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-secretnpx skills add controlplane-com/ai-plugin --skill setup-secretgit 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 | $0.00048 | $0.02269 |
| Opus 5 | $0.00024 | $0.01135 |
| Sonnet 5 | $0.00010 | $0.00454 |
| Haiku 4.5 | $0.00005 | $0.00227 |
Grade A, and why
setup-secret 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secret Access Setup
Tool availability: secrets are read-only through MCP on every profile —
list_resources/get_resource(kind="secret") show existence and metadata, never values. No tool creates, edits, deletes, or reveals a secret: secret data and lifecycle are managed by the user (Console, CLI, Terraform, Pulumi, or the API); you draft manifests with placeholders, the user fills the values and applies.grant_workload_secret_access(every profile) grants a workload access — it never returns values.
Secret access is the #1 thing users get wrong: a workload reads a secret only when three things are all in place. Miss any one and the value is silently absent at runtime — or the deployment pauses on an unresolved reference.
The mandatory chain
| Step | What must be true | Without it |
|---|---|---|
| 1. Identity | an identity exists and is linked to the workload (spec.identityLink) |
workload has no API credential — reads nothing |
| 2. Policy | a policy grants that identity reveal on the secret |
reference resolves to empty |
| 3. Reference | the secret is injected as cpln://secret/NAME (env or volume) |
nothing to read |
reveal, not view — view exposes only metadata. This is the single most common mistake.
Pull secrets are different — no identity/policy
To pull images from a private registry, don't build the chain. Add the registry secret to the GVC's pullSecretLinks and every workload in that GVC can pull. Pull secrets are registry credentials — docker, ecr, or gcp types.
kind: gvc
spec:
pullSecretLinks:
- //secret/my-registry
Authoring a secret manifest — the user applies it
Drafting the manifest is an expected part of the job — users ask for a scaffold, fill in the real values themselves, and apply it. Generate the YAML with UPPERCASE placeholders, then always hand back the next steps:
- Fill in the placeholders locally — the value never enters the chat.
- Apply it:
cpln apply -f secret.yaml --org ORG, the Console's cpln apply button (paste the YAML), or the per-type CLI command that reads the value from a file (cpln secret create-docker --name NAME --file config.json). - Treat the filled file as a live credential — keep it out of git and delete it after applying.
- Say when it's done — verify with
get_resource(kind="secret") and continue with the access chain below.
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 · 138 lines · 48 tokens per session scan A d86435a05d63
setup-secret is a skill published in the GitHub repository controlplane-com/ai-plugin (10 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 2,269 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…