flâneur

How I use Claude Code on large projects - Blog - LocalCan™

localcan.com · 2,563 words · saved by 1 readers

A workflow built on context management, lead/implementer/reviewer agents, and ruthless planning. What works for me on multi-repo, multi-language codebases.

The thing nobody warned me about with AI coding, once I started leaning on it for serious work, is that the bottleneck stops being the code. It becomes context. The agent will happily write whatever you ask, but if it doesn't know what the rest of the system looks like, what the constraints are, or what's already been decided, you get something that compiles, looks clean, and is wrong in ways you only spot a week later. So this post is really about context management. And there's a reason that matters so much. LLMs run on the transformer architecture, whose core mechanism is attention:…

saved by

related reading