Skip to main content
stealth-browser Ultimate stealth browser automation with anti-detection, Cloudflare bypass, CAPTCHA solving, persistent sessions, and silent operation. Use for any web automation requiring bot detection evasion, login persistence, headless browsing, or bypassing security measures. Triggers on "bypass cloudflare", "solve captcha", "stealth browse", "silent automation", "persistent login", "anti-detection", or any task needing undetectable browser automation. When user asks to "login to X website", automatically use headed mode for login, then save session for future headless reuse.
Jump to install Skills Marketplace Discover and explore AI skills built by the community.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Show prompt details A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/duclm1x1/Dive-Ai --skill stealth-browserThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Download Zip Downloading... Related occupations SOC
Based on SOC occupation classification
name stealth-browser description Ultimate stealth browser automation with anti-detection, Cloudflare bypass, CAPTCHA solving, persistent sessions, and silent operation. Use for any web automation requiring bot detection evasion, login persistence, headless browsing, or bypassing security measures. Triggers on "bypass cloudflare", "solve captcha", "stealth browse", "silent automation", "persistent login", "anti-detection", or any task needing undetectable browser automation. When user asks to "login to X website", automatically use headed mode for login, then save session for future headless reuse.
Stealth Browser Automation
Silent, undetectable web automation combining multiple anti-detection layers.
Quick Login Workflow (IMPORTANT)
When user asks to login to any website:
Open in headed mode (visible browser for manual login):
python scripts/stealth_session.py -u "https://target.com/login" -s sitename --headed
User logs in manually in the visible browser
Save session after login confirmed:
python scripts/stealth_session.py -u "https://target.com" -s sitename --headed --save
Future use - load saved session (headless):
python scripts/stealth_session.py -u "https://target.com" -s sitename --load
Sessions stored in: ~/.clawdbot/browser-sessions/<sitename>.json
ๆง่ก็ญ็ฅ (IMPORTANT)
1. ๅ
้้ปๅๆพ็คบ
ไผๅ
ไฝฟ็จ headless ๆจกๅผ้้ปๅฐ่ฏ
ๅฆๆๅคฑ่ดฅๆ้่ฆ้ช่ฏ็ ๏ผๅๅๆขๅฐ headed ๆพ็คบๆจกๅผ
้ฟๅ
ๆๆฐ็จๆทๆไฝ
2. ๆญ็น็ปญไผ
้ฟไปปๅกไฝฟ็จ
task_runner.py
from task_runner import TaskRunner
task = TaskRunner('my_task' )
task.set_total(100 )
for i in items:
if task.is_completed(i):
continue
task.mark_completed(i)
task.finish()
3. ่ถ
ๆถๅค็
้ป่ฎคๅ้กต่ถ
ๆถ: 30็ง
้ฟไปปๅกๆฏ50้กนไฟๅญไธๆฌก่ฟๅบฆ
ๅคฑ่ดฅ่ชๅจ้่ฏ3ๆฌก
4. ่ฎฐๅฝๅฐ่ฏ ๆๆ็ปๅฝๅฐ่ฏ่ฎฐๅฝๅจ: ~/.clawdbot/browser-sessions/attempts.json
Architecture โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Stealth Browser โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ Layer 1: Anti-Detection Engine โ
โ - puppeteer-extra-plugin-stealth โ
โ - Browser fingerprint spoofing โ
โ - WebGL/Canvas/Audio fingerprint masking โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ Layer 2: Challenge Bypass โ
โ - Cloudflare Turnstile/JS Challenge โ
โ - hCaptcha / reCAPTCHA integration โ
โ - 2Captcha / Anti-Captcha API โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ Layer 3: Session Persistence โ
โ - Cookie storage (JSON/SQLite) โ
โ - localStorage sync โ
โ - Multi-profile management โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ Layer 4: Proxy & Identity โ
โ - Rotating residential proxies โ
