headless-browser

headless-browser is a skill for Claude Code from oxylabs/agent-skills. It costs 72 tokens per session (1,511 once invoked), scanned A, original, MIT.

A remote browser service that connects to Chrome or Firefox through CDP, a standard way for automation tools to control a browser remotely.

In plain words
What is it for?
Use it with Playwright or Puppeteer to automate protected websites, load JavaScript pages, take screenshots, create PDFs, or run browser sessions in selected regions.
Why use it?
It lets browser automation run on remote machines with anti-detection measures, proxies, CAPTCHA handling, and location targeting built in.

Skill for Claude Code

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

Part of the agent-skills plugin — 5 skills shipped together

Good fit Use it with Playwright or Puppeteer to automate protected websites, load JavaScript pages, take screenshots, create PDFs, or run browser sessions in selected regions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oxylabs/agent-skills/headless-browser
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 oxylabs/agent-skills --skill headless-browser
Clone the repo
git clone --depth 1 https://github.com/oxylabs/agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 5 skills.

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 headless-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/oxylabs/agent-skills/headless-browser.svg)](https://agentmods.dev/skills/oxylabs/agent-skills/headless-browser)
Your own site
<a href="https://agentmods.dev/skills/oxylabs/agent-skills/headless-browser"><img src="https://agentmods.dev/badge/skills/oxylabs/agent-skills/headless-browser.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,511 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 $0.00072 $0.01511
Opus 5 $0.00036 $0.00756
Sonnet 5 $0.00014 $0.00302
Haiku 4.5 $0.00007 $0.00151

Measured 7d ago against content hash bfb1584f4419, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

headless-browser 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.

skills/headless-browser/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oxylabs Headless Browser

Remote headless browser service with built-in anti-detection and proxy integration. Chrome supports Playwright, Puppeteer, and any CDP-compatible library. Firefox is legacy and uses Playwright's Firefox connection API.

Environment Variables

Prefer OXY_UNBLOCKER_USERNAME and OXY_UNBLOCKER_PASSWORD for Headless Browser credentials. OXY_HB_USERNAME and OXY_HB_PASSWORD are supported aliases in older setups.

Connection URLs

Browser Global endpoint US endpoint
Chrome wss://USERNAME:[email protected] wss://USERNAME:[email protected]
Firefox (legacy) wss://USERNAME:[email protected] wss://USERNAME:[email protected]

Browser Types

Type Best For Notes
Chrome High performance, dedicated servers, residential proxies Use chromium.connect_over_cdp / connectOverCDP
Firefox (legacy) Alternative engine for targets that perform better outside Chrome Use firefox.connect; supported Playwright versions are 1.51 and 1.56 via ?o_pw=1.56

Quick Start

Playwright (Python):

from playwright.sync_api import sync_playwright
import os

username = os.environ.get("OXY_UNBLOCKER_USERNAME") or os.environ["OXY_HB_USERNAME"]
password = os.environ.get("OXY_UNBLOCKER_PASSWORD") or os.environ["OXY_HB_PASSWORD"]
endpoint = "ubc.oxylabs.io"

with sync_playwright() as p:
    browser = p.chromium.connect_over_cdp(
        f"wss://{username}:{password}@{endpoint}"
    )
    page = browser.new_page()
    page.goto("https://example.com")
    print(page.content())
    browser.close()

Playwright (JavaScript):

const { chromium } = require("playwright");

const username = process.env.OXY_UNBLOCKER_USERNAME || process.env.OXY_HB_USERNAME;
const password = process.env.OXY_UNBLOCKER_PASSWORD || process.env.OXY_HB_PASSWORD;
const endpoint = "ubc.oxylabs.io";

(async () => {
  const browser = await chromium.connectOverCDP(
    `wss://${username}:${password}@${endpoint}`
  );
  const page = await browser.newPage();
  await page.goto("https://example.com");
  console.log(await page.content());
  await browser.close();
})();

Read the full file on GitHub · 149 lines

Files

What ships with it

1 file 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. 7d ago First seen · 149 lines · 72 tokens per session scan A bfb1584f4419

Subscribe to this mod's changes

headless-browser is a skill published in the GitHub repository oxylabs/agent-skills (871 stars, last pushed 16d ago), licensed MIT. It adds 72 tokens to every session and 1,511 once invoked, about $0.0004 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

safari-extension-control-workflow

Guide macOS Safari integration decisions across Safari Web Extensions, Safari Web Inspector Extensions, Safari App Extensions, SafariServices APIs, content blockers, extension messaging, and app-to-Safari control surfaces. Use when the user wants a Mac app to extend, message, open, inspect, debug, or coordinate with…

gaelic-ghost/socket · 91 tokens

safari-mcp-workflow

Inspect a scoped live site in Safari through Safari Technology Preview's local MCP server. Use for Safari-specific DOM, console, network, screenshot, accessibility, performance, interaction, responsive, or print-media evidence.

gaelic-ghost/socket · 48 tokens

nexus-browser-fleet

Headless browser fleet orchestration and management. Use when you need to coordinate multiple headless browser instances for automated web auditing, scraping, or testing at scale using tools like Pinchtab. Detects and corrects unstable fleets that fail audit coverage.

Shuwanito/SkillsMP · 56 tokens

add-tavily-tool

Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.

nanocoai/nanoclaw · 41 tokens

broken-link-checker

Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".

nowork-studio/notfair-plugin · 72 tokens

dev-browser

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…

code-yeongyu/oh-my-openagent · 84 tokens