Vercel Sandbox Agent Skill

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

2k tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

39888

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/vercel-labs/agent-browser --skill vercel-sandbox

The instruction itself

13 sections, as written by the author

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 @agent-browser/sandbox @vercel/sandbox

The sandbox VM needs system dependencies for Chromium plus agent-browser itself. The @agent-browser/sandbox helpers install them by default for fresh sandboxes and use sandbox snapshots (below) for sub-second startup. Pass installSystemDependencies: false only when the sandbox image already provides Chromium's required libraries.

Core Pattern

import {
  createAgentBrowserSnapshot,
  runAgentBrowserCommand,
  withAgentBrowserSandbox,
  type VercelSandboxSession,
} from "@agent-browser/sandbox/vercel";

async function withBrowser<T>(
  fn: (sandbox: VercelSandboxSession) => Promise<T>,
): Promise<T> {
  return withAgentBrowserSandbox(fn);
}

Screenshot

The screenshot --json command saves to a file and returns the path. Read the file back as base64:

export async function screenshotUrl(url: string) {
  return withBrowser(async (sandbox) => {
    await runAgentBrowserCommand(sandbox, ["open", url]);

    const titleResult = await runAgentBrowserCommand<{ data?: { title?: string } }>(sandbox, [
      "get", "title",
    ]);
    const title = titleResult.json?.data?.title || url;

    const ssResult = await runAgentBrowserCommand<{ data?: { path?: string } }>(sandbox, [
      "screenshot",
    ]);
    const ssPath = ssResult.json?.data?.path;
    if (!ssPath) throw new Error("Screenshot did not return a file path.");
    const b64Result = await sandbox.runCommand("base64", ["-w", "0", ssPath]);
    const screenshot = (await b64Result.stdout()).trim();

    await runAgentBrowserCommand(sandbox, ["close"], { json: false });

    return { title, screenshot };
  });
}

Accessibility Snapshot

export async function snapshotUrl(url: string) {
  return withBrowser(async (sandbox) => {
    await runAgentBrowserCommand(sandbox, ["open", url]);

    const titleResult = await runAgentBrowserCommand<{ data?: { title?: string } }>(sandbox, [
      "get", "title",
    ]);
    const title = titleResult.json?.data?.title || url;

    const snapResult = await runAgentBrowserCommand(sandbox, ["snapshot", "-i", "-c"], {
      json: false,
    });

    await runAgentBrowserCommand(sandbox, ["close"], { json: false });

    return { title, snapshot: snapResult.stdout };
  });
}

Multi-Step Workflows

The sandbox persists between commands, so you can run full automation sequences:

export async function fillAndSubmitForm(url: string, data: Record<string, string>) {
  return withBrowser(async (sandbox) => {
    await runAgentBrowserCommand(sandbox, ["open", url]);

    const snapResult = await runAgentBrowserCommand(sandbox, ["snapshot", "-i"], {
      json: false,
    });
    const snapshot = snapResult.stdout;
    // Parse snapshot to find element refs...

    for (const [ref, value] of Object.entries(data)) {
      await runAgentBrowserCommand(sandbox, ["fill", ref, value]);
    }

    await runAgentBrowserCommand(sandbox, ["click", "@e5"]);
    await runAgentBrowserCommand(sandbox, ["wait", "--load", "networkidle"]);

    const ssResult = await runAgentBrowserCommand<{ data?: { path?: string } }>(sandbox, [
      "screenshot",
    ]);
    const ssPath = ssResult.json?.data?.path;
    if (!ssPath) throw new Error("Screenshot did not return a file path.");
    const b64Result = await sandbox.runCommand("base64", ["-w", "0", ssPath]);
    const screenshot = (await b64Result.stdout()).trim();

    await runAgentBrowserCommand(sandbox, ["close"], { json: false });

    return { screenshot };
  });
}

Sandbox Snapshots (Fast Startup)

A sandbox snapshot is a saved VM image of a Vercel Sandbox with system dependencies + agent-browser + Chromium already installed. Think of it like a Docker image: instead of installing dependencies from scratch every time, the sandbox boots from the pre-built image.

This is unrelated to agent-browser's *accessibility snapshot* feature (agent-browser snapshot), which dumps a page's accessibility tree. A sandbox snapshot is a Vercel infrastructure concept for fast VM startup.

Without a sandbox snapshot, each run installs system deps + agent-browser + Chromium (~30s). With one, startup is sub-second.

Creating a sandbox snapshot

The snapshot must include system dependencies (via dnf), agent-browser, and Chromium:

const snapshotId = await createAgentBrowserSnapshot();

Run this once, then set the environment variable:

AGENT_BROWSER_SNAPSHOT_ID=snap_xxxxxxxxxxxx

A helper script is available in the demo app:

npx tsx examples/environments/scripts/create-snapshot.ts

Recommended for any production deployment using the Sandbox pattern.