โ - User-Agent rotation โ
โ - Timezone/Locale spoofing โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Setup
Install Core Dependencies npm install -g puppeteer-extra puppeteer-extra-plugin-stealth
npm install -g playwright
pip install undetected-chromedriver DrissionPage
Optional: CAPTCHA Solvers Store API keys in ~/.clawdbot/secrets/captcha.json:
{
"2captcha" : "YOUR_2CAPTCHA_KEY" ,
"anticaptcha" : "YOUR_ANTICAPTCHA_KEY" ,
"capsolver" : "YOUR_CAPSOLVER_KEY"
}
Optional: Proxy Configuration Store in ~/.clawdbot/secrets/proxies.json:
{
"rotating" : "http://user:pass@proxy.provider.com:port" ,
"residential" : [ "socks5://ip1:port" , "socks5://ip2:port" ] ,
"datacenter" : "http://dc-proxy:port"
}
Quick Start
1. Stealth Session (Python - Recommended)
import undetected_chromedriver as uc
from DrissionPage import ChromiumPage
driver = uc.Chrome(headless=True , use_subprocess=True )
driver.get("https://nowsecure.nl" )
page = ChromiumPage()
page.get("https://cloudflare-protected-site.com" )
2. Stealth Session (Node.js)
import puppeteer from 'puppeteer-extra' ;
import StealthPlugin from 'puppeteer-extra-plugin-stealth' ;
puppeteer.use (StealthPlugin ());
const browser = await puppeteer.launch ({
headless : 'new' ,
args : [
'--disable-blink-features=AutomationControlled' ,
'--disable-dev-shm-usage' ,
'--no-sandbox'
]
});
const page = await browser.newPage ();
await page.goto ('https://bot.sannysoft.com' );
Core Operations
Open Stealth Page
agent-browser --profile ~/.stealth-profile open https://target.com
python scripts/stealth_open.py --url "https://target.com" --headless
Bypass Cloudflare
from DrissionPage import ChromiumPage
page = ChromiumPage()
page.get("https://cloudflare-site.com" )
page.wait.ele_displayed("main-content" , timeout=30 )
For stubborn Cloudflare sites, use FlareSolverr:
docker run -d --name flaresolverr -p 8191:8191 ghcr.io/flaresolverr/flaresolverr
curl -X POST http://localhost:8191/v1 \
-H "Content-Type: application/json" \
-d '{"cmd":"request.get","url":"https://cf-protected.com","maxTimeout":60000}'
Solve CAPTCHAs
import requests
import json
import time
def solve_recaptcha (site_key, page_url, api_key ):
"""Solve reCAPTCHA v2/v3 via 2Captcha"""
resp = requests.post("http://2captcha.com/in.php" , data={
"key" : api_key,
"method" : "userrecaptcha" ,
"googlekey" : site_key,
"pageurl" : page_url,
"json" : 1
}).json()
task_id = resp["request" ]
for _ in range (60 ):
time.sleep(3 )
result = requests.get(f"http://2captcha.com/res.php?key={api_key} &action=get&id={task_id} &json=1" ).json()
if result["status" ] == 1 :
return result["request" ]
return None
def solve_hcaptcha (site_key, page_url, api_key ):
"""Solve hCaptcha via Anti-Captcha"""
resp = requests.post("https://api.anti-captcha.com/createTask" , json={
"clientKey" : api_key,
"task" : {
"type" : "HCaptchaTaskProxyless" ,
"websiteURL" : page_url,
"websiteKey" : site_key
}
}).json()
task_id = resp["taskId" ]
for _ in range (60 ):
time.sleep(3 )
result = requests.post("https://api.anti-captcha.com/getTaskResult" , json={
"clientKey" : api_key,
"taskId" : task_id
}).json()
if result["status" ] == "ready" :
return result["solution" ]["gRecaptchaResponse" ]
return None
Persistent Sessions
import json
import os
from pathlib import Path
SESSIONS_DIR = Path.home() / ".clawdbot" / "browser-sessions"
SESSIONS_DIR.mkdir(parents=True , exist_ok=True )
def save_cookies (driver, session_name ):
"""Save cookies to JSON"""
cookies = driver.get_cookies()
path = SESSIONS_DIR / f"{session_name} _cookies.json"
path.write_text(json.dumps(cookies, indent=2 ))
