captcha-relayHuman-in-the-loop CAPTCHA solving with two modes: screenshot (default, zero infrastructure) and token relay (requires network access). Screenshot mode captur...
Install via ClawdBot CLI:
clawdbot install 0xclanky/captcha-relaySolve CAPTCHAs by relaying them to a human. Two modes available.
Grid overlay screenshot ā send image to human via Telegram ā human replies with cell numbers ā inject clicks.
sharp for image processing + CDP for screenshots and click injection.node index.js # screenshot mode (default)
node index.js --mode screenshot # explicit
node index.js --screenshot # legacy aliasconst { solveCaptchaScreenshot } = require('./index');
const capture = await solveCaptchaScreenshot({ cdpPort: 18800 });
// capture.imagePath ā annotated screenshot to send to human
// capture.prompt ā text prompt for the humanDetects CAPTCHA type + sitekey ā serves real widget on relay page ā human solves natively ā token injected via CDP.
node index.js --mode relay # with localtunnel
node index.js --mode relay --no-tunnel # with Tailscale/LANconst { solveCaptcha } = require('./index');
const result = await solveCaptcha({ cdpPort: 18800, useTunnel: false });
// result.relayUrl ā URL to send to human
// result.token ā solved CAPTCHA token| Scenario | Mode |
|----------|------|
| Quick & easy, no setup | screenshot |
| Any CAPTCHA type (sliders, text, etc.) | screenshot |
| Known CAPTCHA with sitekey (reCAPTCHA, hCaptcha, Turnstile) | relay |
| Tailscale already configured | relay |
| No network access to host | screenshot |
| Flag | Default | Description |
|------|---------|-------------|
| --mode screenshot\|relay | screenshot | Select solving mode |
| --screenshot | ā | Alias for --mode screenshot |
| --no-inject | inject | Return token without injecting into browser |
| --no-tunnel | tunnel | Skip tunnel, use local/Tailscale IP (relay mode) |
| --timeout N | 120 | Timeout in seconds |
| --cdp-port N | 18800 | Chrome DevTools Protocol port |
solveCaptchaScreenshot({ cdpPort }) capture.imagePath to human via message tool with capture.promptinjectGridClicks(cdpPort, capture, selectedCells) to click those cellssolveCaptcha({ useTunnel: false }) (Tailscale) or solveCaptcha() (tunnel)result.relayUrl to human via message tool--remote-debugging-port=18800npm install (deps: ws, sharp)Generated Mar 1, 2026
Automates CAPTCHA solving during checkout processes on e-commerce sites, enabling seamless order placement for bulk purchasing or inventory management bots. Uses screenshot mode for quick setup without network dependencies, handling various CAPTCHA types like reCAPTCHA or text challenges.
Facilitates CAPTCHA solving for automated social media posting, account creation, or engagement tasks on platforms like Facebook or Twitter. Relay mode is ideal for token-based CAPTCHAs when Tailscale is configured, ensuring reliable token injection for repeated actions.
Enables CAPTCHA bypass for web scraping tools that collect data from protected websites, such as academic journals or business directories. Screenshot mode handles diverse CAPTCHA formats without infrastructure, while relay mode improves efficiency for known CAPTCHA types with sitekeys.
Automates CAPTCHA solving for booking tickets on event or travel websites, where speed is critical to secure limited inventory. Uses screenshot mode for zero-setup flexibility or relay mode with Tailscale for enhanced reliability in high-demand scenarios.
Offers a monthly subscription for businesses to integrate the skill into their automation workflows, providing regular updates and support. Revenue is generated through tiered pricing based on usage volume, such as number of CAPTCHAs solved per month.
Provides API access to the skill's functions, charging per CAPTCHA solved, which appeals to occasional users or small-scale projects. Revenue scales with usage, with pricing models like $0.01 per CAPTCHA for low-volume clients.
Sells custom integration packages and consulting services to large enterprises needing tailored CAPTCHA-solving solutions for specific automation needs. Revenue comes from one-time setup fees and ongoing maintenance contracts.
š¬ Integration Tip
Ensure Chrome runs with --remote-debugging-port=18800 before using the skill, and for relay mode, set up Tailscale or a tunnel in advance to avoid network issues.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection