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 agentmods add skills/controlplane-com/ai-plugin/setup-cloud-accessnpx skills add controlplane-com/ai-plugin --skill setup-cloud-accessgit clone --depth 1 https://github.com/controlplane-com/ai-pluginWhat 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 | $0.00049 | $0.02220 |
| Opus 5 | $0.00024 | $0.01110 |
| Sonnet 5 | $0.00010 | $0.00444 |
| Haiku 4.5 | $0.00005 | $0.00222 |
Grade A, and why
setup-cloud-access 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 2d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Access Setup (Universal Cloud Identity)
Tool availability: the cloud-account tools (
create_cloud_account,update_cloud_account,how_to_create_<provider>_cloud_account) live in thefullprofile.create_identity/update_identityandupdate_workloadarecore. If a full tool isn't advertised, reconnect with?toolsets=fullor use thecplnCLI. Thenats-account/azure-connectorsecret a cloud account references must already exist — created by the user; offer to draft the manifest for them to fill and apply (setup-secretskill). Reads work on every profile vialist_resources/get_resource;delete_resourceis on every profile exceptreadonly.
A workload reads cloud resources with no embedded keys: a GVC-scoped identity carries a per-provider cloud-access block that federates with the provider's IAM, and Control Plane vends short-lived credentials at runtime. Cloud SDKs (boto3, google-cloud, @azure/sdk) pick them up automatically — no SDK config.
The chain
| Step | What must be true | Without it |
|---|---|---|
| 1. Cloud account | a cloud_account (org-wide) maps to the provider, registered after the cloud-side IAM setup |
identity can't federate |
| 2. Identity cloud block | the identity carries an aws/gcp/azure/ngs block linking that cloud account |
no credentials vended |
| 3. Workload link | the identity is attached to the workload (spec.identityLink) |
workload has no identity |
Order is strict: the cloud account must exist before the identity's cloud block references it.
Key constraints
- Identities are GVC-scoped — one per workload, shareable within a GVC, never across GVCs. Same access in another GVC = recreate the identity there.
- One cloud account per provider per identity — one AWS + one GCP + one Azure + one NGS is fine; two AWS on one identity is not.
- Cloud accounts are org-scoped — always pass
org. - Provider is immutable — to switch providers, delete and recreate the cloud account.
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.
- 2d ago First seen · 116 lines · 49 tokens per session scan A 779b627cadea
setup-cloud-access is a skill published in the GitHub repository controlplane-com/ai-plugin (10 stars, last pushed 8d ago), licensed MIT. It adds 49 tokens to every session and 2,220 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
rustfs-release-publish
Run the end-to-end RustFS console gate, version bump, preview validation, human confirmation, and final-tag publication pipeline. Use only when the user explicitly asks to release or publish a RustFS version (发版/发布).
pr-review
Review a GitHub PR end-to-end from a URL or number — fetch metadata, inspect the diff, run multi-role adversarial review, check CI status, and post the review comment. Use when the user provides a PR link and asks to review it.
issue-triage
Triage a GitHub issue — determine if it is already fixed, needs implementation, or should be closed. Searches related commits and PRs, verifies implementation status, and posts a triage comment or closes the issue. Use when the user provides an issue URL and asks whether it can be closed or needs work.
security-advisory-lessons
Perform a dedicated RustFS security/advisory review for authn/authz, IAM, RPC trust, paths, secrets, browser isolation, encryption, Object Lock, or other security boundaries. Use only when the user requests a security/advisory review or an adversarial review explicitly escalates to the full advisory map; do not…
tier-debug
Debug ILM tiering / lifecycle transition issues — NoSuchVersion on tier GET, restore failures, xl.meta inspection, remote-tier versionId tracing. Use when investigating tiered/transitioned objects, warm backends, or transition metadata.
plugin-contract-guard
Invariants and change procedure for the target-plugin / extension system — plugin manifests, admin plugin/extension catalog and instance APIs, secret redaction, external-plugin install policy. Use when editing crates/targets (manifest, plugin, controlplane, catalog, runtime), crates/extension-schema, or…