return path
def load_cookies (driver, session_name ):
"""Load cookies from saved session"""
path = SESSIONS_DIR / f"{session_name} _cookies.json"
if path.exists():
cookies = json.loads(path.read_text())
for cookie in cookies:
driver.add_cookie(cookie)
return True
return False
def save_local_storage (page, session_name ):
"""Save localStorage"""
ls = page.evaluate("() => JSON.stringify(localStorage)" )
path = SESSIONS_DIR / f"{session_name} _localStorage.json"
path.write_text(ls)
return path
def load_local_storage (page, session_name ):
"""Restore localStorage"""
path = SESSIONS_DIR / f"{session_name} _localStorage.json"
if path.exists():
data = path.read_text()
page.evaluate(f"(data) => {{ Object.entries(JSON.parse(data)).forEach(([k,v]) => localStorage.setItem(k,v)) }}" , data)
return True
return False
Silent Automation Workflow
from DrissionPage import ChromiumPage, ChromiumOptions
options = ChromiumOptions()
options.headless()
options.set_argument('--disable-blink-features=AutomationControlled' )
options.set_argument('--disable-dev-shm-usage' )
options.set_user_agent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36' )
page = ChromiumPage(options)
page.get("https://target-site.com" )
page.wait.doc_loaded()
page.ele("@id=username" ).input ("user@email.com" )
page.ele("@id=password" ).input ("password123" )
page.ele("@type=submit" ).click()
page.cookies.save("~/.clawdbot/browser-sessions/target-site.json" )
Proxy Rotation
import random
import json
from pathlib import Path
def get_proxy ():
"""Get random proxy from pool"""
config = json.loads((Path.home() / ".clawdbot/secrets/proxies.json" ).read_text())
proxies = config.get("residential" , [])
return random.choice(proxies) if proxies else config.get("rotating" )
options = ChromiumOptions()
options.set_proxy(get_proxy())
page = ChromiumPage(options)
User Input Required To complete this skill, provide:
CAPTCHA API Keys (optional but recommended):
Proxy Configuration (optional):
Residential proxy provider credentials
Or list of SOCKS5/HTTP proxies
Target Sites (for pre-configured sessions):
Which sites need login persistence?
What credentials should be stored?
Files Structure stealth-browser/
โโโ SKILL.md
โโโ scripts/
โ โโโ stealth_session.py # Main stealth browser wrapper
โ โโโ solve_captcha.py # CAPTCHA solving utilities
โ โโโ session_manager.py # Cookie/localStorage persistence
โ โโโ proxy_rotate.py # Proxy rotation
โ โโโ cf_bypass.py # Cloudflare-specific bypass
โโโ references/
โโโ fingerprints.md # Browser fingerprint details
โโโ detection-tests.md # Sites to test anti-detection
Testing Anti-Detection
python scripts/stealth_open.py --url "https://bot.sannysoft.com"
python scripts/stealth_open.py --url "https://nowsecure.nl"
python scripts/stealth_open.py --url "https://arh.antoinevastel.com/bots/areyouheadless"
python scripts/stealth_open.py --url "https://pixelscan.net"
Integration with agent-browser For simple tasks, use agent-browser with a persistent profile:
agent-browser --profile ~/.stealth-profile --headed open https://login-site.com
agent-browser --profile ~/.stealth-profile snapshot
agent-browser --profile ~/.stealth-profile click @e5
For Cloudflare or CAPTCHA-heavy sites, use Python scripts instead.
Best Practices
Always use headless: 'new' not headless: true (less detectable)Rotate User-Agents matching browser versionAdd random delays between actions (100-500ms)Use residential proxies for sensitive targetsSave sessions after successful loginTest on bot.sannysoft.com before production use More from this repository
