Browser automation

8,597 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.

verifier

241

workos/case

Agent Claude Code

Fresh-context verification agent for /case. Reads the diff, tests the specific fix with Playwright, creates evidence markers and screenshots. Never implements.

not rated 156 1mo ago A 32 tokens

Grok-mcp CLAUDE.md

242

LKbaba/Grok-mcp

Instructions file Claude Code

Instructions for LKbaba/Grok-mcp, covering development environment and playwright mcp guide.

not rated 152 17d ago A 190 tokens original MIT

e2e-tester

243

DebugBase/glance

Agent Claude Code

Tests web applications end-to-end using Glance browser MCP. Navigates pages, fills forms, clicks buttons, takes screenshots, runs assertions, and reports bugs. Use when you want to verify an app works correctly — login flows, forms, navigation, responsiveness — with real browser interaction.

not rated 151 4mo ago A 63 tokens original MIT

running-demo

244

microsoft/sre-agent

Skill Claude CodeCodex ✓ vendor

Run break/fix demo scenarios with browser verification. Use when asked to demo, break the app, or show the SRE Agent working.

not rated 151 +2 3d ago A 31 tokens original MIT

bdg

245

szymdzum/browser-debugger-cli

Skill Claude Code

Use bdg CLI for browser automation via Chrome DevTools Protocol. Provides direct CDP access (60+ domains, 300+ methods) for DOM queries, navigation, screenshots, network control, and JavaScript execution. Use this skill when you need to automate browsers, scrape dynamic content, or interact with web pages…

not rated 150 +1 2mo ago A 69 tokens original MIT

web-e2e-qa

246

ondysss/codepilot1c-edt

Skill Claude Code

Full browser E2E + UX/UI audit of newly developed 1C objects in the live web client — discover the new interface, exercise complete user flows, evaluate UX/UI quality, analyze the browser run (screenshots/console/network), and report PASS/WARN/FAIL.

not rated 148 +1 14d ago A 63 tokens AGPL-3.0

job-application-agent

247

vaibhavarora14/job-application-agent

Skill Claude CodeCodex

Finds, evaluates, fills, submits, and tracks a candidate's own job applications using a verified resume, evidence-based targeting, secure local profile storage, and browser automation. Use for onboarding or migrating a job-search profile, searching active roles, assessing a posting, applying to an authorized URL or…

not rated 145 +2 2d ago A 74 tokens original MIT

claude-web CLAUDE.md

248

agi-inc/claude-web

Instructions file Claude Code

Claude Code instructions for agi-inc/claude-web, covering claude.md - web agent automation guide, core web actions (from tools/tools.json), navigate, click and type.

not rated 141 9mo ago A 2,149 tokens

yokingma/one-search-mcp

Instructions file CodexOpenCode

Instructions for yokingma/one-search-mcp, covering agent guide, start here, project map, implementation rules and tests and verification.

not rated 139 1mo ago A 583 tokens original MIT

vasu-playwright-utils

250

vasu31dev/playwright-ts-template

Skill Claude Code

Use the vasu-playwright-utils library for Playwright browser automation with simplified action, assertion, locator, element, page, and API utilities.

not rated 138 5mo ago A 35 tokens

adspower-browser

251

AdsPower/adspower-browser

Skill Claude CodeCodex

AdsPower profile operation via adspower-browser CLI. open/launch/start browser or profile, environment, config profile, AdsPower; create/update/delete/list profiles; groups, tags, proxies; kernel download/list; client patch; API check-status. User phrases like open environment or map to commands such as open-browser.

not rated 135 1mo ago A 69 tokens original MIT

byob

252

wxtsky/byob

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 73 tokens together

Control the user's real Chrome from Claude Code through a local, auditable bridge.

not rated 132 1mo ago A tokens not measured original MIT

agent-browser

253

koolamusic/claudefiles

Skill Claude CodeCodex

This skill should be used when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, scrape data, or extract information from web pages. Use for any browser automation task.

not rated 132 6d ago A 48 tokens original MIT

vessel-browser

254

unmodeled-tyler/vessel-browser

MCP server Claude CodeCodexCursor +2

AI-native browser runtime for autonomous agents with human-in-the-loop supervision. Runs locally from the @quanta-intellect/vessel-browser npm package.

not rated 130 11d ago A tokens not measured original MIT

oculos AGENTS.md

255

huseyinstif/oculos

Instructions file CodexOpenCode

Instructions for huseyinstif/oculos, covering oculos — ai agent instructions, core workflow, discovery, list all windows and search for elements (preferred — fast).

not rated 130 +1 6mo ago A 1,678 tokens original MIT

surf

256

w-winter/dot314

Skill Claude Code

Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.

not rated 129 +4 2d ago A 60 tokens original MIT

vectora-foundry/native-devtools-mcp

Instructions file CodexOpenCode

AGENTS.md instructions for vectora-foundry/native-devtools-mcp, covering agent context: native-devtools-mcp, 🧠 core reasoning loop, 🗺️ capabilities matrix (strategy guide), 🛠️ tool definitions & schemas and 1. vision & perception (the "eyes").

not rated 128 3mo ago A 8,302 tokens original MIT

nanasess/setup-chromedriver

Instructions file Claude Code

Claude Code instructions for nanasess/setup-chromedriver, covering claude.md, commands, build and development, running a single test and or.

not rated 126 +1 2d ago A 985 tokens original MIT

browser-relay

259

reliefeai/browser-relay

Plugin Claude Code

Bundles 1 skill · 86 tokens together

Let agents use the Chrome you already have open and logged in through a Skill + CLI, locally or across machines.

not rated 125 1mo ago A tokens not measured original MIT

apitap

260

n1byn1kt/apitap

Skill Claude CodeCodex

ApiTap gives AI agents cheap access to web data through three layers.

not rated 125 +1 1mo ago A 0 tokens original Apache-2.0

mcp-jobs

261

mergedao/mcp-jobs

MCP server Claude CodeCodexCursor +2

A job search and crawling tool built with Model Context Protocol. Runs locally from the mcp-jobs npm package.

not rated 125 +1 2mo ago A tokens not measured

freestylefly/wechat-article-extractor-skill

Skill Claude CodeCodex

Extract metadata and content from WeChat Official Account articles. Use when user needs to parse WeChat article URLs (mp.weixin.qq.com), extract article info (title, author, content, publish time, cover image), or convert WeChat articles to structured data. Supports various article types including posts, videos…

not rated 124 6mo ago A 76 tokens

rico-bookmark-manager

264

ricocc/rico-bookmark-manager

Skill Claude CodeCodex

Browser bookmark management and organization: analyze, organize, deduplicate, check dead links, search, export, incrementally update, acquire browser bookmark data, or generate a local bookmark navigation site. Triggers in two cases, in any language: (1) the user mentions "rico" together with bookmark intent (rico is…

not rated 124 +3 2mo ago A 145 tokens original MIT

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: