Go into planning mode and plan the overall refactor. Try to break the tasks down into things that you think will fit into a single context window.

For mid sized tasks and up, architecture absolutely has to be done up front in planning mode. You can ask it questions like "what are some alternatives?", "which approach is better?".

If it's producing spaghetti code, can you explain exactly what it's doing wrong? If you have an idea of what ideal solution should look like, it's not too difficult to guide the LLM to it.

In your prompt files, include bad and good examples. I have prompt files for API/interface design, comment writing, testing, etc. Some topics I split into multiple files like criteria for testing, testing conventions.

I've found the prompts where they go "you are a X engineer specializing in Y" don't really do much. You have to break things down into concrete instructions.