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/multi-branch-cluster-setup/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/multi-branch-cluster-setup)<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/multi-branch-cluster-setup"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/multi-branch-cluster-setup/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/multi-branch-cluster-setup"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/multi-branch-cluster-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.01793 |
| Opus 5 | $0.00034 | $0.00897 |
| Sonnet 5 | $0.00013 | $0.00359 |
| Haiku 4.5 | $0.00007 | $0.00179 |
Grade A, and why
multi-branch-cluster-setup 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 7d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Branch Cluster Setup
Provisions one minikube cluster per branch supplied by the user. The number of clusters matches the number of branches — 2 branches = 2 clusters, 4 branches = 4 clusters, etc.
Cluster naming and port assignment (dynamic, based on branches provided):
| # | Cluster name | Worktree | Branch | Dashboard | API | Gateway |
|---|---|---|---|---|---|---|
| 1 | ark-cluster-1 |
$ARK_REPO (main repo, no worktree needed if branch 1 = current) |
branch 1 | :3274 | :8080 | :8090 |
| 2 | ark-cluster-2 |
/tmp/ark-worktree-<branch2-slug> |
branch 2 | :3275 | :8081 | :8091 |
| 3 | ark-cluster-3 |
/tmp/ark-worktree-<branch3-slug> |
branch 3 | :3276 | :8082 | :8092 |
| N | ark-cluster-N |
/tmp/ark-worktree-<branchN-slug> |
branch N | :3273+N | :8079+N | :8089+N |
Port formula: Dashboard = 3273+N, API = 8079+N, Gateway = 8089+N
Prerequisites check
Run before starting:
minikube version && kubectl version --client && helm version --short && devspace version && docker info | grep "Total Memory"
Set your repo path (replace with your actual checkout location):
export ARK_REPO=~/agents-at-scale-ark # adjust if cloned elsewhere
Docker Desktop memory requirement: ~0.7 GB base + (N × 2.2 GB). For 3 clusters: ~7 GB minimum. Set via Docker Desktop → Settings → Resources → Memory.
Step 1 — Extract branches from the user's request
If the user's message contains branch names (e.g. "create clusters with branch1 branch2 branch3"), extract all of them directly — do NOT ask for confirmation.
- The number of clusters = the number of branches provided
- Assign each branch to
ark-cluster-N(N = 1, 2, 3...) - Branch slug = branch name with
/replaced by- - Branch 1 uses
$ARK_REPOdirectly if it matches the current checkout; otherwise also gets a worktree - Branches 2..N each get a worktree at
/tmp/ark-worktree-<branchN-slug>
If no branches are provided in the message, ask how many clusters and which branches.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 177 lines · 67 tokens per session scan A b92e00cf52ae
multi-branch-cluster-setup is a skill published in the GitHub repository mckinsey/agents-at-scale-ark (422 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 1,793 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 2026-09-03.
Other skills, from other repositories
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.
aiq-deploy
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
timoni
Use when deploying applications to Kubernetes with Timoni. Covers installing and upgrading module instances from OCI registries, composing multi-app deployments with bundles, injecting values from clusters or CI with runtimes, targeting multiple clusters, and authoring, testing, signing and publishing modules with CUE.