Hey everyone, Looking for your best tips to optimize token usage in Claude Code. My issue: I have a fairly heavy file stack ( multiple CLAUDE.md files, context files, auto-memory, etc.). Every new conversation starts with a large amount of cached tokens loaded before I even type my first message. I hit limits fast and can't work efficiently on longer tasks anymore. Would love to know: - How do you manage your context files to avoid loading everything each time? - Any practices to slim down /context or CLAUDE.md files? - Ways to structure a project so Claude doesn't load everything unnecessarily? for exemple : Cached: 54.9k | In: 954 | Out: 10.5k | Total: 54.9k -> after 1 message Thanks in advance!

1. Watch the intro video and introduce yourself in the intro post here 2. Start with The Foundation (free course). Concepts, folder architecture, prompting framework. Everything else builds on this. 3. Check in at the bottom of each lesson. Polls, discussion posts, other members working through the same stuff. Use them. 4. When you're ready to build real things, move to Implementation Playbooks (Level 2). When you're ready to build your own tools, Building Your Stack (Level 3). 5. Post your work. Ask questions. Help others when you can. What are you here to build?