A headless web browser for AI agents, meaning it loads and controls websites without showing a window. It is intended for data extraction and web automation as an alternative to Chrome or Chromium.

Use it to extract information from websites or automate website actions. It can connect to an agent through its MCP server.

It lets an agent work with websites without running a full visible browser. This can reduce the setup needed for automated browsing tasks.

lightpanda — Plugin by lightpanda-io

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.

Claude Code

/plugin marketplace add lightpanda-io/agent-skill

agentmods

npx agentmods add plugins/lightpanda-io/agent-skill/marketplace

Clone the repo

git clone --depth 1 https://github.com/lightpanda-io/agent-skill

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

lightpanda 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 2d 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-plugin/marketplace.json · 47 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "lightpanda",
  "owner": {
    "name": "Lightpanda",
    "email": "[email protected]"
  },
  "metadata": {
    "description": "Lightpanda browser for AI agents",
    "version": "1.0.0"
  },
  "plugins": [
    {
      "name": "lightpanda",
      "source": "./",
      "description": "Fast headless browser for AI agents - drop-in replacement for Chrome/Chromium for data extraction and web automation",
      "version": "2.1.0",
      "author": {
        "name": "Lightpanda"
      },
      "category": "automation",
      "keywords": [
        "browser",
        "headless",
        "web-scraping",
        "mcp",
        "automation",
        "lightpanda"
      ],
      "homepage": "https://lightpanda.io/docs",
      "strict": false,
      "skills": [
        "./",
        "./pandascript"
      ],
      "mcpServers": [
        {
          "lightpanda": {
            "command": "lightpanda",
            "args": ["mcp"]
          }
        }
      ]
    }
  ]
}

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.

2d ago First seen · 47 lines scan A 47a07498a97f

Subscribe to this mod's changes

lightpanda is a plugin published in the GitHub repository lightpanda-io/agent-skill (95 stars, last pushed 4d ago), licensed Apache-2.0. 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 Productivity

lightpanda

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

cli

hhru

dhm

kernel-sdks

webmcpify

realbrowser