1
Artemonim (Artemonim) 2
You could create a huge TODO.md file right now and ask Agent to complete all the tasks in it.
- But that wouldn’t be economically efficient. At least until Context_summarize_tool is implemented.
- And also, Cursor has a limit of 2 hours for working on a single request, yes.
hmeng (Haris M) 3
jonbride (Jonathan Bride)
4
I haven’t tested this, but someone has implemented their own Cursor version of the Ralph method:
Agree this would be helpful. The first step would need to be something that looks a lot like Plan mode, but decomposes large work into a lot of small tasks.
Liviu_Oprisan (Liviu Oprisan) 6
I’m testing Claude and just discovered this tool they have. A better implementation in Cursor would be amazing. I like Cursor’s ease of use but it feels like it’s spending it’s energy in the wrong directions. Ralph Wiggum with good context management, subagents and good prompts would be the right direction I think.
I’ve been using that Cursor CLI based harness for a day or two now and it’s awesome. Cursor should definitely integrate this as a stock feature, especially for larger plans.
Got mine to work on Cursor.
Use with caution. I have tested it on one of my features of an app i am developing and it worked through 15 user stories on 5 iterations.
it works, at least on linux it does, I cant get it it to work on WSL.