Terraform Plan Review with Claude Code: API Runtime Pattern
A production playbook for Terraform plan review in cross-industry operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Infrastructure teams
The problem
Infrastructure teams need Terraform plan review to run repeatedly against plan output, modules, policy checks, and deploy notes. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the Terraform plan review instructions as a skill, send plan output, modules, policy checks, and deploy notes as run-scoped inputs, execute with Claude Code, poll terminal status, and consume argo.result.v1 instead of parsing a transcript.
Tradeoffs and failure modes
The API boundary forces the workflow to define inputs, terminal states, and result shape before customers depend on it. For Terraform plan review, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Run request
POST /api/skills/<skill_id>/run
provider=claude-code
workflow=terraform-plan-review
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo