Official agent skill

Vercel Sandbox Browser

by vercel-labs in vercel-labs/agent-browser

Runs agent-browser with headless Chrome inside Vercel Sandbox microVMs so Vercel-deployed apps can automate a browser without binary size limits.

OfficialApache-2.0Auto-check passedProductivity & Automation

Install Vercel Sandbox Browser

skills CLI

$ npx skills add vercel-labs/agent-browser --skill vercel-sandbox -a claude-code

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

GitHub CLI

$ gh skill install vercel-labs/agent-browser vercel-sandbox --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/vercel-labs/agent-browser.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill-data/vercel-sandbox .claude/skills/vercel-sandbox && 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/

Paste into Claude Code

Install the "vercel-sandbox" agent skill from https://github.com/vercel-labs/agent-browser/tree/main/skill-data/vercel-sandbox into .claude/skills/vercel-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-sandbox", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/vercel-labs/agent-browser/tree/main/skill-data/vercel-sandbox

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add vercel-labs/agent-browser --skill vercel-sandbox -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install vercel-labs/agent-browser vercel-sandbox --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vercel-labs/agent-browser.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skill-data/vercel-sandbox .agents/skills/vercel-sandbox && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "vercel-sandbox" agent skill from https://github.com/vercel-labs/agent-browser/tree/main/skill-data/vercel-sandbox into .agents/skills/vercel-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-sandbox", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add vercel-labs/agent-browser --skill vercel-sandbox -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install vercel-labs/agent-browser vercel-sandbox --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vercel-labs/agent-browser.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skill-data/vercel-sandbox .cursor/skills/vercel-sandbox && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "vercel-sandbox" agent skill from https://github.com/vercel-labs/agent-browser/tree/main/skill-data/vercel-sandbox into .cursor/skills/vercel-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-sandbox", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/vercel-labs/agent-browser.git --path skill-data/vercel-sandbox

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add vercel-labs/agent-browser --skill vercel-sandbox -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install vercel-labs/agent-browser vercel-sandbox --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vercel-labs/agent-browser.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skill-data/vercel-sandbox .gemini/skills/vercel-sandbox && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "vercel-sandbox" agent skill from https://github.com/vercel-labs/agent-browser/tree/main/skill-data/vercel-sandbox into .gemini/skills/vercel-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-sandbox", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install vercel-labs/agent-browser vercel-sandbox

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add vercel-labs/agent-browser --skill vercel-sandbox -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/vercel-labs/agent-browser.git skills-src && mkdir -p .github/skills && cp -r skills-src/skill-data/vercel-sandbox .github/skills/vercel-sandbox && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "vercel-sandbox" agent skill from https://github.com/vercel-labs/agent-browser/tree/main/skill-data/vercel-sandbox into .github/skills/vercel-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-sandbox", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add vercel-labs/agent-browser --skill vercel-sandbox -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install vercel-labs/agent-browser vercel-sandbox --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vercel-labs/agent-browser.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skill-data/vercel-sandbox .opencode/skills/vercel-sandbox && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "vercel-sandbox" agent skill from https://github.com/vercel-labs/agent-browser/tree/main/skill-data/vercel-sandbox into .opencode/skills/vercel-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-sandbox", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: vercel-sandbox
GitHub stars: 44k
Token cost: ~2k tokens
SKILL.md length: 416 words
Files: 1
Skills in repo: 10
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Runs agent-browser with headless Chrome inside Vercel Sandbox microVMs so Vercel-deployed apps can automate a browser without binary size limits.

Adding browser automation to an app deployed on Vercel
SKILL.md covers Dependencies, Core Pattern, Screenshot and Accessibility Snapshot, plus 7 more sections
Calls pnpm and npx; needs VERCEL_TOKEN and VERCEL_OIDC_TOKEN
Running headless Chrome where binary size limits block it

What it does

This skill shows how to run the agent-browser CLI and headless Chrome inside ephemeral Vercel Sandbox microVMs, so an app deployed on Vercel can drive a browser without hitting binary size limits. A Linux VM starts on demand, runs the browser commands, then shuts down. It works with any framework deployed on Vercel, such as Next.js, SvelteKit, Nuxt, Remix or Astro.

