Modal

What it does

When your agent uses it

• Deploying AI/ML models
• Running GPU-accelerated workloads
• Serving web endpoints
• Scheduling batch jobs

Example prompts

• “/modal”

Requirements

• Python 3
• A credential in MODAL_TOKEN_SECRET
• A credential in API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Check whether MODAL_TOKEN_ID and MODAL_TOKEN_SECRET are already present in the current environment.
2. 2If not, check for those values in a local .env file and load them if appropriate for the workflow.
3. 3Only fall back to interactive modal setup or generating fresh tokens if neither source already provides credentials.

What it can do on your machine

Read from SKILL.md and the folder at commit 8cbdd18. 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
  • uv

  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

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • MODAL_TOKEN_SECRET
  • API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Modal loads about 3.1k tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 150 tokens; SKILL.md has 876 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~150

When it runs · the whole SKILL.md, loaded when a task matches

~3.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~17k

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

• NoteMentions a .env fileSKILL.md:49

  not, check for those values in a local `.env` file and load them if appropriate for the workflow.

• NoteMentions a .env fileSKILL.md:63

  already available in the environment or `.env`, generate them at https://modal.com/settings

• NoteMentions a .env fileSKILL.md:119

  - `.env()` — Set environment variables

• NoteMentions a .env fileSKILL.md:192

  Or from a `.env` file: `modal.Secret.from_dotenv()`

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 BioTender-max/awesome-bio-agent-skills at commit 8cbdd18, republished under its Apache-2.0 licence (© BioTender-max). 876 words, ~3,092 tokens.

name

modal

description

Cloud computing platform for running Python on GPUs and serverless infrastructure. Use when deploying AI/ML models, running GPU-accelerated workloads, serving web endpoints, scheduling batch jobs, or scaling Python code to the cloud. Use this skill whenever the user mentions Modal, serverless GPU compute, deploying ML models to the cloud, serving inference endpoints, running batch processing in the cloud, or needs to scale Python workloads beyond their local machine. Also use when the user wants to run code on H100s, A100s, or other cloud GPUs, or needs to create a web API for a model.

license

Apache-2.0

metadata.skill-author

K-Dense Inc.

uv pip install modal

modal setup

export MODAL_TOKEN_ID=<your-token-id>
export MODAL_TOKEN_SECRET=<your-token-secret>

import modal

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

@app.function()
def square(x):
    return x ** 2

@app.local_entrypoint()
def main():
    # .remote() runs in the cloud
    print(square.remote(42))

image = (
    modal.Image.debian_slim(python_version="3.11")
    .uv_pip_install("torch==2.8.0", "transformers", "accelerate")
    .apt_install("git")
)

@app.function(image=image)
def inference(prompt):
    from transformers import pipeline
    pipe = pipeline("text-generation", model="meta-llama/Llama-3-8B")
    return pipe(prompt)

@app.function(gpu="H100")
def train_model():
    import torch
    device = torch.device("cuda")
    # GPU training code here

# Multiple GPUs
@app.function(gpu="H100:4")
def distributed_training():
    ...

# GPU fallback chain
@app.function(gpu=["H100", "A100-80GB", "A100-40GB"])
def flexible_inference():
    ...

vol = modal.Volume.from_name("model-weights", create_if_missing=True)

@app.function(volumes={"/data": vol})
def save_model():
    # Write to the mounted path
    with open("/data/model.pt", "wb") as f:
        torch.save(model.state_dict(), f)

@app.function(volumes={"/data": vol})
def load_model():
    model.load_state_dict(torch.load("/data/model.pt"))

@app.function(secrets=[modal.Secret.from_name("my-api-keys")])
def call_api():
    import os
    api_key = os.environ["API_KEY"]
    # Use the key

@app.function()
@modal.fastapi_endpoint()
def predict(text: str):
    return {"result": model.predict(text)}

@app.function(schedule=modal.Cron("0 9 * * *"))  # Daily at 9 AM UTC
def daily_pipeline():
    # ETL, retraining, scraping, etc.
    ...

@app.function(schedule=modal.Period(hours=6))
def periodic_check():
    ...

@app.function(
    max_containers=100,    # Upper limit
    min_containers=2,      # Keep warm for low latency
    buffer_containers=5,   # Reserve capacity
    scaledown_window=300,  # Idle seconds before shutdown
)
def process(data):
    ...

results = list(process.map([item1, item2, item3, ...]))

@app.function()
@modal.concurrent(max_inputs=10)
async def handle_request(req):
    ...

@app.function(
    cpu=4.0,              # Physical cores (not vCPUs)
    memory=16384,         # MiB
    ephemeral_disk=51200, # MiB (up to 3 TiB)
    timeout=3600,         # Seconds
)
def heavy_computation():
    ...

@app.cls(gpu="L40S", image=image)
class Predictor:
    @modal.enter()
    def load_model(self):
        self.model = load_heavy_model()  # Runs once on container start

    @modal.method()
    def predict(self, text: str):
        return self.model(text)

    @modal.exit()
    def cleanup(self):
        ...  # Runs on container shutdown

import modal

app = modal.App("llm-service")

image = (
    modal.Image.debian_slim(python_version="3.11")
    .uv_pip_install("vllm")
)

@app.cls(gpu="H100", image=image, min_containers=1)
class LLMService:
    @modal.enter()
    def load(self):
        from vllm import LLM
        self.llm = LLM(model="meta-llama/Llama-3-70B")

    @modal.method()
    @modal.fastapi_endpoint(method="POST")
    def generate(self, prompt: str, max_tokens: int = 256):
        outputs = self.llm.generate([prompt], max_tokens=max_tokens)
        return {"text": outputs[0].outputs[0].text}

app = modal.App("batch-pipeline")
vol = modal.Volume.from_name("pipeline-data", create_if_missing=True)

@app.function(volumes={"/data": vol}, cpu=4.0, memory=8192)
def process_chunk(chunk_id: int):
    import pandas as pd
    df = pd.read_parquet(f"/data/input/chunk_{chunk_id}.parquet")
    result = heavy_transform(df)
    result.to_parquet(f"/data/output/chunk_{chunk_id}.parquet")
    return len(result)

@app.local_entrypoint()
def main():
    chunk_ids = list(range(100))
    results = list(process_chunk.map(chunk_ids))
    print(f"Processed {sum(results)} total rows")

app = modal.App("etl-pipeline")

@app.function(
    schedule=modal.Cron("0 */6 * * *"),  # Every 6 hours
    secrets=[modal.Secret.from_name("db-credentials")],
)
def etl_job():
    import os
    db_url = os.environ["DATABASE_URL"]
    # Extract, transform, load
    ...

© BioTender-max, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (references) in skills/kdense/modal of BioTender-max/awesome-bio-agent-skills.

• SKILL.md
• references/api_reference.md
• references/examples.md
• references/functions.md
• references/getting-started.md
• references/gpu.md
• references/images.md
• references/resources.md
• references/scaling.md
• references/scheduled-jobs.md
• references/secrets.md
• references/volumes.md
• references/web-endpoints.md

Open the folder on GitHubat commit 8cbdd18