nico λ

“Math ain’t about numbers. If you think math is about numbers, you probably think that Shakespeare is all about words. You probably think that dancing is all about shoes. You probably think that music is all about notes. Math ain’t about numbers. Math is about logic, it’s about beauty, it’s about connections, it’s about how you get from one place

1. CLAUDE.md is for onboarding Claude into your codebase. It should define your project's WHY , WHAT , and HOW .


2. Less (instructions) is more . While you shouldn't omit necessary instructions, you should include as few instructions as reasonably possible in the file.


3. Keep the contents of your CLAUDE.md concise and universally

• This is gonna be game-changing for the next 2-4 weeks before they nerf the model.
  
  Then for the next 2-3 months people complaining about the degradation will be labeled “skill issue”.
  
  Then a sacrificial Anthropic engineer will “discover” a couple obscure bugs that “in some cases” might have lead to less than optimal performance. Still largely a user

• Set fixed limits : Set explicit upper bounds on loops, queues, and other data structures. Fixed limits prevent infinite loops and uncontrolled resource use, following the fail-fast principle. This approach helps catch issues early and keeps the system stable.

• Limit function length : Keep functions concise, ideally under 70 lines . Shorter functions are easier to understand, test, and debug. They promote single responsibility, where each function does one thing well, leading to a more modular and maintainable codebase.

• Centralize control flow : Keep switch or if statements in the main parent function, and move non-branching logic to helper functions. Let the parent function manage state, using helpers to calculate changes without directly applying them. Keep leaf functions pure and focused on specific computations. This divides responsibility: one function

• Simple and explicit control flow : Favor straightforward control structures over complex logic. Simple control flow makes code easier to understand and reduces the risk of bugs. Avoid recursion if possible to keep execution bounded and predictable, preventing stack overflows and uncontrolled resource use.