The pattern uses the @agent-browser/sandbox and @vercel/sandbox packages, installed with pnpm, and TypeScript helpers such as createAgentBrowserSnapshot and runAgentBrowserCommand. Examples cover screenshots saved to a file and read back as base64, accessibility-tree snapshots, and multi-step flows such as filling and submitting a form in a sandbox that stays alive between commands. A sandbox snapshot, a saved VM image with system dependencies, agent-browser and Chromium preinstalled, cuts startup from about 30 seconds to under a second, and its ID goes in the AGENT_BROWSER_SNAPSHOT_ID environment variable.

When your agent uses it

Adding browser automation to an app deployed on Vercel
Running headless Chrome where binary size limits block it
Keeping a browser session alive across several commands
Needing an isolated, throwaway browser environment per task

Example prompts

“Add a route to my Next.js app that takes a screenshot of any URL using Vercel Sandbox.”
“Fill and submit the signup form on this site from a Vercel Sandbox and return the result.”
“Create a sandbox snapshot so the browser starts in under a second.”

Requirements

A Vercel project with access to Vercel Sandbox
The @agent-browser/sandbox and @vercel/sandbox packages

What it can do on your machine

Read from SKILL.md and the folder at commit 0207911. 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:
- pnpm
- npx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm and npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- VERCEL_TOKEN
- VERCEL_OIDC_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vercel Sandbox Browser loads about 2k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 416 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~140
When it runs · the whole SKILL.md, loaded when a task matches: ~2k

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 vercel-labs/agent-browser at commit 0207911, republished under its Apache-2.0 licence (© vercel-labs). 416 words, ~1,972 tokens.

Download SKILL.mdSave it as .claude/skills/vercel-sandbox/SKILL.md (or your agent's skills folder).

name: vercel-sandbox
description: 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.

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

bash

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>,
  postSubmitWaitArgs: 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"]);
    // Pass an app-specific wait, such as ["--url", "**/checkout/complete"],
    // ["--text", "Thanks"], or ["#confirmation"].
    await runAgentBrowserCommand(sandbox, ["wait", ...postSubmitWaitArgs]);

    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:

bash

AGENT_BROWSER_SNAPSHOT_ID=snap_xxxxxxxxxxxx

A helper script is available in the demo app:

bash

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

Recommended for any production deployment using the Sandbox pattern.

Show full SKILL.md (167 more words)Show less

Authentication

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

bash

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 });
}

json

// 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.

Files

Just SKILL.md in skill-data/vercel-sandbox of vercel-labs/agent-browser.

Open the folder on GitHubat commit 0207911

Compare with similar skills

Vercel Sandbox Browser 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.

Vercel Sandbox Browser compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Vercel Sandbox Browser this skillvercel-labs/agent-browser	44k	—	~2k	Automated safety check: Pass	Apache-2.0	yesterday
Vercel Optimize Auditvercel-labs/agent-skills	32k	8 repos	~4.3k	Automated safety check: Pass	None	1 mo ago
Cloudflare Workers Frameworkssecondsky/claude-skills	227	—	~1.4k	Automated safety check: Pass	MIT	11 days ago
Sanity Best Practicesrobotostudio/turbo-start-sanity	183	—	~940	Automated safety check: Pass	MIT	4 days ago
Sanity Best Practicessanity-io/agent-toolkit	188	—	~1.3k	Automated safety check: Pass	MIT	4 days ago
Framework Adaptershashgraph-online/awesome-codex-plugins	1.3k	—	~2.9k	Automated safety check: Notes	Apache-2.0	today

