# Send Tor Browser Automation to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "tor-browser", "name": "Tor Browser Automation", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/Admin4Giter/tor-browser", "canonicalUrl": "https://clawhub.ai/Admin4Giter/tor-browser", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/tor-browser", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=tor-browser", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "references/setup-guide.md", "scripts/tor-browser.py" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "tor-browser", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-10T03:09:38.838Z", "expiresAt": "2026-05-17T03:09:38.838Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=tor-browser", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=tor-browser", "contentDisposition": "attachment; filename=\"tor-browser-1.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "tor-browser" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/tor-browser" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/tor-browser", "downloadUrl": "https://openagent3.xyz/downloads/tor-browser", "agentUrl": "https://openagent3.xyz/skills/tor-browser/agent", "manifestUrl": "https://openagent3.xyz/skills/tor-browser/agent.json", "briefUrl": "https://openagent3.xyz/skills/tor-browser/agent.md" } } ``` ## Documentation ### Tor Browser Automation Headless browser automation with Tor SOCKS5 proxy support for accessing .onion sites and anonymous web browsing. ### Prerequisites Tor service running with SOCKS5 proxy on port 9050 Python 3.8+ Playwright with Chromium browser Quick setup: # Install Tor sudo apt install tor && sudo systemctl start tor # Install Python dependencies pip install playwright playwright install chromium ### Quick Start # Check Tor connection tor-browser check-tor # Navigate to a .onion site tor-browser open http://3g2upl4pq6kufc4m.onion # Get page snapshot tor-browser snapshot -i # Click an element tor-browser click @e1 # Take screenshot tor-browser screenshot -o output.png --full ### Navigation # Open URL via Tor tor-browser open [--proxy socks5://host:port] # Check Tor connection status tor-browser check-tor ### Page Analysis # Get full page snapshot tor-browser snapshot # Get interactive elements only (forms, buttons, links) tor-browser snapshot -i # Extract all links tor-browser links # Get page text tor-browser gettext tor-browser gettext --ref @e5 ### Interaction # Click element by ref tor-browser click @e1 # Fill input field tor-browser fill @e2 "text to enter" # Wait for page load tor-browser wait 2000 ### Screenshots # Take viewport screenshot tor-browser screenshot # Save to file tor-browser screenshot -o capture.png # Full page screenshot tor-browser screenshot --full -o page.png ### Python API from scripts.tor_browser import TorBrowser, Config import asyncio async def main(): # Configure browser config = Config( tor_proxy="socks5://127.0.0.1:9050", headless=True, timeout=30000 ) # Initialize and start browser = TorBrowser(config) await browser.start() # Navigate result = await browser.navigate("http://3g2upl4pq6kufc4m.onion") print(f"Loaded: {result['title']}") # Get snapshot snapshot = await browser.get_snapshot(interactive_only=True) for elem in snapshot['elements']: print(f"{elem['ref']}: {elem['tag']} - {elem['text'][:30]}") # Interact await browser.fill("@e2", "search query") await browser.click("@e3") # Extract data links = await browser.extract_links() for link in links: print(f"{link['text']}: {link['href']}") # Cleanup await browser.close() asyncio.run(main()) ### Configuration Options OptionDefaultDescriptiontor_proxysocks5://127.0.0.1:9050Tor SOCKS5 proxy URLheadlesstrueRun without GUItimeout30000Page load timeout (ms)user_agentTor Browser UABrowser user agentviewport1920x1080Browser viewport size ### Security & Legal Intended Use: Security research and threat intelligence Anonymous web scraping of public dark web resources Testing .onion site accessibility Privacy-preserving web automation Important: Only use for legal purposes Respect site Terms of Service Do not use for unauthorized access Comply with local laws regarding dark web access Be aware that some activities may be monitored ### Tor Connection Issues # Check Tor is running sudo systemctl status tor # Test SOCKS5 proxy curl --socks5-hostname 127.0.0.1:9050 https://check.torproject.org/api/ip # View Tor logs sudo journalctl -u tor -f ### Common Errors Connection refused: Ensure Tor service is started Check firewall rules Verify proxy URL Timeout: .onion sites may be slow; increase timeout Try different Tor circuits: restart Tor service CAPTCHA blocking: Use --headed mode to manually solve Some sites block automation ### Docker Setup FROM python:3.11-slim RUN apt-get update && apt-get install -y tor RUN pip install playwright && playwright install chromium COPY . /app WORKDIR /app CMD ["tor-browser", "check-tor"] ### References Setup Guide: references/setup-guide.md Playwright Docs: https://playwright.dev/python/ Tor Project: https://www.torproject.org/ ### License MIT - See original licenses for Playwright and Tor Project components. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: Admin4Giter - Version: 1.1.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-10T03:09:38.838Z - Expires at: 2026-05-17T03:09:38.838Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/tor-browser) - [Send to Agent page](https://openagent3.xyz/skills/tor-browser/agent) - [JSON manifest](https://openagent3.xyz/skills/tor-browser/agent.json) - [Markdown brief](https://openagent3.xyz/skills/tor-browser/agent.md) - [Download page](https://openagent3.xyz/downloads/tor-browser)