agent-browser

A command-line browser controller for opening web pages, interacting with forms and buttons, extracting page content, and taking screenshots. It can automate a headless browser, which runs without a visible browser window.

In plain words
What is it for?
Use it to browse sites, log in through a browser, click or fill page controls, inspect interactive elements, test web apps, and capture screenshots.
Why use it?
It handles repetitive browser actions and helps verify how a web page or web app behaves.

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

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 915 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 $0.00041 $0.00915
Opus 5 $0.00020 $0.00458
Sonnet 5 $0.00008 $0.00183
Haiku 4.5 $0.00004 $0.00092

Measured 3d ago against content hash 7b322d14daab, 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 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.

templates/en/common_skills/agent-browser/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-browser — Browser Automation CLI

A headless browser automation tool by Vercel Labs. Open web pages, interact with elements, extract information, and take screenshots.

Installation

If not already installed:

npm install -g agent-browser && agent-browser install
  • npm install -g agent-browser: Install the CLI
  • agent-browser install: Download Chrome for Testing (first time only; add --with-deps on Linux)

Verify installation:

agent-browser --help

Basic Workflow

1. open <url>        → Open a page
2. snapshot -i       → Get interactive element snapshot (refs: @e1, @e2, etc.)
3. click/fill/scroll → Interact using refs
4. snapshot -i       → Re-check state after interaction
5. screenshot        → Save screenshot if needed

Important: Always run snapshot -i before interacting to get element refs.

Command Reference

Navigation

agent-browser open <url>
agent-browser back
agent-browser forward
agent-browser reload
agent-browser close

Snapshot (Page Structure)

agent-browser snapshot          # Full page
agent-browser snapshot -i       # Interactive elements only (recommended)
agent-browser snapshot -c       # Compact view
agent-browser snapshot -d 3     # Depth-limited

Element Interaction

agent-browser click @e1
agent-browser dblclick @e1
agent-browser fill @e2 "text"           # Clear and type
agent-browser type @e2 "text"           # Append text
agent-browser hover @e1
agent-browser check @e1                 # Checkbox on
agent-browser uncheck @e1               # Checkbox off
agent-browser select @e1 "value"        # Dropdown select
agent-browser press Enter               # Key press
agent-browser scroll down 500           # Scroll
agent-browser scrollintoview @e1        # Scroll element into view

Wait

agent-browser wait 1500              # Wait milliseconds
agent-browser wait @e1               # Wait for element
agent-browser wait --text "Success"  # Wait for text
agent-browser wait --load networkidle  # Wait for network idle

Read the full file on GitHub · 145 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. 3d ago First seen · 145 lines · 41 tokens per session scan A 7b322d14daab

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository xuiltul/animaworks (254 stars, last pushed 3d ago), licensed Apache-2.0. It adds 41 tokens to every session and 915 once invoked, about $0.0002 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

hive.browser-automation

Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…

aden-hive/hive · 142 tokens

hive.linkedin-automation

Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…

aden-hive/hive · 99 tokens

hive.x-automation

Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…

aden-hive/hive · 81 tokens

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens

hive.telegram-notifications-setup

Set up a Telegram notification channel (Sentinel) for a colony by driving the browser — create a bot via @BotFather in Telegram Web, store its token, detect the chat to notify, and turn Sentinel on so the colony can ping the user on Telegram and accept replies. Use when the user asks to "set up Telegram…

aden-hive/hive · 121 tokens

browser-edge-cases

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.

aden-hive/hive · 40 tokens