Borrowing it
Nothing to install: this file belongs to mckinsey/agents-at-scale-ark. 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/mckinsey/agents-at-scale-ark/main/.claude/skills/ark-setup-cluster/SKILL.mdgit clone --depth 1 https://github.com/mckinsey/agents-at-scale-arkWrote 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/mckinsey/agents-at-scale-ark/ark-setup-cluster)<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/ark-setup-cluster"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/ark-setup-cluster/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/mckinsey/agents-at-scale-ark/ark-setup-cluster"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/ark-setup-cluster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Privilege Escalation · line 63 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 67 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 71 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 67 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00054 | $0.01093 |
| Opus 5 | $0.00027 | $0.00547 |
| Sonnet 5 | $0.00011 | $0.00219 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade C, and why
ark-setup-cluster scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
kind get kubeconfig --name <cluster-name> --internal | sed "s/<cluster-name>-control-plane/$CONTROL_PLANE_IP/g" > ~/.kube/config How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ark Setup Cluster
Set up and install the Ark platform using ark-cli. Supports two modes:
- Default: Deploy Ark to an existing cluster
- Isolated e2e: Create a dedicated Kind cluster for testing without affecting existing clusters
When to use this skill
- User wants to install or set up Ark
- Build manager needs an isolated cluster for e2e testing
- User needs to deploy Ark to their local cluster
- User needs to troubleshoot Ark installation issues
Prerequisites
- Docker - Required for Kind cluster creation
- kubectl - Kubernetes CLI
- Helm - For installing Ark components
- Node.js - For building the ark-cli tool
- Kind - For creating local clusters (
which kind)
Step 0: Check existing cluster state
CRITICAL: Always check before creating or modifying clusters.
kubectl cluster-info 2>/dev/null
kubectl get pods -n default 2>/dev/null | head -10
kind get clusters 2>/dev/null
If a cluster is already running
Never silently destroy an existing cluster. It may have user data, demos, or in-progress work. Present options:
- Option A: Reuse existing cluster — deploy Ark into it. Fastest, but overwrites current Ark state.
- Option B: Create isolated cluster (recommended for e2e testing) —
kind create cluster --name ark-e2e-test. Fully isolated, preserves existing cluster. - Option C: Replace existing cluster — delete and recreate. Only if user explicitly confirms.
Wait for user to choose, or if called by the build manager for e2e testing, default to Option B.
Step 1: Create cluster
Default mode (existing cluster or new ark-cluster)
kind create cluster --name ark-cluster
Isolated e2e testing mode
kind create cluster --name ark-e2e-test
kubectl config use-context kind-ark-e2e-test
Configure kubeconfig (if running inside Docker/DinD)
CONTROL_PLANE_IP=$(docker inspect -f '{{range.NetworkSettings.Networks}}{{.IPAddress}}{{end}}' <cluster-name>-control-plane)
kind get kubeconfig --name <cluster-name> --internal | sed "s/<cluster-name>-control-plane/$CONTROL_PLANE_IP/g" > ~/.kube/config
kubectl cluster-info
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.
- 9d ago First seen · 143 lines · 54 tokens per session scan C d4769315d870
ark-setup-cluster is a skill published in the GitHub repository mckinsey/agents-at-scale-ark (423 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,093 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
chaos-experiment
Design and document chaos engineering experiments. Guide steady state baseline, hypothesis formation, failure injection plans, and results analysis. Use when you say "design a chaos experiment", "plan a game day", "failure injection", "test resilience", or "chaos engineering". Do NOT use for security threat analysis…
cross-repo-testing
This skill should be used when the user asks to "test a cross-repo feature", "deploy a feature branch to staging", "test SDK against OH Cloud", "e2e test a cloud workspace feature", "test provider tokens", "test secrets inheritance", or when changes span the SDK and OpenHands server repos and need end-to-end…
container-manager-kubernetes-operations
Full operational Kubernetes surface via the container-manager-mcp MCP server — workloads (pods/rollouts/StatefulSets/DaemonSets/ReplicaSets/Jobs/CronJobs), config (ConfigMaps/Secrets/Namespaces/CRDs/patch), networking (Ingress/native Services/NetworkPolicy/DNS), storage (PV/PVC/StorageClass/snapshots/CSI), RBAC…
k8s-ops
Opinionated multi-step Kubernetes workflows on top of the k8s-mcp server. Encodes tool-sequencing logic and failure-mode decision trees for deploying from a repo, debugging pods/rollouts, performing safe restarts, and auditing cluster posture. Use when the user asks to deploy, diagnose, restart, roll out, or audit…
kubernetes-mesh-provisioner
Kubernetes Mesh Provisioner atomic skill. Stands up an RKE2 cluster (server + agents) with Cilium CNI and the NVIDIA GPU device plugin, the Kubernetes parallel of swarm-mesh-provisioner. Idempotent — re-runnable.
agent-production-validator
Agent skill for production-validator - invoke with $agent-production-validator.