Agent skill

Modal GPU

by benchflow-ai in benchflow-ai/skillsbench

Run Python code on cloud GPUs using Modal serverless platform.

Apache-2.0Auto-check passedBackend & APIs

Install Modal GPU

skills CLI

$ npx skills add benchflow-ai/skillsbench --skill modal-gpu -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install benchflow-ai/skillsbench modal-gpu --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu .claude/skills/modal-gpu && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "modal-gpu" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu into .claude/skills/modal-gpu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "modal-gpu", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add benchflow-ai/skillsbench --skill modal-gpu -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install benchflow-ai/skillsbench modal-gpu --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .agents/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu .agents/skills/modal-gpu && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "modal-gpu" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu into .agents/skills/modal-gpu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "modal-gpu", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add benchflow-ai/skillsbench --skill modal-gpu -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install benchflow-ai/skillsbench modal-gpu --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu .cursor/skills/modal-gpu && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "modal-gpu" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu into .cursor/skills/modal-gpu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "modal-gpu", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/benchflow-ai/skillsbench.git --path tasks-extra/mhc-layer-impl/environment/skills/modal-gpu

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add benchflow-ai/skillsbench --skill modal-gpu -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install benchflow-ai/skillsbench modal-gpu --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu .gemini/skills/modal-gpu && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "modal-gpu" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu into .gemini/skills/modal-gpu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "modal-gpu", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install benchflow-ai/skillsbench modal-gpu

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add benchflow-ai/skillsbench --skill modal-gpu -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .github/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu .github/skills/modal-gpu && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "modal-gpu" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu into .github/skills/modal-gpu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "modal-gpu", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add benchflow-ai/skillsbench --skill modal-gpu -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install benchflow-ai/skillsbench modal-gpu --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu .opencode/skills/modal-gpu && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "modal-gpu" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/modal-gpu into .opencode/skills/modal-gpu/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "modal-gpu", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: modal-gpu
GitHub stars: 1.8k
Token cost: ~657 tokens
SKILL.md length: 143 words
Files: 6 (incl. references)
Skills in repo: 189
Repo updated: Jul 23, 2026
First seen: Oct 9, 2026
Licence: Apache-2.0

At a glance

Run Python code on cloud GPUs using Modal serverless platform.

You need A100/T4/A10G GPU access for training ML models
SKILL.md covers Overview, Quick Reference, Installation and Minimal Example, plus 4 more sections
Calls modal and pip
Tasks that involve Serverless

What it does

Modal GPU is an agent skill from benchflow-ai/skillsbench. Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU selection, data downloading inside functions, and result handling.

Its SKILL.md is about 660 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/common-issues.md`, `references/data-download.md` and `references/getting-started.md`).

It sits in Backend & APIs, covering Serverless and Machine learning. It works with Python. The repository describes itself as: SkillsBench evaluates how well skills work and how effective agents are at using them. The licence is Apache-2.0.

When your agent uses it

You need A100/T4/A10G GPU access for training ML models
Tasks that involve Serverless
Tasks that involve Machine learning

Example prompts

“/modal-gpu”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 9a1f4dd. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- modal
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- modal.com
- github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Modal GPU loads about 657 tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 58 tokens; SKILL.md has 143 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~58
When it runs · the whole SKILL.md, loaded when a task matches: ~657
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~3.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from benchflow-ai/skillsbench at commit 9a1f4dd, republished under its Apache-2.0 licence (© benchflow-ai). 143 words, ~657 tokens.

Download SKILL.mdSave it as .claude/skills/modal-gpu/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.

name: modal-gpu
description: Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU selection, data downloading inside functions, and result handling.

Overview

Modal is a serverless platform for running Python code on cloud GPUs. It provides:

Serverless GPUs: On-demand access to T4, A10G, A100 GPUs
Container Images: Define dependencies declaratively with pip
Remote Execution: Run functions on cloud infrastructure
Result Handling: Return Python objects from remote functions

Two patterns:

Single Function: Simple script with @app.function decorator
Multi-Function: Complex workflows with multiple remote calls

Quick Reference

Topic	Reference
Basic Structure	Getting Started
GPU Options	GPU Selection
Data Handling	Data Download
Results & Outputs	Results
Troubleshooting	Common Issues

Installation

bash

pip install modal
modal token set --token-id <id> --token-secret <secret>

Minimal Example

python

import modal

app = modal.App("my-training-app")

image = modal.Image.debian_slim(python_version="3.11").pip_install(
    "torch",
    "einops",
    "numpy",
)

@app.function(gpu="A100", image=image, timeout=3600)
def train():
    import torch
    device = torch.device("cuda")
    print(f"Using GPU: {torch.cuda.get_device_name(0)}")

    # Training code here
    return {"loss": 0.5}

@app.local_entrypoint()
def main():
    results = train.remote()
    print(results)

Common Imports

python

import modal
from modal import Image, App

# Inside remote function
import torch
import torch.nn as nn
from huggingface_hub import hf_hub_download

When to Use What

Scenario	Approach
Quick GPU experiments	`gpu="T4"` (16GB, cheapest)
Medium training jobs	`gpu="A10G"` (24GB)
Large-scale training	`gpu="A100"` (40/80GB, fastest)
Long-running jobs	Set `timeout=3600` or higher
Data from HuggingFace	Download inside function with `hf_hub_download`
Return metrics	Return dict from function

Running

bash

# Run script
modal run train_modal.py

# Run in background
modal run --detach train_modal.py

External Resources

Modal Documentation: https://modal.com/docs
Modal Examples: https://github.com/modal-labs/modal-examples

Files

SKILL.md and 5 other files (references) in tasks-extra/mhc-layer-impl/environment/skills/modal-gpu of benchflow-ai/skillsbench.

