How I Use Claude Code

@Yesterday

Recent fanfare around Claude Code compels me to write down what I know.

  1. It is an incredibly intuitive product.
  2. Leveraging Plan Mode is key. I have a simple heuristic; the more time I spend in plan mode, the better off I am.
  3. Phase-based updates and planning are good.
  4. Diagrams are good.
  5. Building context in a mono repo is good. Context is nothing more than past work and past files, in a literal sense.
  6. Opus 4.5 was a real unlock; its amazing.

Things I don’t use enough

  1. Structured permissions for my Claude → it’s dumb that I have to issue permissions for every bash command.
  2. Custom agents → there are things I can do to create common agents. One idea is to have my Claude Code review my entire history and suggest some options for improvement.
  3. Structured workflows
    1. tests
    2. PR templates
    3. reviewer/optimizer agents
  4. Git worktrees

Things I don’t believe in:

  1. Letting the model run freely (some might say amok) in a Gas Town like approach. I don’t say this from a critical perspective. I just think it depends on having a ton of credits.
  2. That engineers are obsolete; systems depend on humans understanding them. Systems no one understands are systems no one can fix. Engineers are so important for good design.