agent-browser

A command-line tool for controlling a headless web browser. It lets an agent open pages, inspect elements, click, fill forms, take screenshots, and read page content.

In plain words
What is it for?
Use it to browse websites, submit forms, inspect page structure, scrape or read content, and capture screenshots.
Why use it?
It provides a repeatable way to work with web pages without relying on fragile page selectors. The agent can identify elements by references from the page's accessibility tree.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,582 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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.01582
Opus 5 $0.00028 $0.00791
Sonnet 5 $0.00011 $0.00316
Haiku 4.5 $0.00006 $0.00158

Measured yesterday against content hash ee5f17106fc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

agent-browser/skills/agent-browser/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-browser

Overview

agent-browser is a CLI that gives AI agents direct control over headless browsers. It uses a ref-based interaction model: every interactive element receives a unique reference identifier (@e1, @e2, etc.) derived from the accessibility tree. This enables deterministic, token-efficient browser automation without fragile CSS selectors.

Prerequisites

Ensure agent-browser is installed and the browser binary is available:

# Check installation
agent-browser --version

# Install globally
npm install -g agent-browser
agent-browser install

# On Linux, include system dependencies
agent-browser install --with-deps

Core Workflow: The Ref Cycle

Every browser interaction follows a strict cycle:

open URL → snapshot → read refs → interact → re-snapshot → repeat
  1. Navigate to the target page with open
  2. Snapshot to obtain the accessibility tree with refs
  3. Read the snapshot output — identify target elements by their refs
  4. Interact with elements using their refs (click @e1, fill @e2 "text")
  5. Re-snapshot after any action that changes the DOM

Critical rule: Refs are invalidated after navigation or significant DOM changes. Always take a fresh snapshot before interacting with elements after any page change.

Command Quick Reference

Command Syntax Purpose
open agent-browser open <url> Navigate to URL
snapshot agent-browser snapshot [-i] [-c] [-d N] [-s "sel"] Get accessibility tree with refs
click agent-browser click @eN [--new-tab] Click element
dblclick agent-browser dblclick @eN Double-click element
fill agent-browser fill @eN "text" Clear field and type text
type agent-browser type @eN "text" Type without clearing
focus agent-browser focus @eN Focus element
select agent-browser select @eN "option" Select dropdown option
check agent-browser check @eN Check checkbox
uncheck agent-browser uncheck @eN Uncheck checkbox
hover agent-browser hover @eN Hover over element
press agent-browser press <key> Press keyboard key
scroll agent-browser scroll <dir> <amount> Scroll page
screenshot agent-browser screenshot [--annotate] Capture screenshot
set headers agent-browser set headers '{...}' Set request headers

Read the full file on GitHub · 147 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 147 lines · 56 tokens per session scan A ee5f17106fc9

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,582 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 2026-08-31.

Related

Other skills, from other repositories

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

mintlify-preview

Run the public Mintlify product docs site locally for live preview. Use when previewing or iterating on docs under docs/ (.mdx/.md pages, docs.json nav), or when the user says "start the docs", "run mintlify", "preview the docs site".

latitude-dev/latitude-llm · 69 tokens