I filled in [email protected] and test-password-123, clicked Sign up, and the page showed a welcome message. One image and the favicon failed to load.
What the page shows after submitting
- The heading is still "Join Recipe Club", and the form is still there with both fields filled in.
- A new paragraph reads exactly: "Welcome, [email protected]!". The email is shown in all caps, although I typed it in lowercase.
- Below that is an image with the alt text "logo". It is the one that failed to load (see below).
Resources that failed to load
GET http://127.0.0.1:8765/missing.png(Image) returned 404. This looks like the "logo" image, so it probably shows as broken.GET http://127.0.0.1:8765/favicon.icoreturned 404.- The page document itself (
index.html) loaded with a 200.
I did not check the browser console for JavaScript errors beyond the network requests above.
How it was tried: I installed agent-browser 0.27.0 into a temporary folder (not globally) and ran it with a throwaway home directory, restricted to one local test page I built (a sign-up form with a deliberately missing image and an email-uppercasing handler). Only Skill and agent-browser commands were allowed, with no logins or other sites. The browser download step was not run. I repeated the same steps by hand and got the same page text and the same two 404s. Not tried: logging in, the credential vault, Slack, Electron apps, recording, and any real website.
What it does
A short discovery file for agent-browser, a fast browser automation command line tool for AI agents. It drives Chrome or Chromium over the DevTools protocol and uses accessibility-tree snapshots with compact element refs, with no Playwright or Puppeteer dependency.
How it works
- Install the program once:
npm i -g agent-browser && agent-browser install. - This file is only a stub. Before any command, the agent loads the real guide from the CLI with
agent-browser skills get core, so the instructions always match the installed version. - Specialized guides cover Electron desktop apps, Slack, exploratory testing and QA, deriving an API client from recorded traffic, Vercel Sandbox, protected Vercel deployments and AWS Bedrock AgentCore cloud browsers.
- An optional observability dashboard runs on port 4848.
Good for
Website automation, form filling, screenshots, data extraction and web app testing. It controls a real browser and can log in to sites: read the risk note first.
High risk: This package is only a short pointer file. It tells the agent to install a global npm program (`npm i -g agent-browser && agent-browser install`) and load the real instructions from it, so the actual guidance is not in this package and changes with the installed version. The program drives a real Chrome: it can open sites, click, fill and submit forms, log in (it has a credential vault), run JavaScript on pages, upload files and record traffic and video, and it can automate desktop apps and Slack. It can act on anything the browser is logged into. Use a separate session or profile, restrict domains where you can, and avoid accounts you cannot afford to touch. Needs Node.js and network access. Tried once on a local test page in an isolated setup (throwaway home, localhost only, no logins): it filled and submitted a form and listed failed requests correctly. Logins, credential vault, Slack, desktop apps, recording and real sites were not tried; the model left its browser session open.