agent-browser

agent-browser is a skill for Claude Code, Codex from davekilleen/Dex. It costs 77 tokens per session (1,497 once invoked), scanned A, original, no licence file.

A guide to browser automation with Vercel's agent-browser command-line tool. Browser automation means controlling web pages through software.

In plain words
What is it for?
Use it to open websites, click controls, fill in forms, take screenshots, and scrape page content.
Why use it?
It provides a way to interact with pages when manual clicking would be slow or when information must be collected repeatedly.

Skill for Claude CodeCodex

Part of the compound-engineering plugin — 15 skills, 19 commands shipped together

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

Made for: Claude Code, Codex.

Or install compound-engineering, the plugin that ships this one along with the rest of its 15 skills, 19 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.

agentmods badge for agent-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/davekilleen/dex/agent-browser.svg)](https://agentmods.dev/skills/davekilleen/dex/agent-browser)
Your own site
<a href="https://agentmods.dev/skills/davekilleen/dex/agent-browser"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/agent-browser.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00077 $0.01497
Opus 5 $0.00039 $0.00749
Sonnet 5 $0.00015 $0.00299
Haiku 4.5 $0.00008 $0.00150

Measured yesterday against content hash fd63d41d4a9d, 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.

.claude/plugins/compound-engineering/skills/agent-browser/SKILL.md · 224 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 4d ago First seen · 224 lines · 77 tokens per session scan A fd63d41d4a9d

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository davekilleen/Dex (474 stars, last pushed today), with no licence file. It adds 77 tokens to every session and 1,497 once invoked, about $0.0004 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

ha-browser

Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…

shiwenwen/hope-agent · 140 tokens

seo-content

Heuristic content/GEO-readiness analysis of the visible text from seo-crawl. No network. Judgments are heuristic (marked Estimated); raw counts are Measured.

Orkas-AI/Orkas · 2 tokens

playwright-recording

Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.

calesthio/OpenMontage · 53 tokens

render-imessage-chat

Assemble an iMessage chat-reveal video ad from a thread JSON — one continuous Playwright recording of the conversation animating in (typing dots, composer typing, bubble pops, auto-scroll) crossfaded into a designed end card, with iMessage send/receive SFX and an optional ducked music bed. FREE assembly (Playwright +…

gooseworks-ai/goose-skills · 112 tokens

google-ad-scraper

Scrape competitor ads from Google Ads by domain. Returns ad creatives, formats, and campaign details. Use for competitive ad research and messaging analysis.

gooseworks-ai/goose-skills · 35 tokens

dev-browser

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…

code-yeongyu/oh-my-openagent · 84 tokens