AutoGineer
Generated banner for Dev Browser
Generated logo for Dev Browser

Dev Browser

Sawyer HoodCommunityCreated by Sawyer Hood

  • Skill
  • Tool integration
  • Automation and integrations
  • MIT
  • Low risk
Download ZIP

From the author

Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, log into sites, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", "open the browser", or any browser interaction request.
— the description by Sawyer Hood

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

dev-browser is a command-line interface that enables browser automation by controlling a persistent Chrome instance. It allows users to execute Puppeteer scripts to navigate websites, interact with elements, and extract data. By using named pages, the tool maintains state across multiple script executions, making it suitable for complex workflows like logging into sites or multi-step web interactions.

What it does

  • Provides a CLI to control a real Chrome browser instance.
  • Supports persistent named pages that maintain state between separate script runs.
  • Allows execution of custom Puppeteer scripts for web interaction.
  • Enables capturing screenshots and ARIA tree snapshots for debugging.
  • Supports file uploads and PDF generation via browser automation.
  • Offers a headless mode for background task execution.

When to use it

  • When you need to automate repetitive browser tasks like form filling or data scraping.
  • When you require a persistent browser session to maintain login states.
  • When you need to test web application interactions programmatically.
  • When you want to capture visual or structural snapshots of a webpage.

Advantages

  • Persistent state across runs via named pages.
  • Uses standard Puppeteer syntax for familiar automation.
  • Lightweight CLI interface for quick script execution.
  • Supports both headed and headless browser modes.

Usage examples

“Go to https://example.com and take a screenshot.”
The agent uses dev-browser to navigate to the specified URL and saves a screenshot of the page to the current working directory.
“Click the login button on the page named main.”
The agent retrieves the persistent 'main' page and executes a click command on the specified element reference.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/sawyerhood/dev-browser/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip dev-browser.zip -d .agents/skills

Documentation by Sawyer Hood

dev-browser

CLI for controlling a real Chrome with short Puppeteer scripts. One warm daemon; named pages persist between runs.

npm install -g dev-browser   # bun add -g dev-browser works too; the first run downloads the binary if the install script was blocked
dev-browser install          # only if the first run says "No Chrome found"

Run dev-browser --help (full guide; dev-browser help <topic> for one section) before non-trivial work. Quick start:

dev-browser <<'EOF'
const page = await browser.getPage("main");        // named page persists across runs
await page.goto("https://example.com");            // default waitUntil: domcontentloaded
await page.snapshot({ interactive: true })         // ARIA tree with refs; last expression is printed
EOF
dev-browser -e 'const p = await browser.getPage("main"); await p.click("ref/e6"); await p.waitForLoad(); p.url()'

Gotchas: end lines with semicolons (a line starting with ( continues the previous one); return an object as ({ a, b }); page.click never waits (use waitForSelector first); page names are per browser (--headless and headed are separate Chromes and profiles); refs reset on navigation — re-snapshot; file paths resolve against your cwd (uploadFile, screenshot/pdf path); do not run parallel dev-browser calls against the same named page.

Files

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Node.js

Security

What our scanner noticed· Low risk

  • Instructions that use the network

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Sawyer Hood
Publisher
Sawyer Hood (Community)
Source
SawyerHood/dev-browser · skills/dev-browser · commit 520ba5c
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Sawyer Hood.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download dev-browser.zip