A desktop and browser automation add-on for Claude Code, the coding agent. It can operate macOS and Windows applications and provides tools for browser work, quality checks, design applications, media editing, and web scraping.

Use it to automate desktop or browser tasks, run interface checks, work in Figma or Canva, edit video, scrape websites, or coordinate multiple agents.

It lets coding-agent workflows interact with software and websites outside the code editor.

screenhand — Plugin for Claude Code by manushi4

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/manushi4/Screenhand

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/manushi4/screenhand/screenhand/github.svg)](https://agentmods.dev/plugins/manushi4/screenhand/screenhand)

Your own site

<a href="https://agentmods.dev/plugins/manushi4/screenhand/screenhand"><img src="https://agentmods.dev/badge/plugins/manushi4/screenhand/screenhand/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/manushi4/screenhand/screenhand"><img src="https://agentmods.dev/badge/plugins/manushi4/screenhand/screenhand.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 13 skills, 5 agents, 1 hook, 1 MCP server cost 1,248 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 unknown No closer match found in the catalogue.

Security

Grade A, and why

screenhand 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 1mo 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.

.claude/plugins/screenhand/.claude-plugin/plugin.json · 24 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Contents

What it installs

The manifest is a name and a version. 13 skills, 5 agents, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 1,248 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.

1mo ago First seen · 24 lines scan A b74fc705465a

Subscribe to this mod's changes

screenhand is a plugin published in the GitHub repository manushi4/Screenhand (15 stars, last pushed 6mo ago), licensed AGPL-3.0. 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 automation E2E testing Testing accessibility ai-agent browser-automation claude computer-use desktop-automation

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

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

muggle

Real-browser E2E acceptance for your coding agent: test the flows you changed and open the PR with screenshots. Built for flows other tools can't reach: managed test identities with live inboxes (magic links, email OTP and 2FA, verification mail, password resets), an encrypted secret store for login and test…

multiplex-ai/muggle-ai-works · 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

sniff

Autonomous QA scanner via sniff-qa: walks your running app in a real browser and reports real bugs (broken pages/links, console/network errors, broken forms, state-loss, empty/placeholder data, bad loading/error states, responsive + a11y) with reproduction proof, severity, confidence, and a fix. No API key.

Aboudjem/sniff · not measured

agentcursor

Local, free, human-like browser automation over MCP. A visible, realistic cursor for coding agents, E2E testing, and workflows on real sites.

kumard3/agentcursor · not measured