vercel-sandbox

vercel-sandbox is a skill for Claude Code from build-with-dhiraj/ai-workflow-framework-portability-kit. It costs 46 tokens per session (3,071 once invoked), scanned B, original, MIT.

A Vercel service that runs untrusted or generated code inside short-lived isolated virtual machines. It can also run browser automation with a headless Chrome browser, which operates without displaying a normal browser window.

In plain words
What is it for?
Use it to execute generated code safely, run experiments, and perform browser automation inside an isolated Linux environment. It supports applications built with several web frameworks.
Why use it?
It helps keep user-generated or AI-generated code separate from the main application, reducing the risk that experiments or browser tasks affect the host system.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vercel-plugin plugin — 47 skills, 6 commands, 3 agents, 1 MCP server shipped together

Good fit Use it to execute generated code safely, run experiments, and perform browser automation inside an isolated Linux environment. It supports applications built with several web frameworks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/build-with-dhiraj/ai-workflow-framework-portability-kit/vercel-sandbox
Install

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.

Any agent
npx skills add build-with-dhiraj/ai-workflow-framework-portability-kit --skill vercel-sandbox
Clone the repo
git clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kit

Made for: Claude Code.

Or install vercel-plugin, the plugin that ships this one along with the rest of its 47 skills, 6 commands, 3 agents, 1 MCP server.

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 vercel-sandbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/vercel-sandbox/github.svg)](https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/vercel-sandbox)
Your own site
<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/vercel-sandbox"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/vercel-sandbox/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 vercel-sandbox

Your own site · 80×15
<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/vercel-sandbox"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/vercel-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,071 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00046 $0.03071
Opus 5.5 $0.00018 $0.01228
Sonnet 5.5 $0.00009 $0.00614
Haiku 4.5 $0.00005 $0.00307

Measured 1mo ago against content hash 8a80453de690, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

vercel-sandbox scanned grade B with 2 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 1mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`sudo dnf clean all 2>&1 && sudo dnf install -y --skip-broken ${CHROMIUM_SYSTEM_DEPS.join(" ")} 2>&1 && sudo ldconfig 2>&1`,

Runs shell commandslowCapability

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

pattern: 'child_process.*exec\(|execSync\(|spawn\(.*\{.*shell:\s*true'
Plugins/vercel-marketplace-source/skills/vercel-sandbox/SKILL.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with Vercel Sandbox

Run agent-browser + headless Chrome inside ephemeral Vercel Sandbox microVMs. A Linux VM spins up on demand, executes browser commands, and shuts down. Works with any Vercel-deployed framework (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.).

Dependencies

pnpm add @vercel/sandbox

The sandbox VM needs system dependencies for Chromium plus agent-browser itself. Use sandbox snapshots (below) to pre-install everything for sub-second startup.

Core Pattern

import { Sandbox } from "@vercel/sandbox";

// System libraries required by Chromium on the sandbox VM (Amazon Linux / dnf)
const CHROMIUM_SYSTEM_DEPS = [
  "nss", "nspr", "libxkbcommon", "atk", "at-spi2-atk", "at-spi2-core",
  "libXcomposite", "libXdamage", "libXrandr", "libXfixes", "libXcursor",
  "libXi", "libXtst", "libXScrnSaver", "libXext", "mesa-libgbm", "libdrm",
  "mesa-libGL", "mesa-libEGL", "cups-libs", "alsa-lib", "pango", "cairo",
  "gtk3", "dbus-libs",
];

function getSandboxCredentials() {
  if (
    process.env.VERCEL_TOKEN &&
    process.env.VERCEL_TEAM_ID &&
    process.env.VERCEL_PROJECT_ID
  ) {
    return {
      token: process.env.VERCEL_TOKEN,
      teamId: process.env.VERCEL_TEAM_ID,
      projectId: process.env.VERCEL_PROJECT_ID,
    };
  }
  return {};
}

async function withBrowser<T>(
  fn: (sandbox: InstanceType<typeof Sandbox>) => Promise<T>,
): Promise<T> {
  const snapshotId = process.env.AGENT_BROWSER_SNAPSHOT_ID;
  const credentials = getSandboxCredentials();

  const sandbox = snapshotId
    ? await Sandbox.create({
        ...credentials,
        source: { type: "snapshot", snapshotId },
        timeout: 120_000,
      })
    : await Sandbox.create({ ...credentials, runtime: "node24", timeout: 120_000 });

  if (!snapshotId) {
    await sandbox.runCommand("sh", [
      "-c",
      `sudo dnf clean all 2>&1 && sudo dnf install -y --skip-broken ${CHROMIUM_SYSTEM_DEPS.join(" ")} 2>&1 && sudo ldconfig 2>&1`,
    ]);
    await sandbox.runCommand("npm", ["install", "-g", "agent-browser"]);
    await sandbox.runCommand("npx", ["agent-browser", "install"]);
  }

  try {
    return await fn(sandbox);
  } finally {
    await sandbox.stop();
  }
}

Read the full file on GitHub · 370 lines

Files

What ships with it

2 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.

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. 1mo ago First seen · 370 lines · 46 tokens per session scan B 8a80453de690

Subscribe to this mod's changes

vercel-sandbox is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 20d ago), licensed MIT. It adds 46 tokens to every session and 3,071 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.

Related

Other skills, from other repositories

transformers-js

Run Hugging Face models in JavaScript or TypeScript with Transformers.js, WebGPU, or WASM across browser, Node.js, Bun, and Deno. Use for client-side or JS-runtime inference, not Python training.

waybarrios/opencode-power-pack · 50 tokens

unblock

Use whenever you need to read a web page, URL, article, documentation page, search result, product page or any live website content. Fetches through UnblockingAPI (unblockfetch, findtemplates), letting the API pick a plain fetch or a real browser per site, and returning structured JSON when a template covers the site.

unblockingapi/mcp · 70 tokens

build-app

Use when writing code that calls UnblockingAPI, or code that must fetch or scrape web pages from an app, script, backend, scheduled job or integration and UnblockingAPI is the chosen fetcher. Covers the REST API (POST /unblock), keeping the key server-side, timeouts and background jobs, concurrency, retries, credits…

unblockingapi/mcp · 76 tokens

templates

Use when code needs structured data (JSON fields) from a website through UnblockingAPI, for example search results, listings, products, prices or company records, or when the user asks about UnblockingAPI templates. Covers finding a published template for a URL, its output shape, calling it from an app, pinning…

unblockingapi/mcp · 80 tokens

app-recipes

Use when building a rank tracker (Google positions for keywords and domains), a price monitor (product prices and alerts) or a listings aggregator (properties, jobs, cars or products from several sites in one place) on UnblockingAPI, or a similar app that fetches web pages on a schedule and stores what changed.

unblockingapi/mcp · 68 tokens

browser-app-delivery

Deliver a runnable local browser app so the user can operate it on the first handoff. This delivery skill does not choose whether a requested local system should be a browser app. On a current turn that explicitly says to implement a brand-new browser project now, load bundled:greenfield-project-scaffolding before…

asgeirtj/system_prompts_leaks · 332 tokens