New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Modal

by BlockRunAI in BlockRunAI/blockrun-mcp

A skill your agent uses when the user needs to run isolated code remotely — a disposable container, optional GPU access (T4 → H100), or a safer place for untrusted / heavy code.

MITAuto-check passed

Install Modal

skills CLI
$ npx skills add BlockRunAI/blockrun-mcp --skill modal -a claude-code

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

GitHub CLI
$ gh skill install BlockRunAI/blockrun-mcp modal --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/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/modal .claude/skills/modal && 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/

Facts

Skill name
modal
GitHub stars
392
Token cost
~1.9k tokens
SKILL.md length
765 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user needs to run isolated code remotely — a disposable container, optional GPU access (T4 → H100), or a safer place for untrusted / heavy code.

  • Works in 3 steps: Quick Python eval → GPU inference, A100, with deps… → Test untrusted code Claude generated
  • The user needs to run isolated code remotely — a disposable container
  • SKILL.md covers READ THIS BEFORE SETTING timeout, How to Call from MCP, Endpoint Catalog and Field Reference, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Modal is an agent skill from BlockRunAI/blockrun-mcp. Use when the user needs to run isolated code remotely — a disposable container, optional GPU access (T4 → H100), or a safer place for untrusted / heavy code. Prefer local execution for normal repo work; use Modal sandboxes for isolation, hardware access, or one-shot heavy compute.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments. The licence is MIT.

When your agent uses it

  • The user needs to run isolated code remotely — a disposable container
  • Optional GPU access (T4 → H100)
  • A safer place for untrusted / heavy code

Example prompts

  • “/modal”

Requirements

  • Python 3
  • Docker

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Quick Python eval
  2. GPU inference, A100, with deps pre-installed
  3. Test untrusted code Claude generated

What it can do on your machine

Read from SKILL.md and the folder at commit e9b2bd5. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).

    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 no API keys, tokens, secrets or passwords.

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

Context cost

Modal loads about 1.9k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 765 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 BlockRunAI/blockrun-mcp at commit e9b2bd5, republished under its MIT licence (© BlockRunAI). 765 words, ~1,889 tokens.

Download SKILL.mdSave it as .claude/skills/modal/SKILL.md (or your agent's skills folder).
name
modal
description
Use when the user needs to run isolated code remotely — a disposable container, optional GPU access (T4 → H100), or a safer place for untrusted / heavy code. Prefer local execution for normal repo work; use Modal sandboxes for isolation, hardware access, or one-shot heavy compute.
triggers
modal sandbox, remote python, sandbox execution, isolated code run, gpu sandbox, h100, a100, remote container, ephemeral container, run untrusted code

Modal Sandboxes

Disposable remote containers (with optional GPU) via Modal, paid per call in USDC. No Modal account, no GPU procurement.

Base only in wallet mode; fine on an API key. sol.blockrun.ai carries the /v1/modal/* routes but has no Modal backend configured, so every action — create, exec, status, terminate — answers 503. That reads as "the sandbox service is down" rather than "wrong chain", which is exactly the wrong conclusion to act on: retrying will not help. The tool checks the active chain first and says so. Switch with blockrun_wallet action:"chain" chain:"base". Prices below are Base prices and include its per-transaction fee.

READ THIS BEFORE SETTING timeout

timeout is the BILLED lifetime, charged upfront in full, and never refunded — not an idle timeout. Above 300s the price switches from a flat rate to per-hour billing for the entire duration you ask for, whether you use it or not. Terminating early refunds nothing.

That makes timeout the single most expensive field in this MCP:

what you ask forwhat you pay
{ timeout: 300 }$0.0110
{ timeout: 300, gpu: "A100" }$0.2010
{ timeout: 600, gpu: "A100" }$0.6677
{ timeout: 86400, gpu: "H100" }$192.0010

All four are live-verified quotes. A 24h H100 sandbox costs $192 upfront, non-refundable, even if your job finishes in a minute.

So: ask for the time you need, not a safe-looking ceiling. Need 20 minutes of H100? timeout: 1200 is $2.67, not $192. Keep timeout ≤ 300 and you stay on the flat rate entirely.

How to Call from MCP

ts
// 1. Create — timeout: 300 keeps you on the FLAT rate ($0.0110, or $0.2010 with A100).
//    Anything above 300 bills hourly for the full requested lifetime, no refund.
blockrun_modal({ path: "sandbox/create", body: {
  image: "python:3.11",
  gpu: "A100",
  timeout: 300,
  setup_commands: ["pip install torch transformers"]
}})
// returns { sandbox_id, ... }

// 2. Exec
blockrun_modal({ path: "sandbox/exec", body: {
  sandbox_id: "sb_abc...",
  command: ["python", "-c", "import torch; print(torch.cuda.get_device_name(0))"]
}})

// 3. Terminate
blockrun_modal({ path: "sandbox/terminate", body: { sandbox_id: "sb_abc..." } })

