terradart: Skill for Claude Code

.agents/skills/terradart-add-curated-resource/SKILL.md

terradart-add-curated-resource is a skill for Claude Code, Codex from nozomi-koborinai/terradart. It costs 50 tokens per session (2,361 once invoked), scanned A, original, Apache-2.0.

A step-by-step skill for adding or updating a curated Google Cloud resource in TerraDart, a tool that generates Dart wrappers for Terraform resources. It uses provider schemas and project overrides, then regenerates the generated code.

In plain words
What is it for?
Use it to add a Google Cloud resource, configure its Terraform type and optional IAM behavior, update generation inputs, run linting, and verify the result.
Why use it?
It prevents hand-editing generated files and helps keep schemas, metadata, overrides, documentation, and generated wrappers consistent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is nozomi-koborinai/terradart's own configuration. It tells Claude Code and Codex how to work on terradart itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything terradart configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is --output ../terradart_google/lib/src \.

Reuse

Borrowing it

Nothing to install: this file belongs to nozomi-koborinai/terradart. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nozomi-koborinai/terradart/main/.agents/skills/terradart-add-curated-resource/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nozomi-koborinai/terradart

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for terradart-add-curated-resource

README.md
[![agentmods](https://agentmods.dev/badge/skills/nozomi-koborinai/terradart/terradart-add-curated-resource/github.svg)](https://agentmods.dev/skills/nozomi-koborinai/terradart/terradart-add-curated-resource)
Your own site
<a href="https://agentmods.dev/skills/nozomi-koborinai/terradart/terradart-add-curated-resource"><img src="https://agentmods.dev/badge/skills/nozomi-koborinai/terradart/terradart-add-curated-resource/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.

agentmods 80×15 button for terradart-add-curated-resource

Your own site · 80×15
<a href="https://agentmods.dev/skills/nozomi-koborinai/terradart/terradart-add-curated-resource"><img src="https://agentmods.dev/badge/skills/nozomi-koborinai/terradart/terradart-add-curated-resource.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,361 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 50
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.02361
Opus 5.5 $0.00020 $0.00944
Sonnet 5.5 $0.00010 $0.00472
Haiku 4.5 $0.00005 $0.00236

Measured 27d ago against content hash 132ced9674bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

terradart-add-curated-resource 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 27d 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.

.agents/skills/terradart-add-curated-resource/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add or update a curated Google resource

Read CONTEXT.md for vocabulary. Generation policy and pitfalls are in AGENTS.md. Do not hand-edit files under packages/terradart_google/lib/src/ — regenerate with terradart wrap.

Contents

Inputs

  • schema.json with the target Terraform type (checked-in fixture or task-provided artifact).
  • Optional Magic Modules YAML when semantic hints help (see tool/mm_yaml_sources.yaml).
  • Do not fetch schemas ad hoc or assume terraform is installed in cloud-agent VMs unless the task provides it.

Workflow

Task progress:

