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.
/plugin marketplace add southlab-ai/Claude-Plugin-Marketplacenpx agentmods add plugins/southlab-ai/claude-plugin-marketplace/computer-visiongit clone --depth 1 https://github.com/southlab-ai/Claude-Plugin-MarketplaceWrote 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.
[](https://agentmods.dev/plugins/southlab-ai/claude-plugin-marketplace/computer-vision)<a href="https://agentmods.dev/plugins/southlab-ai/claude-plugin-marketplace/computer-vision"><img src="https://agentmods.dev/badge/plugins/southlab-ai/claude-plugin-marketplace/computer-vision.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
computer-vision 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 5d 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.
What it actually says
{
"name": "computer-vision",
"version": "2.6.0",
"description": "Desktop computer vision and input control for Claude Code on Windows. 24 tools: screenshots, scene analysis, human-like mouse movement, action recording, UIA-based element invocation (cv_click_ui — works on WinUI 3 apps where SendInput fails), deep UI tree search, click, type, OCR, element finder, text extraction. Background mode via PostMessage.",
"author": {
"name": "Southlab AI"
},
"repository": "https://github.com/southlab-ai/Claude-Plugin-Marketplace",
"license": "MIT",
"keywords": [
"computer-vision",
"windows",
"desktop",
"automation",
"mcp",
"screenshot",
"ocr",
"accessibility",
"background-mode",
"parallel"
]
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 0 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 5d ago First seen · 23 lines scan A 2e0c35128c88
computer-vision is a plugin published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo 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 2026-08-31.
Other plugins, from other repositories
firecrawl
Web scraping, search, crawling, and file parsing through the firecrawl-cli binary with a write-to-disk-then-Read pattern that keeps large results out of context — a user-facing wrapper skill, a lazy-install setup skill, and a separate gated maintainer update skill tracking the upstream CLI and skill source.
playwright
Live E2E browser automation via Microsoft's @playwright/cli — named sessions, accessibility-ref snapshots, click/fill by ref, screenshots, console and network capture, mocking, tracing, video, and auth state, with artifacts written to disk so only paths enter context, plus a vendored upstream baseline and maintainer…
cdp-cli
Ride a running Chromium browser via CDP. Access authenticated sessions without credentials. Works with Brave, Chrome, Edge, Arc.
kernel-sdks
TypeScript and Python SDK skills for building browser automation with Kernel's Typescript and Python SDKs.
promptcause marketplace
The Prompt Cause marketplace — a curated catalog of AI skills for Claude Code, Cursor, Copilot, Codex, Gemini, and more.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.