Coordinate sub-agents to monitor PRs and fix prod bugs
A Cursor Projects coordinator agent delegates to sub-agents, watches new PRs and production bugs, spins up agents to fix issues, and surfaces questions to the user.
A frontend developer pairs Claude in Chrome with Claude Code to open the app, click through it, read the DOM, check console errors and network requests, and fix UI bugs.
A frontend developer pairs Claude in Chrome with Claude Code to open the app, click through it, read the DOM, check console errors and network requests, and fix UI bugs.
The author uses the Claude in Chrome extension, which sits in the browser sidebar. It can navigate pages, click buttons, read DOM elements, check console errors and monitor network requests. Paired with Claude Code in the terminal, the loop is: write code, have Claude open it in Chrome, test it and spot problems.
The readable part of the article is only the introduction. It says the author no longer has to switch tabs or reproduce errors by hand, but gives no specific bugs, numbers or failures.
The article is member-only and cuts off early. Claude in Chrome needs a paid plan (Pro, Team or Enterprise), and a reader comment raises concerns about what browser traffic it can see.
Open my app at [URL] in Chrome and reproduce this UI bug: [description]. Inspect the DOM, console errors and network requests to find the cause, then fix it in the code in [repo path]. Reload and confirm the bug is gone and nothing nearby has broken. Summarize the root cause and the change. Don't commit until I've reviewed the diff.
A Cursor Projects coordinator agent delegates to sub-agents, watches new PRs and production bugs, spins up agents to fix issues, and surfaces questions to the user.
Ran a Cursor agent continuously for 24 hours to build a project management tool; the app fully works but is not production ready.
The author had ChatGPT take the Session Buddy extension source from Chrome, port it to Safari and install it, taking about 20 minutes.