7,463 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
MCP server Claude CodeCodexCursor +2
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Skill Claude CodeCodex
ApiTap gives AI agents cheap access to web data through three layers.
abracadabra50/open-supermarkets
Skill Claude Code
Open-source supermarket infrastructure across 13 provider integrations in 9 countries. Search live catalogues and prices, compare retailers, build baskets, inspect slots and orders, and preview checkout through CLI, HTTP, MCP or agent skills.
MCP server Claude CodeCodexCursor +2
Your AI sees the screen but can't measure it — measured web UI findings, shared live sessions. Runs locally from the uisight npm package. Needs 3 environment variables to run.
Skill Claude CodeCodex
Guidance for driving Windows desktop automation from the wincli command-line tool - the token-efficient entry point that mirrors the Windows MCP server. Use when a coding agent has shell access and wants one compact command surface instead of many MCP tool schemas.
Skill Claude CodeCodex
Drive and inspect the running Steam client UI over the Chrome DevTools Protocol (CEF remote debugging, port 8080) — list targets, evaluate JS probes, navigate routes, click elements, dispatch keys, capture screenshots, stream console errors. Use for hands-free UI automation and read-only diagnosis of Steam's gamepad…
Skill Claude CodeCodex
Search, browse, inspect album-specific or site-wide comments, list favorite folders, browse, add, and delete favorites, perform daily check-in, and download manga from JMComic (18comic), obtain the latest Android APK from hect0x7/JMComic-APK, and invoke the upstream jm-view-server jms command for local reading. Use…
Skill Claude CodeCodex
Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…
Plugin Claude Code
Bundles 1 skill · 12 tokens together
Screenshot open browser tabs for visual debugging.
Skill Claude CodeCodex
Anti-detection browser automation MCP skill for OpenClaw agents with 47 tools for navigation, interaction, observation, extraction, downloads, profiles, sessions, and stealth web search.
jhartquist/claude-remotion-kickstart
MCP server Claude CodeCodexCursor +2
One of 4 in .mcp.json
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
browsing-skills/browsing-skills
Skill Claude CodeCodex
Umbrella skill for a library of website-specific browsing skills. Use when the user's request targets one of these specific websites: airbnb.com, aliexpress.com, amazon.com, booking.com, capterra.com, craigslist.org, facebook.com, g2.com, glassdoor.com, instagram.com, linkedin.com, madlan.co.il, maps.google.com…
MCP server Claude CodeCodexCursor +2
One of 2 in server.json
Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliabili… Remote server at server.smithery.ai.
MCP server Claude CodeCodexCursor +2
MCP server "hwatu" as configured in hongnoul/hwatu. Launched with https://github.com/hongnoul/hwatu/releases/download/v0.6.0/hwatu-mcp-linux-x86_6.
Skill Cursor
Regenerate the README UI screenshots for nyx-local-ai from the browser harness — build the webview, serve the harness scenes, capture and crop the images into docs/. Use when the UI changed visibly, when the user asks to update screenshots, or before a release with UI changes.
MCP server Claude CodeCodexCursor +2
MCP server "crawl4ai-mcp" as configured in sadiuysal/crawl4ai-mcp-server. Runs in Docker (./crawls:/app/crawls). Needs 1 environment variable to run.
Skill Claude Code
Converts any web page URL to LLM-ready Markdown via a headless browser. Bypasses passive anti-bot fingerprinting and JavaScript rendering, then strips navigation, footers, scripts, and cookie banners. Triggered by URLs that need the actual readable page content.
Skill Claude Code
Lightpanda browser, drop-in replacement for Chrome-based browsing in any AI agent - faster and lighter for tasks without graphical rendering like data retrieval. Install it and use it via MCP server, CLI fetch, CDP with Playwright/Puppeteer, or WebDriver with Selenium; MCP and CDP also run on Lightpanda Cloud. Its…
ManiacMike/chatgpt-endless-canvas
Skill Claude CodeCodex
Generate images through the ChatGPT web app (chatgpt.com) via a local infinite-canvas board — queued jobs, scheduled batches, annotate-to-edit, style-reference generation, lineage. Use when the user asks to generate images ("生图", "draw with ChatGPT", "open the board", "new canvas"), or wants images consistent with a…
Skill Claude CodeCodex
Open Web Bridge (OWB) — drive the user's own real browser with the owb command. Read pages behind their existing logins, gather and cross-check information, fill forms, walk multi-step flows, debug their site, audit responsive/accessibility behavior, and capture or reverse-engineer network traffic. Use this whenever…
Cursor rule Cursor
Shared Svelte testing guidance.
extrasmall0/dear-hiring-manager
Plugin Claude Code
Bundles 7 skills, 6 commands, 1 MCP server · 733 tokens together
Assisted job-application filler. Extracts the JD, scores fit, fills every form field from your profile and answer memory, and stops before Submit for your review. Runs interactively in Claude Code.
Skill Claude CodeCodex
Use this skill for live web research, webpage fetching, login-state browsing, dynamic pages, social sites, and tasks that need current internet evidence.
Skill Claude CodeCodex
Instructions for an agent that operates a virtual desktop while explaining its actions aloud. A virtual desktop is a simulated computer screen where the agent can control windows, a pointer, and terminal sessions.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: