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.
curl -O https://raw.githubusercontent.com/nozomi-koborinai/terradart/main/.agents/skills/terradart-add-curated-resource/SKILL.mdgit clone --depth 1 https://github.com/nozomi-koborinai/terradartWrote 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/nozomi-koborinai/terradart/terradart-add-curated-resource)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00050 | $0.01932 |
| Opus 5 | $0.00025 | $0.00966 |
| Sonnet 5 | $0.00010 | $0.00386 |
| Haiku 4.5 | $0.00005 | $0.00193 |
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 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 — 77 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.jsonwith 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
terraformis installed in cloud-agent VMs unless the task provides it.
Workflow
Task progress:
- 1. Confirm the type exists in
schema.json. Note the exactgoogle_*key (do not infer from MM product file names). IAM adjuncts may be*_iam_member,*_iam_binding, or*_iam_policy. For binding/policy, setcuratedDocthat states authoritative / replace semantics (yaml_loader_test.dartenforces this). Prefer*_iam_memberin examples when an additive grant is enough. - 2. Manifest: add or update one row in
tool/mm_yaml_sources.yaml(upstreampath ornullwith reason). Every curated override must have a manifest entry. - 3. MM fixture (when
upstreamis set): rundart tool/sync_mm_yaml.dartfor 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). - 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 underterradart_google/lib/are generated bywrapfrom the catalog — never hand-edit them;wrapfails 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). - 7. Regenerate:
dart run bin/terradart.dart wrap --only <terraform_type> ...then fullwrap --checkagainst the fixture paths inAGENTS.mdUseful Commands. - 8. Review the generated
terradart_googlediff (constructors, enums, sealed types, sensitive fields, barrel export). - 9. Counts: if catalog size changed, update
tool/doc_expectations.dart,catalog_count_test.dart, andwrap_command_test.dartfile-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/*IamPolicywhen the sibling*IamMemberis already curated and in quickstart synth, prefertool/example_debt.yamlwithiam-adjunct-debt:over extending examples; otherwise add or extend a quickstart.curatedDocalone is not enough. - 10b. Cost-classify (mandatory — do not skip): every Terraform type in the example synth output (including dependencies like
google_storage_bucket). Before editingtool/apply_cost_denylist.yaml, call gcp-cost MCP:list_services→list_skus→get_sku_price. Recordgcp-cost: SKU …(orgcp-cost: no Cloud Billing Catalog SKUafter MCP lookup) plusbilling-behavior:in the comment.billing-behavior:alone is only valid for*_iam_member/*_iam_binding/*_iam_policy. Hourly-billed types (e.g. VPN tunnel) →sweep_only, notsafe. When unsure, leave unclassified (default-deny). CI test 13 rejects hand-wavysafecomments. - 11. Verify: run the
terradart-agent-verifyworkflow (tool/agent_verify.sh; add--maintainerwhen touching wrap-init / wrap-promote).
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 Changed · -2 lines 235f2f60dad3
- 12d ago First seen · 79 lines · 50 tokens per session scan A dc36522bd6e3
terradart-add-curated-resource is a skill published in the GitHub repository nozomi-koborinai/terradart (46 stars, last pushed 3d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,932 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
gcp-expert
Expert-level Google Cloud Platform, services, and cloud architecture. Use when the user mentions Google Cloud, Cloud Functions, BigQuery, or Firestore.
gcloud-cli
Manage Google Cloud projects, IAM, GKE, Cloud Run, and storage with gcloud while checking the active project and deployment target.
oma-tf-infra
Infrastructure-as-code specialist for multi-cloud provisioning using Terraform across any provider (AWS, GCP, Azure, Oracle Cloud). Use for terraform plan/apply, state management, compute, databases, storage, networking, IAM, OIDC, cost optimization, policy-as-code, ISO/IEC 42001 AI controls, ISO 22301 continuity, and…
databricks-platform-provisioning
Provision and test Databricks workspaces. Use when the user asks to create a workspace, set up a new environment, provision infrastructure, bootstrap Databricks, test a workspace, verify a deployment, or run validation checks against a Databricks workspace. Covers Azure, AWS, and GCP.
databricks-deployment-verification
MANDATORY post-deployment verification. After any workspace + Unity Catalog deployment, you MUST run all THREE compute paths against a UC table — classic cluster, serverless SQL warehouse, serverless notebook job. Skipping any of the three is incomplete work. Use whenever a workspace + UC has been freshly deployed or…
databricks-unity-catalog-setup
Set up Unity Catalog on Databricks workspaces. Use when the user asks to configure Unity Catalog, create a metastore, set up catalogs, schemas, external locations, storage credentials, or configure data governance. Covers Azure, AWS, and GCP.