SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/benchflow-ai/skillsbench/modal-gpunpx skills add benchflow-ai/skillsbench --skill modal-gpugit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/modal-gpu)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/modal-gpu"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/modal-gpu.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.00642 |
| Opus 5 | $0.00026 | $0.00321 |
| Sonnet 5 | $0.00010 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
modal-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 6d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modal GPU Training
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.functiondecorator - 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
pip install modal
modal token set --token-id <id> --token-secret <secret>
Minimal Example
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
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 |
What ships with it
5 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.
- 6d ago First seen · 103 lines · 51 tokens per session scan A ba362fbddbfd
modal-gpu is a skill published in the GitHub repository benchflow-ai/skillsbench (1,747 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 642 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 2026-08-30.
Other skills, from other repositories
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
agent-platform-endpoint-management
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).
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.
hf-cloud-sagemaker-deployment-planner
Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image /…
deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.