SKILL.md
references/common-issues.md
references/data-download.md
references/getting-started.md
references/gpu-selection.md
references/results.md

Open the folder on GitHubat commit 9a1f4dd

Compare with similar skills

Modal GPU next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Modal GPU compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Modal GPU this skillbenchflow-ai/skillsbench	1.8k	—	~657	Automated safety check: Pass	Apache-2.0	2 mo ago
Modaldavila7/claude-code-templates	32k	7 repos	~2.6k	Automated safety check: Pass	MIT	today
ModalK-Dense-AI/scientific-agent-skills	48k	1 repos	~4.5k	Automated safety check: Notes	Apache-2.0	4 days ago
ModalBioTender-max/awesome-bio-agent-skills	199	—	~3.1k	Automated safety check: Notes	Apache-2.0	3 mo ago
AWS Serverless Edazxkane/aws-skills	367	4 repos	~3.2k	Automated safety check: Pass	MIT	3 mo ago
Modal Serverless GPUOrchestra-Research/AI-Research-SKILLs	13k	5 repos	~2.1k	Automated safety check: Pass	MIT	3 mo ago

Similar skills

Modal
davila7/claude-code-templates
Run Python code in the cloud with serverless containers, GPUs, and autoscaling.
32k GitHub starsUsed in 7 repos~2.6k tokens
Backend & APIsAuto-check passed
Modal
K-Dense-AI/scientific-agent-skills
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs.
48k GitHub starsUsed in 1 repo~4.5k tokens
Backend & APIsAuto-check: notes
Modal
BioTender-max/awesome-bio-agent-skills
Cloud computing platform for running Python on GPUs and serverless infrastructure.
199 GitHub stars~3.1k tokensUpdated 3 mo ago
Backend & APIsAuto-check: notes
AWS Serverless Eda
zxkane/aws-skills
AWS serverless and event-driven architecture expert based on Well-Architected Framework.
367 GitHub starsUsed in 4 repos~3.2k tokens
Backend & APIsAuto-check passed
Modal Serverless GPU
Orchestra-Research/AI-Research-SKILLs
Serverless GPU cloud platform for running ML workloads. An agent skill from Orchestra-Research/AI-Research-SKILLs.
13k GitHub starsUsed in 5 repos~2.1k tokens
Backend & APIsAuto-check passed
Vastai SDK
vast-ai/vast-cli
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
223 GitHub stars~2k tokensUpdated today
Backend & APIsAuto-check passed

Questions about Modal GPU

What does Modal GPU do?

Run Python code on cloud GPUs using Modal serverless platform. Modal GPU is an agent skill from benchflow-ai/skillsbench. Run Python code on cloud GPUs using Modal serverless platform.

When should I use Modal GPU?

Modal GPU fits situations like: you need A100/T4/A10G GPU access for training ML models; tasks that involve Serverless; tasks that involve Machine learning.

How do I install Modal GPU in Claude Code?

Run `npx skills add benchflow-ai/skillsbench --skill modal-gpu -a claude-code`. Or copy the skill folder (tasks-extra/mhc-layer-impl/environment/skills/modal-gpu in benchflow-ai/skillsbench) into .claude/skills/modal-gpu in your project. Claude Code loads it when a task matches its description.

How do I install Modal GPU in Codex?

Run `npx skills add benchflow-ai/skillsbench --skill modal-gpu -a codex`. Or copy the skill folder (tasks-extra/mhc-layer-impl/environment/skills/modal-gpu in benchflow-ai/skillsbench) into .agents/skills/modal-gpu in your project. Codex loads it when a task matches its description.

Can I use Modal GPU in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add benchflow-ai/skillsbench --skill modal-gpu -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/modal-gpu, .gemini/skills/modal-gpu, .github/skills/modal-gpu and .opencode/skills/modal-gpu in your project.

What does Modal GPU need to run?

Going by SKILL.md and its folder, Modal GPU needs the command-line tools its instructions call (modal and pip). Our summary lists: Python 3.

Does Modal GPU access the network?

SKILL.md names 2 domains. As links in the text: modal.com and github.com. This is read from the text; nothing was executed.

Is Modal GPU safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Modal GPU use?

Modal GPU is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Modal GPU use?

About 657 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.8k tokens, read only when the agent opens those files.

What are the alternatives to Modal GPU?

Skills that share tags, products or a category with Modal GPU: Modal (davila7/claude-code-templates, 32k stars), Modal (K-Dense-AI/scientific-agent-skills, 48k stars), Modal (BioTender-max/awesome-bio-agent-skills, 199 stars) and AWS Serverless Eda (zxkane/aws-skills, 367 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Modal GPU?

benchflow-ai (a GitHub organization) maintains it in benchflow-ai/skillsbench, which has 1,834 GitHub stars. The repository holds 189 skills in this directory. The repository was last updated on July 23, 2026.

Source: benchflow-ai/skillsbench on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Modal GPU

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Modal GPU Training

Overview

Quick Reference

Installation

Minimal Example

Common Imports

When to Use What

Running

External Resources

Files

Compare with similar skills

Similar skills

More from benchflow-ai/skillsbench

Related

Questions about Modal GPU