  • 1. Confirm the type exists in schema.json. Note the exact google_* key (do not infer from MM product file names). IAM adjuncts may be *_iam_member, *_iam_binding, or *_iam_policy. For binding/policy, set curatedDoc that states authoritative / replace semantics (yaml_loader_test.dart enforces this). Prefer *_iam_member in examples when an additive grant is enough. The adjunct's parent argument comes from - parents: iam-adjuncts in tool/reference_targets.yaml (service: api.ref); a parent whose identity input the heuristic misses gets an identity: entry there, not a customSlots override. Its member / members are typed IamPrincipal by - principals: IamPrincipal; examples pass sa.principal or .user(...) / .group(...), never a user: string.
  • 2. Manifest: add or update one row in tool/mm_yaml_sources.yaml (upstream path or null with reason). Every curated override must have a manifest entry.
  • 3. MM fixture (when upstream is set): run dart tool/sync_mm_yaml.dart for that type only if you intend to consume new MM hints in this PR.
  • 4. New resource only: scaffold with terradart wrap-init (skip when editing an existing override — including one the weekly schema bump already scaffolded; its tool/curation_backlog.yaml note says so).
  • 5. Edit packages/terradart_codegen/lib/src/codegen/wrapper_overrides/yaml/<terraform_type>.yaml — keep it thin (human API decisions only).
  • 5b. New barrel? Add its entry to packages/terradart_codegen/lib/src/codegen/barrels/barrels.yaml (doc: required; file: / extraExports: only when needed). Barrel files under terradart_google/lib/ are generated by wrap from the catalog — never hand-edit them; wrap fails closed on a catalog barrel with no manifest entry.
  • 6. Lint: cd packages/terradart_codegen && dart run bin/terradart.dart lint-override (must exit 0). A migrate-shape-underivable finding means the migration manifest cannot derive a prelude helper or custom slot (#659): reshape the helper to a field-per-key encode() map literal, declare customSlots.<slot>.migrate: {kind: manual, reason: ...} when the slot is manual by design, or add a reasoned tool/migrate_manifest_debt.yaml entry — the last two are maintainer decisions, outside the Wave scope ledger.
  • 7. Regenerate: dart run bin/terradart.dart wrap --only <terraform_type> ... for the wrapper, then a full wrap with --migrate-manifest — the migration manifest (packages/terradart_migrate/lib/src/manifest/google.g.dart) is a whole-registry artifact that --only skips, every curated factory adds a MigrateEntry to it, and the wrap --check lane fails while it is stale — then wrap --check against the fixture paths in AGENTS.md Useful Commands.
  • 8. Review the generated terradart_google diff (constructors, enums, sealed types, sensitive fields, barrel export).
  • 9. Counts: if catalog size changed, update tool/doc_expectations.dart, catalog_count_test.dart, and wrap_command_test.dart file-count assertions in the same PR.
  • 10. Wave / example: if this resource is part of a Wave release, follow terradart-ship-wave. For new *IamBinding / *IamPolicy when the sibling *IamMember is already curated and in quickstart synth, prefer tool/example_debt.yaml with iam-adjunct-debt: over extending examples; otherwise add or extend a quickstart. curatedDoc alone is not enough.
  • 10b. Gated example check: if applying the new type needs an organization, an entitlement or real external inputs, bills while it exists, or leaves behind something that cannot be deleted (or a name that stays reserved), its example must be a gated example (README ## Before you apply section — see AGENTS.md Example verification). Extend the product's gated example or add one; never put such a factory into an example without that section. Cost or apply-ability is never a reason for tool/example_debt.yaml.
  • 11. Verify: run the terradart-agent-verify workflow (tool/agent_verify.sh; add --maintainer when touching wrap-init / wrap-promote).

Read the full file on GitHub · 79 lines

Changes

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.

  1. 27d ago Changed · +1 lines 132ced9674bd
  2. 1mo ago Changed e760fd889999
  3. 1mo ago Changed c9ae84fb0382
  4. 1mo ago Changed · +1 lines 8208468d8767
  5. 1mo ago Changed · -2 lines 235f2f60dad3
  6. 2mo ago First seen · 79 lines · 50 tokens per session scan A dc36522bd6e3

Subscribe to this mod's changes

terradart-add-curated-resource is a skill published in the GitHub repository nozomi-koborinai/terradart (52 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 2,361 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Related

Other skills, from other repositories

terraform-infrastructure-as-code

Comprehensive Terraform Infrastructure as Code skill covering resources, modules, state management, workspaces, providers, and advanced patterns for cloud-agnostic infrastructure deployment.

manutej/luxor-claude-marketplace · 36 tokens

Terraform Infrastructure as Code

Production-grade Terraform development with HCL best practices, module design, state management, multi-cloud patterns, and AI-enhanced infrastructure as code for scalable cloud deployments.

bobmatnyc/mcp-skillset · 36 tokens

auditing-terraform-infrastructure-for-security

Auditing Terraform infrastructure-as-code for security misconfigurations using Checkov, tfsec, Terrascan, and OPA/Rego policies to detect overly permissive IAM policies, public resource exposure, missing encryption, and insecure defaults before cloud deployment.

xalgorix/xalgorix · 59 tokens

terraform-expert

Expert-level Terraform infrastructure as code, modules, state management, and production best practices. Use when the user mentions infrastructure as code, devops, or automation, or when the task involves Terraform Basics, Resource Management, Modules, or State Management.

personamanagmentlayer/pcl · 53 tokens

auditing-terraform-infrastructure-for-security

Auditing Terraform infrastructure-as-code for security misconfigurations using Checkov, tfsec, Terrascan, and OPA/Rego policies to detect overly permissive IAM policies, public resource exposure, missing encryption, and insecure defaults before cloud deployment.

26zl/cybersec-toolkit · 59 tokens

terraform-docs

Terraform 1.15.x — configuration language, resources, variables, modules, state, backends, providers, functions.

pledgeandgrow/pledge-skills · 29 tokens