agentmods.dev

muggle

muggle is a plugin for Claude Code from multiplex-ai/muggle-ai-works. Its manifest loads nothing; the 30 skills, 15 commands, 3 agents, 3 hooks, 1 MCP server it bundles cost 2,983 tokens per session together, scanned A, original, MIT.

A plugin for testing web applications in a real browser. It can create tests from plain-English instructions, replay them on a local app, take screenshots, and check flows such as signup, checkout, and dashboards.

In plain words
What is it for?
It is for end-to-end acceptance testing, browser-based UI checks, screenshot capture, and validating web app workflows from coding agents.
Why use it?
It helps find broken user journeys by testing the app as a person would use it.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions Claude Code; mentions Codex.

not rated 16repo changed 27d ago A scan tokens not measured original MIT

Good fit It is for end-to-end acceptance testing, browser-based UI checks, screenshot capture, and validating web app workflows from coding agents.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add multiplex-ai/muggle-ai-works
/plugin install muggle
View source ↗ multiplex-ai/muggle-ai-works muggletest.com
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/multiplex-ai/muggle-ai-works

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for muggle

README.md
[![agentmods](https://agentmods.dev/badge/plugins/multiplex-ai/muggle-ai-works/plugin/github.svg)](https://agentmods.dev/plugins/multiplex-ai/muggle-ai-works/plugin)
Your own site
<a href="https://agentmods.dev/plugins/multiplex-ai/muggle-ai-works/plugin"><img src="https://agentmods.dev/badge/plugins/multiplex-ai/muggle-ai-works/plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for muggle

Your own site · 80×15
<a href="https://agentmods.dev/plugins/multiplex-ai/muggle-ai-works/plugin"><img src="https://agentmods.dev/badge/plugins/multiplex-ai/muggle-ai-works/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 30 skills, 15 commands, 3 agents, 3 hooks, 1 MCP server cost 2,983 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

muggle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 27d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/.claude-plugin/plugin.json · 27 lines

What it actually says

{
  "name": "muggle",
  "description": "Run real-browser end-to-end (E2E) acceptance tests on your web app from any AI coding agent. Generate test scripts from plain English, replay them on localhost, capture screenshots, and validate user flows like signup, checkout, and dashboards. Works across Claude Code, Cursor, Codex, and Windsurf.",
  "version": "5.18.0",
  "author": {
    "name": "Muggle AI",
    "email": "[email protected]"
  },
  "homepage": "https://www.muggletest.com",
  "repository": "https://github.com/multiplex-ai/muggle-ai-works",
  "license": "MIT",
  "keywords": [
    "acceptance-testing",
    "testing",
    "mcp",
    "browser-automation",
    "ai-coding",
    "muggle-ai",
    "ui-validation",
    "regression-testing",
    "e2e-testing",
    "ux-testing",
    "visual-testing",
    "frontend-testing"
  ]
}
Contents

What it installs

The manifest is a name and a version. 30 skills, 15 commands, 3 agents, 3 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 2,983 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 27d ago Changed 3c57c0295fb4
  2. 1mo ago Changed d83aa27e2865
  3. 1mo ago First seen · 27 lines scan A ebb09a8c09ed

Subscribe to this mod's changes

muggle is a plugin published in the GitHub repository multiplex-ai/muggle-ai-works (16 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automationClaude CodeE2E testingTestingai-agentsai-powered-testingai-qaai-testingbrowser-automation
Related

Other plugins, from other repositories

mockhunter

Audit live web pages for fake/mock data — 5-phase Playwright + Claude Code skill that classifies every visible value as REAL, MOCK, LLM, HARDCODED, BROKEN, or UNKNOWN.

CodeShuX/mockhunter · not measured

qa-essentials

QASkills.sh QA Essentials — 10 curated skills that turn your agent into a QA engineer: Claude Code QA, E2E (Playwright/Cypress), API testing, pytest, Jest, k6 performance, and an autonomous QA agent loop.

PramodDutta/qaskills · not measured

kogiqa-browser

Selector-free browser automation for debugging, testing and documenting web apps, backed by the kogiQA MCP server.

atagon-GmbH/kogiqa-mcp · not measured

assay

Opens a page you changed, drives every control it offers, and reports what it did and what happened. One line every time, clean or not.

awss1i/assay · not measured

qa-use

Simplified CLI-integrated plugin for E2E testing with essential slash commands plus dynamic API CLI workflows (qa-use api). Provides AI-first feature verification, browser automation, and test management. All CLI operations documented in SKILL.md and accessible via qa-use docs for harness compatibility.

desplega-ai/qa-use · not measured

vibe-testing

Code-aware browser testing and release QA for AI coding agents.

AishwaryShrivastav/vibe-testing · not measured