Skip to content
Back to skills

Ops Terraform

ASecurity

Read-only Terraform posture detector: binary/version, formatting, validate, and saved-plan summary for a target module directory. Detection only - no init with backend, no plan against live state, no apply. Use for "terraform health", "is this module valid", "summarize this plan file", "ops-terraform".

  • 6 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 11, 2026
developmentbashterraformapibackend

Works with

  • api

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned September 11, 2026

npx -y skills add grahama1970/agent-skills --skill ops-terraform --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ops Terraform?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ops Terraform
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/grahama1970-ops-terraform/badge)](https://www.skillsdirectory.com/skills/grahama1970-ops-terraform)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: ops-terraform
description: >
  Read-only Terraform posture detector: binary/version, formatting, validate,
  and saved-plan summary for a target module directory. Detection only - no
  init with backend, no plan against live state, no apply. Use for "terraform
  health", "is this module valid", "summarize this plan file", "ops-terraform".
triggers:
  - ops-terraform
  - terraform health
  - terraform module valid
  - summarize terraform plan
provides:
  - terraform-posture-detection
composes:
  - triage-error
  - agentic-evals
complies:
  - best-practices-skills
runtime_self_improvement: none
taxonomy:
  - validation
  - observability
disciplines:
  - developer-tooling
---

# ops-terraform

Detection only, fail-closed. The teaching skill for the skills-first
methodology: contract, one front door, typed outcomes, eval gate - built the
same way a mutating Terraform lane would later be added as a Tau-controlled
tool (plan-hash-bound approval), which this skill deliberately does NOT do.

```bash
./run.sh doctor                       # binary, version, env posture
./run.sh check <module-dir>           # fmt -check + validate (backend=false)
./run.sh plan-summary <plan.json>     # counts adds/changes/destroys from a saved plan JSON
./run.sh registry <query>             # public Registry API module search
./run.sh hcp-status                   # HCP api/v2 account posture (TFE_TOKEN; fail-closed)
```

Outcomes are typed JSON with status PASS|FAIL|NOT_CONFIGURED and a
failure_code on every non-PASS. Mutation (init against real backends, plan
against live state, apply) is out of scope by contract - that belongs to a
Tau tool lane with approval binding.

Files in this skill

  • SKILL.md1.6 KB
  • fixtures/agentic_eval.json4 KB
  • fixtures/sample_plan.json180 B
  • run.sh152 B
  • scripts/ops_terraform.py7.4 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.