Endpoint Catalog

PathMethodBodyPrice
sandbox/createPOST{ image?, timeout?, cpu?, memory?, gpu?, setup_commands? }depends on timeout + gpu — see below
sandbox/execPOST{ sandbox_id, command: ["python","-c","..."], timeout? }$0.0020
sandbox/statusPOST{ sandbox_id }$0.0020
sandbox/terminatePOST{ sandbox_id }$0.0020
sandbox/create pricing is bimodal

timeout ≤ 300s — flat rate, charged once:

gpuprice
(none, CPU)$0.0110
T4$0.0510
L4$0.0810
A10G$0.1010
A100$0.2010
H100$0.4010

timeout > 300s — per-hour × the full requested lifetime, upfront, no refund:

gpuper hour1h24h (max)
(none, CPU)$0.10$0.1010$2.4010
T4$1.50$1.5010$36.0010
L4$2.00$2.0010$48.0010
A10G$2.50$2.5010$60.0010
A100$4.00$4.0010$96.0010
H100$8.00$8.0010$192.0010

Hours are exact, not rounded up — timeout: 1800 on A100 is 0.5h = $2.0010. Every figure above includes the $0.001 flat transaction fee. Max timeout is 86400 (24h).

One quirk worth knowing: timeout: 300 costs $0.0110 (flat) but timeout: 301 costs $0.0094 (CPU-hourly) — just past the cliff is briefly cheaper on CPU. It stops being cheaper at 360s.

Show full SKILL.md (361 more words)Show less

Field Reference

FieldDefaultNotes
imagepython:3.11Any public Docker image. nvidia/cuda:12-runtime if you bring GPU code.
timeout300BILLED lifetime in seconds — charged upfront for the full amount, never refunded. NOT idle eviction: you pay for what you ask for, not what you use. ≤300 = flat rate; >300 switches to per-hour billing (see the tables above). Max 86400 (24h). This is the field that turns a $0.01 sandbox into a $192 one.
cpu1CPU cores
memory1024Memory in MB
gpunoneT4 / L4 / A10G / A100 / H100 — those five only. Anything else is rejected: {"gpu":"A100-80GB"} returns HTTP 400 "Unsupported GPU type. Allowed: T4, L4, A10G, A100, H100". Drives the price hard — see the tables above.
setup_commands[]Shell commands run once during sandbox provisioning
command (exec)requiredArray form: ["python","-c","print(2+2)"]

Worked Examples

1. Quick Python eval
ts
const { structuredContent: sb } = await blockrun_modal({ path: "sandbox/create", body: {} })
await blockrun_modal({ path: "sandbox/exec", body: {
  sandbox_id: sb.sandbox_id,
  command: ["python", "-c", "import numpy; print(numpy.__version__)"]
}})
await blockrun_modal({ path: "sandbox/terminate", body: { sandbox_id: sb.sandbox_id } })

Cost: $0.0150 — create $0.0110 + exec $0.0020 + terminate $0.0020. Every call carries the $0.001 transaction fee, so three calls pay it three times; batch your work into one exec rather than several.

2. GPU inference, A100, with deps pre-installed
ts
blockrun_modal({ path: "sandbox/create", body: {
  image: "pytorch/pytorch:2.4.0-cuda12.1-cudnn9-runtime",
  gpu: "A100",
  timeout: 1200,
  memory: 16384,
  setup_commands: ["pip install --quiet transformers accelerate"]
}})

Then sandbox/exec with your inference command.

Cost: $1.3383 — create $1.3343 + exec $0.0020 + terminate $0.0020. timeout: 1200 is above the 300s flat tier, so the A100 bills hourly for the full 20 minutes you asked for: $4.00/h × (1200/3600) = $1.3333, + the $0.001 fee. It is charged upfront and never refunded — it does NOT auto-evict when idle, and terminating after 30 seconds still costs the full $1.3343. Ask for the time you actually need.

3. Test untrusted code Claude generated
ts
blockrun_modal({ path: "sandbox/exec", body: {
  sandbox_id,
  command: ["bash", "-c", "<the generated script>"],
  timeout: 60
}})

Output is captured. No risk to your local machine.

When NOT to Use Modal

  • Normal repo edits / dev work — use local tools, Modal adds latency and cost
  • Long-running services — sandboxes are ephemeral, not server hosts
  • Anything you'd run hundreds of times per minute — payment overhead dominates at high QPS

Notes

  • sandbox_id is returned by create and required by every other endpoint
  • exec is sync — blocks until command finishes or hits its timeout
  • terminate is cheap; call it to free the sandbox even if timeout would expire shortly
  • The free-tier nvidia/* LLM models in blockrun_chat are different infrastructure — Modal is for your arbitrary code

Reference

  • Endpoints: POST /v1/modal/sandbox/{create,exec,status,terminate}
  • Upstream: Modal

© BlockRunAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/modal of BlockRunAI/blockrun-mcp.

