[pastel8739]

Today I literally gave Claude a single prompt, asking it to make a plan to implement a relatively simple feature that spanned a couple different codebases. It churned for a long time, I asked a couple very simple follow up questions, and then I was out of tokens. I do not consider myself to be any kind of power user at all.

[deaux]

The only time I've ever seen this happen is when you give it a massive codebase, without any meaningful CLAUDE.md to help make sense of it and no explicitly @ mentioning of files/folders to guide, and then ask it for something with huge cross-cutting.

> spanned a couple different codebases

There you go.

If you're looking to prevent this issue I really recommend you set up a number of AGENTS.md files, at least top-level and potentially nested ones for huge, sprawling subfolders. As well as @ mentioning the most relevant 2-3 things, even if it's folder level rather than file.

Not just for Claude, it greatly increases speed and reduces context rot for any model if they have to search less and more quickly understand where things live and how they work together.

[visarga]

I have a tool that scans all code files in a repo and prints the symbols (AST based), it makes orienting around easy, it can be scoped to a file or folder.

[fragmede]

> spanned a couple different codebases

It's either that, or you have a lot of skills loaded or something. I use Claude for hours a day and usually don't run out of tokens.