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 OutlineDriven/odin-claude-plugin --skill terraform-style-checkgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/terraform-style-check)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/terraform-style-check"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/terraform-style-check/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/outlinedriven/odin-claude-plugin/terraform-style-check"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/terraform-style-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01369 |
| Opus 5 | $0.00019 | $0.00685 |
| Sonnet 5 | $0.00008 | $0.00274 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
terraform-style-check 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 6d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terraform style check
Contract
| Field | Bound contract |
|---|---|
| Trigger | Writing, reviewing, or generating Terraform configurations. |
| Authority | Reversible local: writes only named local HCL files; rollback is version control. No remote mutation. |
| Side effect | Local HCL files are formatted, validated, and may have resource blocks, provider constraints, and security attributes rewritten in place. |
| Done | HCL follows file organization, naming, version pinning, and security best practices and passes terraform fmt and validate. |
Inputs
- Target directory or files (required): the Terraform root module or specific
.tffiles to check. Must exist on disk. - Terraform CLI (required):
terraformmust be available on PATH. - Style overrides (optional): project-specific naming prefixes or security exceptions. If absent, apply defaults below.
Refusals
- Will not run
terraform apply,terraform plan, or any state-mutating command. - Will not modify files outside the declared target set, except that conventionally named destination files (
main.tf,<resource_type>.tf,variables.tf,outputs.tf,versions.tf) may be created or modified by the file-organization step when blocks are moved into them. - Will not suppress, comment out, or work around a validation diagnostic. The HCL is not valid until the diagnostic resolves.
- Will not install the Terraform CLI if it is missing.
Procedure
- Define the target scope. Enumerate
.tffiles under the target directory and record the file set. Do not read or modify files outside this set. Done when: the complete.tffile set is recorded. - File organization. Verify each resource type lives in a file named after its type (
main.tffor provider and terraform blocks,<resource_type>.tffor resources,variables.tffor variable declarations,outputs.tffor outputs,versions.tffor required_providers and required_version). Reorganize misplaced blocks by moving them into their conventionally named file, creating that file if it does not yet exist. Done when: every block resides in its conventionally named file. - Naming conventions. Enforce snake_case for all resource, variable, output, and local names. Ensure resource names include a descriptive suffix matching the resource type (
aws_instance.web_servernotaws_instance.this). Ensure variable names use descriptive nouns (vpc_cidr_blocknotcidr). Done when: every name is snake_case and descriptively suffixed. - Version pinning. Verify every provider in
required_providershas an exact version constraint (= X.Y.Zor~> X.Y.Zwith minor pinned). Verify everymodulesource has a version constraint. Add missing pins using the currently resolved version from.terraform.lock.hclif available; otherwise flag for manual review. Flagging a missing pin for manual review is a non-blocking partial success: the step is done for that provider or module, and the flag is recorded in the compliance report. Done when: every provider and module source has a version constraint or a recorded manual-review flag. - Security defaults. Verify S3 buckets have
server_side_encryption_configuration, public access blocks (block_public_acls,block_public_policy,restrict_public_buckets,ignore_public_aclsalltrue), andversioningenabled. Verify security groups default to deny-all ingress. Verify RDS instances havestorage_encrypted = trueandpublicly_accessible = false. Verify EC2 instances havemetadata_options.http_tokens = "required". Apply defaults where missing unless the file contains an explicit# tfsec:ignoreor# checkov:skipannotation for that resource. Done when: every checked resource has its security defaults or an explicit skip annotation. - Run
terraform fmt -recursive -diffon the target scope. When the input is a specific file list rather than a directory, runterraform fmt -diffon each file individually instead of-recursive. Capture stdout and stderr. Done when:terraform fmtexits zero. - Run
terraform validateon the target directory. When the input is a specific file list rather than a directory, skipterraform validate(it requires a full module directory) and note the skip in the compliance report. Capture stdout and stderr. Done when:terraform validateexits zero, or the skip is recorded for single-file input. - Re-enumerate the target
.tffile set. Verify no file outside the original set was created or modified, except for conventionally named destination files created or modified by the file-organization step (Step 2). Done when: the file set is accounted for, with any new conventionally named files explicitly listed. - Report the final state. List each file touched, each check category (organization, naming, version pinning, security) with pass/fail, and the terraform fmt and validate exit codes. Done when: the compliance report is emitted.
What ships with it
1 file 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.
- 6d ago First seen · 54 lines · 39 tokens per session scan A d8d9a484e8ca
terraform-style-check is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,369 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 2026-09-06.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…