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 nottelabs/notte-skillsnpx agentmods add plugins/nottelabs/notte-skills/nottegit clone --depth 1 https://github.com/nottelabs/notte-skillsGrade A, and why
notte 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 3d 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": "notte",
"version": "0.0.5",
"description": "Drive a real cloud or local browser with Notte \u2014 manage sessions and accounts from the CLI, and build, deploy, and repair Notte Functions",
"skills": "./skills/",
"mcpServers": "./.mcp.json",
"author": {
"name": "Notte",
"url": "https://notte.cc"
},
"repository": "https://github.com/nottelabs/notte-skills",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 3 skills, 2 MCP servers travel with it, and installing the plugin installs all of them — 346 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.
- 3d ago First seen · 14 lines scan A 07ed59990c64
notte is a plugin published in the GitHub repository nottelabs/notte-skills (11 stars, last pushed 5d 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.
Other plugins, from other repositories
actionbook
Actionbook MCP server for up-to-date browser automation. Get verified CSS/XPath selectors for any website directly into your agent context.
actionbook-scraper
Generate accurate web scraper code using Actionbook's verified selectors. Achieves 7.76x better data extraction accuracy.
browser-harness
Direct browser control via CDP. Drives the user's real Chrome (or a Browser Use cloud browser) with coordinate clicks, screenshots, and Python helpers — no selector hunting. Requires the one-time browser-harness CLI install (see the skill's references/install.md).
webcmd
Turn websites, browser sessions, desktop apps, and local tools into deterministic CLI surfaces for humans and AI agents.
claude-in-chrome
Drive your real, logged-in Chrome from Claude Code, and list tabs across readable Chrome and Chromium profiles. Exposes the extension's browser tools through the Claude in Chrome bridge and adds a read-only listopentabs tool backed by local session data. Driving requires the connected extension and a running Chrome.
browserjack
Use OpenAI's locally installed Codex browser runtime from Claude Code (macOS).