet it: the verdict is not_verifiable, with the schema's answer as evidence.

Never suggest terraform apply as part of validation.