agent-browser

agent-browser is a skill for Claude Code from ckorhonen/claude-skills. It costs 53 tokens per session (6,178 once invoked), scanned A, original, MIT.

A command-line tool for controlling a headless browser, which is a browser that runs without a visible window. It lets an agent find page elements, navigate sites, fill forms, and read web content.

In plain words
What is it for?
Use it to scrape pages, submit forms, test web applications, monitor page changes, capture screenshots, or generate PDFs.
Why use it?
It removes the need to manually operate a browser or guess fragile selectors when automating websites. Stable element references help the agent target the right controls consistently.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-skills plugin — 62 skills, 4 commands, 7 agents shipped together

Good fit Use it to scrape pages, submit forms, test web applications, monitor page changes, capture screenshots, or generate PDFs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckorhonen/claude-skills/agent-browser
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.

Any agent
npx skills add ckorhonen/claude-skills --skill agent-browser
Clone the repo
git clone --depth 1 https://github.com/ckorhonen/claude-skills

Made for: Claude Code.

Or install claude-skills, the plugin that ships this one along with the rest of its 62 skills, 4 commands, 7 agents.

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 agent-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckorhonen/claude-skills/agent-browser/github.svg)](https://agentmods.dev/skills/ckorhonen/claude-skills/agent-browser)
Your own site
<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/agent-browser"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/agent-browser/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 agent-browser

Your own site · 80×15
<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/agent-browser"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,178 The whole file, excluding the scripts and references it only reads on demand.
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.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.06178
Opus 5 $0.00026 $0.03089
Sonnet 5 $0.00011 $0.01236
Haiku 4.5 $0.00005 $0.00618

Measured 10d ago against content hash 7fb892509110, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-browser 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 10d 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.

skills/agent-browser/SKILL.md · 1,003 lines

How it starts

The opening of the file, as written. The whole thing — 1,003 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-browser CLI

A headless browser automation CLI designed for AI agents, with fast Rust-based execution and element refs optimized for LLM reasoning.

Overview

agent-browser provides programmatic browser control through a CLI that's purpose-built for AI agent workflows. It uses deterministic element references (@e1, @e2, etc.) from accessibility trees, making it ideal for LLM-based automation where consistent element targeting is critical.

Key Features:

  • Fast Rust-based CLI with Node.js fallback
  • Element refs (@e1, @e2) for stable LLM reasoning
  • Session isolation for parallel browser instances
  • JSON output for programmatic parsing
  • Accessibility tree snapshots for element discovery
  • CDP connection support for existing browser instances

When to Use

  • Automating web interactions (form filling, clicking, navigation)
  • Scraping web content with accessibility tree parsing
  • Testing web applications programmatically
  • Multi-agent scenarios requiring isolated browser sessions
  • Screenshot capture and PDF generation
  • Monitoring web page state changes

Prerequisites

  • Node.js >= 18 or Bun runtime
  • Chromium (installed via agent-browser install)

Installation

# Install globally
bun install -g agent-browser

# Download Chromium
agent-browser install

# Linux with system dependencies
agent-browser install --with-deps

Verify installation:

agent-browser --version

Quick Start

# Navigate to a page
agent-browser open https://example.com

# Get accessibility snapshot with element refs
agent-browser snapshot -i  # -i = interactive elements only

# Click an element by ref
agent-browser click @e2

# Fill a form field
agent-browser fill @e3 "[email protected]"

# Take a screenshot
agent-browser screenshot output.png

Core Workflow

1. Open Page and Snapshot

# Open URL
agent-browser open https://example.com

# Get interactive elements with refs
agent-browser snapshot -i --json

The snapshot returns elements like:

@e1 link "Home"
@e2 textbox "Email"
@e3 button "Submit"

Read the full file on GitHub · 1,003 lines

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. 10d ago First seen · 1,003 lines · 53 tokens per session scan A 7fb892509110

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 6,178 once invoked, about $0.0003 per session on Opus 5. 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.

Related

Other skills, from other repositories

dingtalk_channel_connect

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.

agentscope-ai/QwenPaw · 69 tokens

dingtalk_channel_connect

A browser-based procedure for connecting a QwenPaw bot to DingTalk, a workplace messaging platform. It covers creating or configuring the application and publishing the finished bot.

agentscope-ai/QwenPaw · 78 tokens

browser_cdp

Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.

agentscope-ai/QwenPaw · 70 tokens

browser_cdp

Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.

agentscope-ai/QwenPaw · 85 tokens

browser_visible

Browser launch controls for choosing whether a Chromium-based browser window is visible, which browser program to run, and which startup options to pass.

agentscope-ai/QwenPaw · 108 tokens

browser_visible

Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…

agentscope-ai/QwenPaw · 75 tokens