Authentication

On Vercel deployments, the Sandbox SDK authenticates automatically via OIDC. For local development or explicit control, set:

VERCEL_TOKEN=<personal-access-token>
VERCEL_TEAM_ID=<team-id>
VERCEL_PROJECT_ID=<project-id>

These are spread into Sandbox.create() calls. When absent, the SDK falls back to VERCEL_OIDC_TOKEN (automatic on Vercel).

Scheduled Workflows (Cron)

Combine with Vercel Cron Jobs for recurring browser tasks:

// app/api/cron/route.ts  (or equivalent in your framework)
export async function GET() {
  const result = await withBrowser(async (sandbox) => {
    await sandbox.runCommand("agent-browser", ["open", "https://example.com/pricing"]);
    const snap = await sandbox.runCommand("agent-browser", ["snapshot", "-i", "-c"]);
    await sandbox.runCommand("agent-browser", ["close"]);
    return await snap.stdout();
  });

  // Process results, send alerts, store data...
  return Response.json({ ok: true, snapshot: result });
}

// vercel.json
{ "crons": [{ "path": "/api/cron", "schedule": "0 9 * * *" }] }

Environment Variables

| Variable | Required | Description |

|---|---|---|

| AGENT_BROWSER_SNAPSHOT_ID | No (but recommended) | Pre-built sandbox snapshot ID for sub-second startup (see above) |

| VERCEL_TOKEN | No | Vercel personal access token (for local dev; OIDC is automatic on Vercel) |

| VERCEL_TEAM_ID | No | Vercel team ID (for local dev) |

| VERCEL_PROJECT_ID | No | Vercel project ID (for local dev) |

Framework Examples

The pattern works identically across frameworks. The only difference is where you put the server-side code:

| Framework | Server code location |

|---|---|

| Next.js | Server actions, API routes, route handlers |

| SvelteKit | +page.server.ts, +server.ts |

| Nuxt | server/api/, server/routes/ |

| Remix | loader, action functions |

| Astro | .astro frontmatter, API routes |

Example

See examples/environments/ in the agent-browser repo for a working app with the Vercel Sandbox pattern, including a sandbox snapshot creation script, streaming progress UI, and rate limiting.

Other skills for the same job

different authors, same section of the catalogue

Python Executor

by ComeOnOliver

×1

Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D models, automation, pandas, matplotlib

Upgrade browser versions (Chrome or Firefox) in the Flutter Web Engine and/or Framework tests. Use when asked to roll or upgrade Chrome or Firefox to a newer version.

Migrate PowerToys module UI tests from the legacy WinAppDriver/Selenium harness (Microsoft.PowerToys.UITest) to the new winappcli-based harness (Microsoft.PowerToys.UITest.Next). Use when asked to port/convert/rewrite/modernize a module's UI tests to the .Next framework, create a new [Module].UITests.Next project alongside existing legacy tests, or stand up brand-new winappcli UI tests for a module that has none by reading its human test sign-off markdown. Covers the API mapping (By/Element/Session/UITestBase, KeyboardHelper/MouseHelper/ClipboardHelper), project/csproj scaffolding, naming rules, common PowerToys test recipes (toggle a module, read an activation shortcut, fire a global hotkey, inspect the clipboard, discover overlay/editor windows), build/run validation, and CI-stability hardening for fewer CI iterations. Keywords: UI test, UITests, UITestAutomation.Next, winappcli, WinAppDriver, Selenium, migrate, port, modernize, .Next, MSTest, CI stability, flaky test, stabilize on CI.

32k tokens

Open Source

by browser-use

> Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browser_use, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle hooks, MCP server setup, or monitoring/observability with Laminar or OpenLIT. Also trigger for questions about browser-use installation, prompting strategies, or sensitive data handling. Do NOT use this for Cloud API/SDK usage or pricing — use the cloud skill instead. Do NOT use this for directly automating a browser via CLI commands — use the browser-use skill instead.

Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase resources, call Browserbase Functions, browse or scaffold Browserbase templates, fetch or search web content, diagnose browse setup, find or install a skill for a website task, discover site-specific Browse.sh skills, or install/refresh this browse skill.

Development workflows for the playwright-cli repository. Use when the user asks about rolling dependencies, releasing, or other repo maintenance tasks.

Turn a website's observable HTTP traffic into a best-effort OpenAPI 3.1 spec by analyzing a `browser-trace` capture. Use when the user wants to discover/extract API endpoints from a browser session, build an OpenAPI doc from network traffic, or document a third-party site's XHR/fetch surface for client integration.

26k tokens scripts

How to use it

Copy the folder

Take vercel-labs/vercel-sandbox from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference npx, pnpm. Without those the skill loads but fails at the first command.