Borrowing it
Nothing to install: this file belongs to Zayne-sprague/Dr-Claude-Code. 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/Zayne-sprague/Dr-Claude-Code/main/.claude/skills/setup-cluster/SKILL.mdgit clone --depth 1 https://github.com/Zayne-sprague/Dr-Claude-CodeWrote 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/zayne-sprague/dr-claude-code/setup-cluster)<a href="https://agentmods.dev/skills/zayne-sprague/dr-claude-code/setup-cluster"><img src="https://agentmods.dev/badge/skills/zayne-sprague/dr-claude-code/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/zayne-sprague/dr-claude-code/setup-cluster"><img src="https://agentmods.dev/badge/skills/zayne-sprague/dr-claude-code/setup-cluster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00071 | $0.02994 |
| Opus 5.5 | $0.00028 | $0.01198 |
| Sonnet 5.5 | $0.00014 | $0.00599 |
| Haiku 4.5 | $0.00007 | $0.00299 |
Grade A, and why
setup-cluster scanned grade A 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $RUNPOD_API_KEY" \ How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cluster Setup Skill
This is a RIGID workflow. Follow every step. Do not skip phases. Ask before proceeding at each gate.
GPU Memory Reference Table
Use this when estimating GPU requirements:
| GPU | VRAM | Notes |
|---|---|---|
| H200 | 141 GB | Best for 70B+ models |
| H100 SXM | 80 GB | Flagship datacenter GPU |
| H100 PCIe | 80 GB | Slightly lower bandwidth than SXM |
| A100 SXM | 80 GB | Common in academic clusters |
| A100 PCIe | 80 GB | Common in academic clusters |
| GH200 | 96 GB | Grace Hopper — CPU+GPU unified mem |
| L40S | 48 GB | Strong for inference |
| A6000 | 48 GB | Workstation GPU |
| V100 | 32 GB | Older; common in legacy clusters |
| RTX 4090 | 24 GB | Consumer; great for local dev |
| RTX 3090 | 24 GB | Consumer; older |
| RTX 4080 | 16 GB | Consumer mid-range |
| T4 | 16 GB | Common in cloud / budget clusters |
| RTX 3080 | 10 GB | Consumer entry |
| RTX 4070 | 12 GB | Consumer mid-range |
Phase 0: Identify Cluster Type
Ask the user:
"What type of cluster are you setting up?
- SLURM (university HPC, national lab, etc.)
- RunPod (cloud GPU rental)
- Local machine (workstation or server you control directly)"
Route to the appropriate phase based on their answer.
Phase 1a: SLURM Cluster Setup
Step 1.1 — Gather connection info
FIRST: Check ~/.ssh/config for existing aliases.
cat ~/.ssh/config 2>/dev/null
If the user's cluster name already appears as a Host entry in their SSH config, you already have the hostname, user, port, and key. Tell the user: "I found <name> in your SSH config — using hostname <hostname>, user <user>." Use those values directly.
Hostname validation: A valid SSH hostname looks like:
- A FQDN:
login.torch.hpc.nyu.edu,frontera.tacc.utexas.edu - An IP:
192.168.1.100 - An SSH config alias: a short name that appears as
Host <name>in~/.ssh/config
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.
- 2mo ago First seen · 333 lines · 71 tokens per session scan A 65b8b9f1717c
setup-cluster is a skill published in the GitHub repository Zayne-sprague/Dr-Claude-Code (5 stars, last pushed 7mo ago), licensed MIT. It adds 71 tokens to every session and 2,994 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
setup-cluster compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setup-clusterZayne-sprague/Dr-Claude-Code | Skill | 5 | 7mo ago | MIT | A | 71 | Claude Code |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 171 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |