What is advanced-commands?

A collection of advanced command examples for agent-browser, including accessibility snapshots, JavaScript evaluation, screenshots, PDFs, and closing sessions.

Use it to capture full or focused page snapshots, inspect page values with JavaScript, take screenshots, create PDFs, and close browser sessions.

It provides ready-made commands for inspecting pages and collecting information beyond basic browser clicks.

advanced-commands — Command for Claude Code by full-stack-skills: A collection of advanced command examples for agent-browser, including…

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.

agentmods

npx agentmods add commands/full-stack-skills/agent-skills/advanced-commands

Clone the repo

git clone --depth 1 https://github.com/full-stack-skills/agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 15 skills, 2 commands.

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/commands/full-stack-skills/agent-skills/advanced-commands.svg)](https://agentmods.dev/commands/full-stack-skills/agent-skills/advanced-commands)

Your own site

<a href="https://agentmods.dev/commands/full-stack-skills/agent-skills/advanced-commands"><img src="https://agentmods.dev/badge/commands/full-stack-skills/agent-skills/advanced-commands.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 581 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00581
Opus 5	$0.00000	$0.00291
Sonnet 5	$0.00000	$0.00116
Haiku 4.5	$0.00000	$0.00058

Measured 5d ago against content hash 174a1231c66c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

advanced-commands 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.

skills/agent-browser/examples/commands/advanced-commands.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Advanced Commands | 高级命令

官方文档: https://github.com/vercel-labs/agent-browser/blob/main/README.md

Instructions

This example demonstrates how to use advanced agent-browser commands.

Key Concepts

Snapshot command
Eval command
Screenshot and PDF
Close command
Command options

Example: Snapshot

# Basic snapshot (accessibility tree with refs)
agent-browser snapshot

# Interactive snapshot
agent-browser snapshot -i

# Compact snapshot
agent-browser snapshot -c

# Snapshot with depth limit
agent-browser snapshot -d 2

# Snapshot specific element
agent-browser snapshot -s "main"

# Full snapshot
agent-browser snapshot --full

# Snapshot with JSON output
agent-browser snapshot --json

Example: Eval

# Evaluate JavaScript
agent-browser eval "document.title"

# Evaluate with return value
agent-browser eval "document.querySelector('h1').textContent"

# Evaluate complex expression
agent-browser eval "Array.from(document.querySelectorAll('a')).map(a => a.href)"

Example: Screenshot and PDF

# Take screenshot
agent-browser screenshot output.png

# Screenshot full page
agent-browser screenshot output.png --full

# Generate PDF
agent-browser pdf output.pdf

# PDF with options
agent-browser pdf output.pdf --format A4 --print-background

Example: Close

# Close current page
agent-browser close

# Close all pages
agent-browser close --all

Example: Snapshot Workflow

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

# 2. Get snapshot with refs
agent-browser snapshot -i --json

# 3. Use refs from snapshot
agent-browser click @e1
agent-browser fill @e2 "text"

# 4. Snapshot again after interaction
agent-browser snapshot --json

Example: Eval Workflow

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

# Extract data using eval
agent-browser eval "document.querySelectorAll('article').length"

# Get all links
agent-browser eval "Array.from(document.querySelectorAll('a')).map(a => ({text: a.textContent, href: a.href}))"

# Check if element exists
agent-browser eval "!!document.querySelector('.modal')"

Read the full file on GitHub · 124 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.

5d ago First seen · 124 lines · 0 tokens per session scan A 174a1231c66c

Subscribe to this mod's changes

advanced-commands is a command published in the GitHub repository full-stack-skills/agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 581 tokens. 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.

Browser automation

advanced-commands