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.
npx skills add oxylabs/agent-skills --skill headless-browsergit clone --depth 1 https://github.com/oxylabs/agent-skillsWrote 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.
[](https://agentmods.dev/skills/oxylabs/agent-skills/headless-browser)<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>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.
| Model | Per session | Once 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 |
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.
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();
})();
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.
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.
- 7d ago First seen · 149 lines · 72 tokens per session scan A bfb1584f4419
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.
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…
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.
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.
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.
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".
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"…