vercel-sandbox

vercel-sandbox is a skill for Claude Code, Codex from vercel-labs/agent-browser. It costs 126 tokens per session (1,830 once invoked), scanned A, original, Apache-2.0.

A way to run browser automation inside temporary Vercel Sandbox virtual machines. Vercel is a platform for deploying web applications, and the sandbox provides a remote Linux environment with Chrome.

In plain words
What is it for?
Opening and testing Vercel-deployed apps, running Chrome-based automation, and capturing screenshots from sandbox sessions.
Why use it?
It gives deployed web apps a separate place to run browser tasks when local browser binaries or system libraries are inconvenient. Sessions can be created when needed and shut down afterward.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Good fit Opening and testing Vercel-deployed apps, running Chrome-based automation, and capturing screenshots from…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vercel-labs/agent-browser/vercel-sandbox
About the project

agent-browser is a command-line tool that lets AI agents control web browsers for tasks such as clicking, navigation, and screenshots. Developers use it to automate browser interactions from agent workflows.

vercel-labs/agent-browser · 42,018 stars · on GitHub · agent-browser.dev

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 vercel-labs/agent-browser --skill vercel-sandbox
Clone the repo
git clone --depth 1 https://github.com/vercel-labs/agent-browser

Made for: Claude Code, Codex.

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/vercel-labs/agent-browser/vercel-sandbox.svg)](https://agentmods.dev/skills/vercel-labs/agent-browser/vercel-sandbox)
Your own site
<a href="https://agentmods.dev/skills/vercel-labs/agent-browser/vercel-sandbox"><img src="https://agentmods.dev/badge/skills/vercel-labs/agent-browser/vercel-sandbox.svg" alt="Measured on agentmods" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,830 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00126 $0.01830
Opus 5 $0.00063 $0.00915
Sonnet 5 $0.00025 $0.00366
Haiku 4.5 $0.00013 $0.00183

Measured 7d ago against content hash 20f4041c0981, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

vercel-sandbox 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 7d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

skill-data/vercel-sandbox/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 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 @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

Read the full file on GitHub · 214 lines

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. 7d ago First seen · 214 lines · 126 tokens per session scan A 20f4041c0981

Subscribe to this mod's changes

vercel-sandbox is a skill published in the GitHub repository vercel-labs/agent-browser (42,018 stars, last pushed today), licensed Apache-2.0. It adds 126 tokens to every session and 1,830 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

lovable

Lovable MCP tool usage — deploy projects, message agent, test with agent-browser. Minimize credits by delegating to local repo.

x-cmd/x-cmd · 30 tokens

agent-browser

Browser automation via Chrome/Chromium CDP — open, snapshot, click, screenshot. For testing web apps, mobile layouts, and automated interactions without Playwright/Puppeteer.

x-cmd/x-cmd · 39 tokens

cloudflare-browser-rendering

Cloudflare Browser Rendering with Puppeteer/Playwright. Use for screenshots, PDFs, web scraping, or encountering rendering errors, timeout issues, memory exceeded.

secondsky/claude-skills · 37 tokens

functions

Deploy serverless browser automation as cloud functions using Browserbase. Use when the user wants to deploy browser automation to run on a schedule or cron, create a webhook endpoint for browser tasks, run automation in the cloud instead of locally, or asks about Browserbase Functions.

browserbase/skills · 55 tokens

wterm

Web terminal server: manage the wterm-server daemon for browser-based shell access (local or remote via Tailscale). This skill should be used when checking wterm status, listing or creating terminal sessions, killing sessions, or managing the wterm LaunchAgent. Trigger on: wterm, web terminal, remote terminal, remote…

tdimino/claude-code-minoan · 76 tokens