vast-gpu

vast-gpu is a skill for Claude Code from wanshuiyin/Auto-claude-code-research-in-sleep. It costs 46 tokens per session (4,329 once invoked), scanned A, original, MIT.

A tool for renting and managing GPU computers from Vast.ai, an online marketplace for on-demand cloud GPU machines. It covers choosing an offer, setting up the machine, running work, and destroying the instance.

In plain words
What is it for?
Use it for training models, running GPU workloads, or accessing a cloud server when local hardware is unavailable.
Why use it?
It lets you use GPU hardware without owning it. It also helps manage the instance lifecycle so rented machines do not remain active unnecessarily.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument; mentions AGENTS.md.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Follow `../shared-references/compute-env-contract.md`: write/reuse the.

not rated 16krepo +239 2d ago A scan Socket: warnSnyk: warnSkillSpector: warn 46 tokens original MIT

Good fit Use it for training models, running GPU workloads, or accessing a cloud server when local hardware is unavailable.

Compare 6 skills from other repositories ↓
About the project

ARIS is a collection of Markdown-based skills that define a workflow for autonomous machine-learning research, including idea discovery, experiment automation, and review loops. Researchers and AI coding agents use it across tools such as Claude Code, Codex, Cursor, and OpenClaw without depending on a single framework. The catalogue entries are ARIS workflow skills and agents.

wanshuiyin/Auto-claude-code-research-in-sleep · 15,970 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
agentmods
npx agentmods add skills/wanshuiyin/auto-claude-code-research-in-sleep/vast-gpu

Made for: Claude Code.

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 vast-gpu

README.md
[![agentmods](https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/vast-gpu/github.svg)](https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/vast-gpu)
Your own site
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/vast-gpu"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/vast-gpu/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.

agentmods 80×15 button for vast-gpu

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/vast-gpu"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/vast-gpu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,329 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket warn 1 Apr 2026
  • Snyk warn 1 Apr 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

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 →

  • medium Excessive Agency · line 353
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 5.1 $0.00046 $0.04329
Opus 5 $0.00023 $0.02165
Sonnet 5 $0.00009 $0.00866
Haiku 4.5 $0.00005 $0.00433

Measured 7d ago against content hash 38e0f7c622e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vast-gpu 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • vast-gpu — 91% identical, 22 lines differ
skills/skills-codex/vast-gpu/SKILL.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vast.ai GPU Management

Manage vast.ai GPU instance: $ARGUMENTS

Overview

Rent cheap, capable GPUs from vast.ai on demand. This skill analyzes the training task to determine GPU requirements, searches for the best-value offers, presents options with estimated total cost, and handles the full lifecycle: rent → setup → run → destroy.

Users do NOT specify GPU models or hardware. They describe the task — the skill figures out what to rent.

Prerequisites: The vastai CLI must be installed (requires Python ≥ 3.10) and authenticated:

pip install vastai
vastai set api-key YOUR_API_KEY

If your system Python is < 3.10, create a virtual environment with Python ≥ 3.10 (e.g., conda create, pyenv, uv venv, etc.) and install vastai there.

SSH public key must be uploaded at https://cloud.vast.ai/manage-keys/ BEFORE creating any instance. Keys are baked into instances at creation time — if you add a key after renting, you must destroy and re-create the instance.

State File

All active vast.ai instances are tracked in vast-instances.json at the project root:

[
  {
    "instance_id": 33799165,
    "offer_id": 25831376,
    "gpu_name": "RTX_3060",
    "num_gpus": 1,
    "dph": 0.0414,
    "ssh_url": "ssh://[email protected]:58955",
    "ssh_host": "1.208.108.242",
    "ssh_port": 58955,
    "created_at": "2026-03-29T21:12:00Z",
    "status": "running",
    "experiment": "exp01_baseline",
    "estimated_hours": 4.0,
    "estimated_cost": 0.17
  }
]

This file is the source of truth for /run-experiment and /monitor-experiment to connect to vast.ai instances.

Workflow

Action: Provision (default)

Analyze the task, find the best GPU, and present cost-optimized options. This is the main entry point — called directly or automatically by /run-experiment when gpu: vast is set.

Step 1: Analyze Task Requirements

Read available context to determine what the task needs:

  1. From the experiment plan (refine-logs/EXPERIMENT_PLAN.md):
    • Compute budget (total GPU-hours)
    • Hardware hints (e.g., "4x RTX 3090")
    • Model architecture and dataset size
    • Run order and per-milestone cost estimates

Read the full file on GitHub · 395 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. 7d ago First seen · 395 lines · 46 tokens per session scan A 38e0f7c622e8

Subscribe to this mod's changes

vast-gpu is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (15,970 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 4,329 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 2026-09-03.

Related

Other skills, from other repositories

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

google-cloud-filestore-autoscale

Inspects Google Cloud Filestore capacity and utilization, evaluates storage scaling rules, and performs capacity autoscaling (scale UP for low free space or scale DOWN for cost optimization). Use when monitoring Filestore instance headroom, resizing instance shares, configuring automated growth/shrink thresholds…

google/skills · 101 tokens

terraform-module-library

Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.

wshobson/agents · 44 tokens

remote-compute-ssh

Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.

aipoch/open-science · 53 tokens

compute-env-setup

Prepare reproducible setup instructions and validate a user-managed named software environment on an Open Science SSH Compute Host, including direct SSH and Slurm hosts. Use when a remote job needs packages, modules, cache variables, or a repeatable activation that the host does not already provide.

aipoch/open-science · 60 tokens

aws-lambda-microvms

Builds, runs, debugs, and operates applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments running inside a container with up to 8 hr lifetimes. Applicable when workloads need strong isolation between tenants, isolated serverless compute, sandbox compute, or…

aws/agent-toolkit-for-aws · 197 tokens