5,255 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.
mdsohaib/screenshot-time-machine
Instructions file CodexOpenCode
AGENTS.md instructions for mdsohaib/screenshot-time-machine, covering agents.md: how to work in this repo (humans and ai agents), setup (5 commands), module map (v0.1), hard rules (a pr that breaks one will be closed) and before you open a pr.
Skill Claude CodeCodex
Run an isolated persona-based UX test through the real desktop or browser UI. Creates a precise non-developer user persona, gives the tester only an approved product introduction, prevents source-code and design-document leakage, and produces an evidence-based Chinese evaluation report. Use when the user asks for…
mrmarufpro/shopify-embedded-app-verify
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 108 tokens together
Agentic verify loop for Shopify embedded apps — drives the real, authenticated Shopify admin in the developer's own browser via CDP.
Skill Claude Code
Add a new browser tool to the Chrome Bridge end to end — MCP tool in server/index.js, handler in extension/background.js, e2e assertion, README row. Use when asked to add, rename, or remove a browser capability exposed to Claude Code.
Agent Claude Code
Where WeftCut's tests live, why they're split the way they are, and how to run each layer. There is no single tests/ directory — that's deliberate (see Why not one directory). Tests are grouped by runner, not scattered by neglect.
Skill Claude Code
A test-building tool for generating several kinds of checks for code. It covers static analysis, which examines code without running it, plus unit, integration, and end-to-end tests and coverage reports.
Skill Claude Code
Domain skill - run screenshot-light PIE playtest episodes with structured entity observations, bounded semantic actions, transition polling, and in-memory traces for QA and external policy or RL runners.
Skill Claude Code
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
luis-at-safebase/luism-claude-plugins
Plugin Claude Code
Bundles 1 skill · 57 tokens together
QA artifact generator — point it at a PR or give freeform instructions. Navigates the UI, captures screenshots, and stitches a GIF. Fully configurable auth and artifact storage via /.sentinel/config.json.
MCP server Claude CodeCodexCursor +2
MCP server "testcafe-mcp-server" as configured in rkdfx/testcafe-mcp. Runs locally from the testcafe-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
MCP server for Bruno API collections. Runs locally from the bruno-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "playwright-test-generator-mcp" as configured in ingpoc/ui-test-generation-mcp. Runs locally from the playwright-test-generator-mcp npm package.
Plugin Claude Code
Podium — the mobile + canvas automation MCP for AI agents: iOS & Android control, native UI automation, Maestro E2E, React Native debugging, and a no-vision canvas/WebGL brain that taps game UIs like DOM elements — for Claude Code.
Instructions file GitHub Copilot
Copilot instructions for arkhangelsk/mcp-appium-server, covering test case writing using appium mcp server, key development patterns and references.
Skill Claude Code
How to run end-to-end tests against the EleSync local web UI on Windows.
Skill Claude Code
Validate UIs by clicking through them like a real user — iOS Simulator, Android emulator, tvOS, desktop, and web. Detects the platform and picks the right tool — agent-device (Callstack) for mobile/TV/desktop, agent-browser (Vercel Labs) for web, Maestro + Maestro Viewer for declarative cross-platform flows; raw xcrun…
Skill Claude CodeCodex
A workflow that reviews code changes and suggests mutation tests or end-to-end tests. Mutation testing changes code deliberately to see whether tests detect the change, while end-to-end testing checks a complete user flow.
Agent Claude Code
Self-healing QA agent for copilot-engine. Checks prerequisites, build, server health, and API smoke tests. Auto-fixes what it can before reporting issues.
MCP server Claude CodeCodexCursor +2
Agent-built web app quality gate. Real browser is the judge. PASS/FAIL with receipts. Runs locally from the dsh-verify npm package.
Instructions file Claude Code
Instructions for fastslack/mtw-e2e-runner, covering claude.md, project overview, commands, install dependencies and scaffold e2e/ directory in a consuming project.
MCP server Claude CodeCodexCursor +2
Ensemble testing of web pages for accessibility, usability, and standards conformity. Remote server at kilotest.com.
u9401066/template-is-all-you-need
Skill Claude Code
A test-suite generation workflow for software projects. It includes static checks, unit tests, integration tests, end-to-end tests, coverage reports, type checking, linting, security scanning, and dead-code detection.
Instructions file CodexOpenCode
Instructions for willbytee-sudo/android-qa-kit, covering agents.md — setting up and driving an android device, 1. how to work with the user, 2. start by finding out what's already there, 3. what you can do in each mode and 4. if there's no device: ask first.
Skill Claude CodeCodex
Use when completion depends on an end-to-end outcome across components, environments, or external systems.
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: