kind

kind is a skill for Claude Code, Codex from openshift-online/agent-control-plane. It costs 187 tokens per session (2,644 once invoked), scanned A, original, MIT.

A guide for deploying and testing Ambient Code Platform on a local Kind Kubernetes cluster. Kind runs Kubernetes clusters inside containers on a developer’s machine.

In plain words
What is it for?
Starting a gateway-based Kind cluster, applying tenant configuration, setting up Google or Vertex credentials, launching sandbox sessions, and connecting the local openshell command-line tool.
Why use it?
It gives the required sequence for starting the cluster, logging in, checking tenant namespaces, and creating sandbox sessions, reducing setup mistakes during local testing.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/openshift-online/agent-control-plane/kind
Any agent
npx skills add openshift-online/agent-control-plane --skill kind
Clone the repo
git clone --depth 1 https://github.com/openshift-online/agent-control-plane

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 kind

README.md
[![agentmods](https://agentmods.dev/badge/skills/openshift-online/agent-control-plane/kind.svg)](https://agentmods.dev/skills/openshift-online/agent-control-plane/kind)
Your own site
<a href="https://agentmods.dev/skills/openshift-online/agent-control-plane/kind"><img src="https://agentmods.dev/badge/skills/openshift-online/agent-control-plane/kind.svg" alt="Measured on agentmods" height="20"></a>
Per session 187 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,644 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00187 $0.02644
Opus 5 $0.00093 $0.01322
Sonnet 5 $0.00037 $0.00529
Haiku 4.5 $0.00019 $0.00264

Measured 5d ago against content hash 80419b53be15, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kind 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 5d 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.

skills/deploy/kind/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kind Local Development Skill

Gateway mode (OPENSHELL_USE_GATEWAY=true) delegates sandbox lifecycle to an OpenShell gateway via gRPC. The gateway runs per-tenant and manages Sandbox CRs. Gateway resources (StatefulSet, certgen Job, TLS secrets) are deployed by the control plane reconciler from the platform-config ConfigMap — no Helm chart is involved.

Full Workflow: Cluster → Credential → Sandbox

Step 1 — Deploy the Kind Cluster (REQUIRED)

make kind-up OPENSHELL_USE_GATEWAY=true

Then in a separate terminal:

make kind-port-forward

Check ports with make kind-status.

Verify Tenant Namespaces

After kind-up completes, verify tenant namespaces exist and sandboxes can be created:

kubectl get ns tenant-a tenant-b
kubectl get pods -n tenant-a

Step 2 — Login with acpctl (REQUIRED)

The acpctl binary lives at components/ambient-cli/acpctl (prebuilt).

TOKEN=$(kubectl get secret test-user-token -n ambient-code \
  -o jsonpath='{.data.token}' | base64 -d)
components/ambient-cli/acpctl login --url http://localhost:$API_PORT --token "$TOKEN"

Get $API_PORT from make kind-status (the "backend" port, typically 12856 on the main branch).

Step 3 - Apply Tenant Fleet Definitions (REQUIRED)

The declarative approach uses acpctl apply -k to provision projects, agents, providers, and credentials from kustomize overlays in examples/.

make kind-setup-vertex   # configures Vertex AI env vars and K8s secrets
acpctl apply -k examples/overlays/tenant-a/
acpctl apply -k examples/overlays/tenant-b/

This creates:

  • Projects (tenant-a, tenant-b)
  • Agents with provider declarations (e.g., providers: ["vertex"])
  • Providers (type: vertex, referencing K8s secrets with OAuth2 refresh tokens)
  • K8s Secrets with Vertex AI credentials in each tenant namespace

Prerequisite: make kind-setup-vertex must run first to set ANTHROPIC_VERTEX_PROJECT_ID, CLOUD_ML_REGION, and create K8s secrets with Vertex AI service account credentials in tenant namespaces.

Read the full file on GitHub · 273 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. 5d ago First seen · 273 lines · 187 tokens per session scan A 80419b53be15

Subscribe to this mod's changes

kind is a skill published in the GitHub repository openshift-online/agent-control-plane (11 stars, last pushed 2d ago), licensed MIT. It adds 187 tokens to every session and 2,644 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

scaffold

Provisioning infrastructure via cloud IaC (Terraform/OpenTofu/CloudFormation/Pulumi) and local dev environments (Docker Compose, env vars). Use for IaC design or multi-cloud provisioning.

simota/agent-skills · 43 tokens

azd-deployment

Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.

Ghosteken/agent-harness · 29 tokens

openshell-cli

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and inference routing. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox…

NVIDIA/OpenShell · 127 tokens

langbot-deploy

Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…

langbot-app/LangBot · 104 tokens

compute-env-setup

Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…

UnicomAI/wanwu · 134 tokens

compute-env-setup

Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.

companion-inc/feynman · 45 tokens