browser-stealth

browser-stealth is a skill for Claude Code, Codex from LuuOW/meridian-mcp. It costs 47 tokens per session (2,469 once invoked), scanned A, original, MIT.

Guidance for browser automation that uses stealth techniques and residential proxy connections. Browser automation means controlling a web browser with code; a residential proxy routes requests through an IP address associated with a home internet connection.

In plain words
What is it for?
Use it when automating websites with aggressive bot detection, configuring Patchright or Playwright proxies, masking browser automation signals or troubleshooting proxy authentication.
Why use it?
It helps avoid common bot-detection problems and proxy errors in Playwright-based automation. It explains where proxy settings belong, how sticky sessions work and when browser-page requests are needed.

Skill for Claude CodeCodex

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

Good fit Use it when automating websites with aggressive bot detection, configuring Patchright or Playwright proxies, masking browser automation signals or troubleshooting proxy authentication.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/luuow/meridian-mcp/browser-stealth
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 LuuOW/meridian-mcp --skill browser-stealth
Clone the repo
git clone --depth 1 https://github.com/LuuOW/meridian-mcp

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 browser-stealth

README.md
[![agentmods](https://agentmods.dev/badge/skills/luuow/meridian-mcp/browser-stealth/github.svg)](https://agentmods.dev/skills/luuow/meridian-mcp/browser-stealth)
Your own site
<a href="https://agentmods.dev/skills/luuow/meridian-mcp/browser-stealth"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/browser-stealth/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for browser-stealth

Your own site · 80×15
<a href="https://agentmods.dev/skills/luuow/meridian-mcp/browser-stealth"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/browser-stealth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00047 $0.02469
Opus 5 $0.00023 $0.01234
Sonnet 5 $0.00009 $0.00494
Haiku 4.5 $0.00005 $0.00247

Measured 8d ago against content hash d89af6a4f412, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

browser-stealth scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -x "http://${BRIGHTDATA_PROXY_USER}:${BRIGHTDATA_PROXY_PASS}@brd.superproxy.io:22225" \
skills/browser-stealth/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

browser-stealth

Patterns for running Playwright (via patchright) through a residential proxy without triggering bot detection. Covers the critical proxy configuration level bug, sticky session IDs, webdriver masking, and the page.evaluate fetch fallback when context.request can't authenticate through the proxy.

Patchright vs Playwright

Patchright is a drop-in Playwright fork with stealth patches applied at the Chromium level. Use it for targets with aggressive bot detection.

npm install -g patchright
npx patchright install chromium --with-deps
// Replace this:
const { chromium } = require('playwright');

// With this — same API, stealth patches applied:
const { chromium } = require('patchright');

Proxy at Context Level — Not Launch Level

The most common mistake: setting proxy at chromium.launch() affects page navigation but context.request (Playwright's APIRequestContext) does NOT inherit it. You get 407 Proxy Authentication Required on all context.request.get() calls.

// WRONG — context.request gets 407
browser = await chromium.launch({
  proxy: { server: 'http://proxy:8080', username: 'user', password: 'pass' },
});
context = await browser.newContext({});  // ← no proxy here, context.request fails

// CORRECT — proxy must be on newContext() for context.request to work
browser = await chromium.launch({ /* no proxy here */ });
context = await browser.newContext({
  proxy: { server: 'http://proxy:8080', username: 'user', password: 'pass' },
});

If you need both page navigation AND context.request through the proxy, set proxy at both levels or at context level only:

const proxy = proxyConfig();  // returns null if no creds configured

browser = await chromium.launch({
  ...(proxy ? { proxy } : {}),   // page navigation proxy
  args: ['--no-sandbox', '--disable-blink-features=AutomationControlled'],
});

context = await browser.newContext({
  ...(proxy ? { proxy } : {}),   // context.request proxy — must repeat
  viewport: { width: 1440, height: 900 },
  userAgent: 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) ...',
});

Read the full file on GitHub · 244 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. 8d ago First seen · 244 lines · 47 tokens per session scan A d89af6a4f412

Subscribe to this mod's changes

browser-stealth is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 2,469 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.