Open the folder on GitHubat commit e9b2bd5

Compare with similar skills

Modal 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Modal this skillBlockRunAI/blockrun-mcp392—~1.9kAutomated safety check: PassMIT
ModalK-Dense-AI/scientific-agent-skills48k1 repos~4.5kAutomated safety check: NotesApache-2.0
Remotion Interactivityremotion-dev/remotion62k5 repos~4.8kAutomated safety check: PassCustom licence
Imperative Modal APIlobehub/lobehub83k—~1.3kAutomated safety check: PassCustom licence
Remotiondavila7/claude-code-templates32k1 repos~1.6kAutomated safety check: PassMIT
Remotionnexu-io/open-design100k—~301Automated safety check: PassApache-2.0

Similar skills

  • 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

  • Remotion Interactivity

    remotion-dev/remotion

    Official

    Structure Remotion markup for interactivity. An agent skill from remotion-dev/remotion.

    62k GitHub starsUsed in 5 repos~4.8k tokens
    Media & CreativeAuto-check passed

  • Imperative Modal API

    lobehub/lobehub

    Shows how to build modals, dialogs and confirmations in LobeHub with the base-ui imperative API (createModal, confirmModal, ModalHost) instead of declarative Modal components.

    83k GitHub stars~1.3k tokensUpdated today
    Frontend & DesignAuto-check passed

  • Remotion

    davila7/claude-code-templates

    Best practices and comprehensive guide for Remotion - programmatic video creation in React with animations, compositions, and media handling

    32k GitHub starsUsed in 1 repo~1.6k tokens
    Media & CreativeAuto-check passed

  • Remotion

    nexu-io/open-design

    Programmatic video creation with React. An agent skill from nexu-io/open-design.

    100k GitHub stars~301 tokensUpdated today
    Media & CreativeAuto-check passed

  • Modal

    davila7/claude-code-templates

    Run Python code in the cloud with serverless containers, GPUs, and autoscaling.

    32k GitHub starsUsed in 8 repos~2.6k tokens
    Backend & APIsAuto-check passed

More from BlockRunAI/blockrun-mcp

All 17 skills in this repo

  • Signal To Trade Demo

    BlockRunAI/blockrun-mcp

    Prepare or run a polished BlockRun trading demo that discovers a current Polymarket market, combines live price, probability history, smart-money, and liquidity evidence into a balanced signal…

    392 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Blockrun

    BlockRunAI/blockrun-mcp

    Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key.

    392 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Blockrun Debug

    BlockRunAI/blockrun-mcp

    A skill your agent uses when the BlockRun MCP server (@blockrun/mcp) is installed but misbehaving — 'Failed to connect', spawn npx ENOENT, blockrun missing from claude mcp list, HTTP 402 /…

    392 GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Blockrun Setup

    BlockRunAI/blockrun-mcp

    A skill your agent uses when asked to install, add, configure, or set up the BlockRun MCP server (@blockrun/mcp) in Claude Code, Claude Desktop, Cursor, Windsurf, Codex CLI, Grok or another MCP…

    392 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Blockrun Upgrade

    BlockRunAI/blockrun-mcp

    A skill your agent uses when the BlockRun MCP server prints 'Update available', when asked to upgrade, update, or pin @blockrun/mcp, when a fix 'should be in the new version' but the client still…

    392 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Crypto Data

    BlockRunAI/blockrun-mcp

    A skill your agent uses for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, or raw JSON-RPC against a chain…

    392 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

Questions about Modal

What does Modal do?

A skill your agent uses when the user needs to run isolated code remotely — a disposable container, optional GPU access (T4 → H100), or a safer place for untrusted / heavy code. Modal is an agent skill from BlockRunAI/blockrun-mcp. Use when the user needs to run isolated code remotely — a disposable container, optional GPU access (T4 → H100), or a safer place for untrusted / heavy code.

When should I use Modal?

Modal fits situations like: the user needs to run isolated code remotely — a disposable container; optional GPU access (T4 → H100); A safer place for untrusted / heavy code.

How do I install Modal in Claude Code?

Run `npx skills add BlockRunAI/blockrun-mcp --skill modal -a claude-code`. Or copy the skill folder (skills/modal in BlockRunAI/blockrun-mcp) into .claude/skills/modal in your project. Claude Code loads it when a task matches its description.

How do I install Modal in Codex?

Run `npx skills add BlockRunAI/blockrun-mcp --skill modal -a codex`. Or copy the skill folder (skills/modal in BlockRunAI/blockrun-mcp) into .agents/skills/modal in your project. Codex loads it when a task matches its description.

Can I use Modal 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 BlockRunAI/blockrun-mcp --skill modal -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, .gemini/skills/modal, .github/skills/modal and .opencode/skills/modal in your project.

What does Modal need to run?

SKILL.md names no scripts, command-line tools or credentials: Modal is instructions for the agent only. Our summary lists: Python 3; Docker.

Does Modal access the network?

SKILL.md names 1 domain. As links in the text: modal.com. This is read from the text; nothing was executed.

Is Modal 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 use?

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

How many tokens does Modal use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Modal?

Skills that share tags, products or a category with Modal: Modal (K-Dense-AI/scientific-agent-skills, 48k stars), Remotion Interactivity (remotion-dev/remotion, 62k stars), Imperative Modal API (lobehub/lobehub, 83k stars) and Remotion (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Modal?

BlockRunAI (a GitHub organization) maintains it in BlockRunAI/blockrun-mcp, which has 392 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 8, 2026.

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