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.
npx skills add soulcodex/agentic --skill terraform-risk-playbookgit clone --depth 1 https://github.com/soulcodex/agenticWrote 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.
[](https://agentmods.dev/skills/soulcodex/agentic/terraform-risk-playbook)<a href="https://agentmods.dev/skills/soulcodex/agentic/terraform-risk-playbook"><img src="https://agentmods.dev/badge/skills/soulcodex/agentic/terraform-risk-playbook/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.
<a href="https://agentmods.dev/skills/soulcodex/agentic/terraform-risk-playbook"><img src="https://agentmods.dev/badge/skills/soulcodex/agentic/terraform-risk-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00698 |
| Opus 5 | $0.00023 | $0.00349 |
| Sonnet 5 | $0.00009 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
terraform-risk-playbook 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terraform Risk Playbook Skill
Use this skill first for any Terraform or OpenTofu task that plans changes, reviews risk, debugs drift/state/CI issues, or proposes destructive or state-mutating operations.
Step 1 - Emit the Response Contract
Every response must include:
- assumptions and version floor:
runtime (
terraformortofu), exact or assumed version, providers, backend, execution path (local, CI, Cloud, Atlantis), environment criticality - risk category addressed
- chosen remediation and tradeoffs
- validation plan with exact commands tailored to the risk tier
- rollback notes for destructive or state-mutating changes
Mandatory rules:
- never recommend direct production apply without a reviewed plan artifact and explicit approval
- never recommend
destroybeforeplan -destroyhas been reviewed - never use
-auto-approvefor destroy guidance
Step 2 - Diagnose Before You Generate
Use risk-routing.md to classify the failure mode before suggesting code,
module changes, test strategy, CI updates, or state operations.
If the task spans multiple failure modes, cover each one explicitly instead of collapsing them into a single generic fix.
Step 3 - Apply Version and Runtime Guards
Use version-runtime-matrix.md before recommending:
moved,import,removed,check, mock providers,write_only- S3
use_lockfile - native
terraform test/tofu test
If the runtime/version is unknown, state the assumption before suggesting version-sensitive patterns.
Step 4 - Run the LLM Mistake Checklist
Use llm-mistake-checklist.md before finalizing guidance that touches:
- resource identity or address changes
- secrets handling
- provider/runtime upgrades
- plan/apply workflow
- set-type assertions or computed values in tests
Step 5 - Handoff to the Right Terraform Skill
This skill is the shared safety layer. It does not own implementation details.
Use:
design-aws-terraform-iacfor architecture, service boundaries, backend strategy, and acceptance criteriacreate-terraform-modulefor module layout, variables/outputs, examples, and implementation scaffoldingcreate-terraform-testsforterraform test, fixtures, and risk-focused test coverageterraform-infrastructurefor repo/stack structure, CI composition, and multi-region patternsuse-aws-mini-stack-emulatorfor local AWS emulation limits and handoff to real-cloud validation
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 91 lines · 46 tokens per session scan A 90f0d2d23b9b
terraform-risk-playbook is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 698 once invoked, about $0.0002 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.
Other skills, from other repositories
issue-resolve
Use when an assessed gflow-cli issue (verdict CONFIRMED-BUG or LIKELY-BUG) has localized, verifiable scope and should be driven to a fix. Mutating and gated: it works in an isolated worktree, fixes test-first, and opens a DRAFT PR for human review. Built to run autonomously (hermes-ops) within a strict action envelope…
hatch3r-bug-fix
Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.
hatch3r-logical-refactor
Workflow for changing behavior or logic flow without adding new features or overhauling UI. Use when modifying business logic, data flows, behavioral rules, or working on logical refactor issues.
od-code-migration
Default reference pipeline for the code-migration taskKind — code-import → design-extract → token-map → rewrite-plan → patch-edit ↔ build-test devloop → diff-review → handoff.
cgs-regression-suite
Use for regression suite tasks that define or run regression coverage for changed systems, prior bugs, critical paths, and release blockers; produce verification evidence, changed or proposed files, and handoff boundaries.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.