Similar skills

Vercel Optimize Audit
vercel-labs/agent-skills
Official
Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.
32k GitHub starsUsed in 8 repos~4.3k tokens
DevOps & CloudAuto-check passed
Cloudflare Workers Frameworks
secondsky/claude-skills
Framework integration for Cloudflare Workers. An agent skill from secondsky/claude-skills.
227 GitHub stars~1.4k tokensUpdated 11 days ago
Frontend & DesignAuto-check passed
Sanity Best Practices
robotostudio/turbo-start-sanity
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, Blueprints, and…
183 GitHub stars~940 tokensUpdated 4 days ago
Frontend & DesignAuto-check passed
Sanity Best Practices
sanity-io/agent-toolkit
Official
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints…
188 GitHub stars~1.3k tokensUpdated 4 days ago
Backend & APIsAuto-check passed
Framework Adapters
hashgraph-online/awesome-codex-plugins
Official @dodopayments/ framework adapters that mount Checkout, CustomerPortal, and Webhooks route handlers.
1.3k GitHub stars~2.9k tokensUpdated today
Backend & APIsAuto-check: notes
Edgeone Makers Frameworks
TencentEdgeOne/edgeone-makers-tools
Web framework support matrix for EdgeOne Makers — which platform adapter each full-stack framework needs, where it plugs in, the build output directory, the preview asset-prefix option, the 404…
1.9k GitHub stars~2.5k tokensUpdated yesterday
Frontend & DesignAuto-check passed

Questions about Vercel Sandbox Browser

What does Vercel Sandbox Browser do?

Runs agent-browser with headless Chrome inside Vercel Sandbox microVMs so Vercel-deployed apps can automate a browser without binary size limits. This skill shows how to run the agent-browser CLI and headless Chrome inside ephemeral Vercel Sandbox microVMs, so an app deployed on Vercel can drive a browser without hitting binary size limits. A Linux VM starts on demand, runs the browser commands, then shuts down.

When should I use Vercel Sandbox Browser?

Vercel Sandbox Browser fits situations like: adding browser automation to an app deployed on Vercel; running headless Chrome where binary size limits block it; keeping a browser session alive across several commands; needing an isolated, throwaway browser environment per task.

How do I install Vercel Sandbox Browser in Claude Code?

Run `npx skills add vercel-labs/agent-browser --skill vercel-sandbox -a claude-code`. Or copy the skill folder (skill-data/vercel-sandbox in vercel-labs/agent-browser) into .claude/skills/vercel-sandbox in your project. Claude Code loads it when a task matches its description.

How do I install Vercel Sandbox Browser in Codex?

Run `npx skills add vercel-labs/agent-browser --skill vercel-sandbox -a codex`. Or copy the skill folder (skill-data/vercel-sandbox in vercel-labs/agent-browser) into .agents/skills/vercel-sandbox in your project. Codex loads it when a task matches its description.

Can I use Vercel Sandbox Browser 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 vercel-labs/agent-browser --skill vercel-sandbox -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vercel-sandbox, .gemini/skills/vercel-sandbox, .github/skills/vercel-sandbox and .opencode/skills/vercel-sandbox in your project.

What does Vercel Sandbox Browser need to run?

Going by SKILL.md and its folder, Vercel Sandbox Browser needs the command-line tools its instructions call (pnpm and npx) and credentials named VERCEL_TOKEN and VERCEL_OIDC_TOKEN. Our summary lists: A Vercel project with access to Vercel Sandbox; The @agent-browser/sandbox and @vercel/sandbox packages.

Does Vercel Sandbox Browser access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Vercel Sandbox Browser 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 Vercel Sandbox Browser use?

Vercel Sandbox Browser is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vercel Sandbox Browser use?

About 2k tokens (SKILL.md is roughly 7.9k 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 Vercel Sandbox Browser?

Skills that share tags, products or a category with Vercel Sandbox Browser: Vercel Optimize Audit (vercel-labs/agent-skills, 32k stars), Cloudflare Workers Frameworks (secondsky/claude-skills, 227 stars), Sanity Best Practices (robotostudio/turbo-start-sanity, 183 stars) and Sanity Best Practices (sanity-io/agent-toolkit, 188 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vercel Sandbox Browser?

vercel-labs (a GitHub organization, an official publisher) maintains it in vercel-labs/agent-browser, which has 43,705 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 8, 2026.

Source: vercel-labs/agent-browser on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Vercel Sandbox Browser

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Browser Automation with Vercel Sandbox

Dependencies

Core Pattern

Screenshot

Accessibility Snapshot

Multi-Step Workflows

Sandbox Snapshots (Fast Startup)

Creating a sandbox snapshot

Authentication

Scheduled Workflows (Cron)

Environment Variables

Framework Examples

Example

Files

Compare with similar skills

Similar skills

More from vercel-labs/agent-browser

Related

Questions about Vercel Sandbox Browser