serverless-modal

serverless-modal is a skill for Claude Code from wanshuiyin/Auto-claude-code-research-in-sleep. It costs 79 tokens per session (3,532 once invoked), scanned A, original, MIT.

A service for running machine-learning workloads on Modal, a cloud platform that provides temporary computing resources. It supports training, fine-tuning, inference, and batch processing on GPUs without requiring SSH access or a manually managed server.

In plain words
What is it for?
Use it to debug CUDA code, run experiments, train or fine-tune models, perform inference, or process batches remotely.
Why use it?
It removes much of the setup involved in using a remote GPU. Computing resources can start for a job and scale down when the job finishes.

Skill for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is modal volume get experiment-results /run_001/results.json ./results/.

Good fit Use it to debug CUDA code, run experiments, train or fine-tune models, perform inference, or process batches remotely.

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 · 16,030 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/serverless-modal

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 serverless-modal

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/serverless-modal"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/serverless-modal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,532 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 3 Apr 2026
  • Snyk warn 3 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 Rogue Agent · line 5
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 $0.00079 $0.03532
Opus 5 $0.00039 $0.01766
Sonnet 5 $0.00016 $0.00706
Haiku 4.5 $0.00008 $0.00353

Measured 9d ago against content hash e8444d7c5e4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

serverless-modal 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 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run(
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/serverless-modal/SKILL.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task: $ARGUMENTS

Overview

Modal is a serverless GPU cloud. Key advantages over SSH-based platforms (vast.ai, remote servers):

  • Zero config: no SSH, no Docker, no port forwarding. Write Python → modal run → done.
  • Auto scale-to-zero: billing stops the instant your code finishes. No idle instances.
  • Local-first: run modal run from your laptop. Code, data, and results stay local; only the GPU function runs remotely.
  • Reproducible environments: dependencies declared in code via modal.Image, not system-level packages. Treat the modal.Image chain as the RENDERED form of the declarative env spec in ../shared-references/compute-env-contract.md — same spec fields (base, ordered pip phases, env vars, smoke probes), same env:<name>@<specHash> ledger entry in .aris/compute/modal.md, same three-tier validation before a long run.

Best for: Users without a local GPU who need to debug CUDA code, run small-scale tests, or iterate quickly on experiments. The $5 free tier (no card) is enough for code debugging; $30 (with card) covers most small-scale experiment runs.

Trade-off: Modal costs more per GPU-hour than vast.ai or Lightning for some GPU tiers, but eliminates setup time and idle billing, often making it cheaper for short/medium workloads. For long training runs (>4 hours), consider vast.ai for lower $/hr.

Authentication

pip install modal
modal setup          # Opens browser login, writes token to ~/.modal.toml
# Verify:
modal run -q 'print("ok")'
  • Sign up: https://modal.com (GitHub/Google login)
  • Free (no card): $5/month — enough for quick tests
  • Free (with card): $30/month — bind a payment method at https://modal.com/settings for the full free tier. Set a workspace spending limit to prevent accidental overcharge (Settings → Usage → Spending Limit)
  • Academic: apply for $10k credits | Startups: apply for $25k credits
  • Secrets: modal secret create huggingface-secret HF_TOKEN=hf_xxxxx

Read the full file on GitHub · 336 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. 9d ago First seen · 336 lines · 79 tokens per session scan A e8444d7c5e4c

Subscribe to this mod's changes

serverless-modal is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (16,030 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 3,532 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Orchestra-Research/AI-Research-SKILLs · 75 tokens

modal-serverless-gpu

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

Orchestra-Research/AI-Research-SKILLs · 42 tokens

skypilot-multi-cloud-orchestration

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

Orchestra-Research/AI-Research-SKILLs · 51 tokens

modal-serverless-gpu

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

raphaelmansuy/edgecrab · 42 tokens

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

raphaelmansuy/edgecrab · 75 tokens

tensorrt-llm

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

raphaelmansuy/edgecrab · 75 tokens