Like a manual sub agents approach. I try not to pollute the Claude code session context with meanderings to much. Do that in the chat and bring the condensed ideas over.

If you tell it to use linters and other kinds of code analysis tools it takes it to the next level. Ruff for Python or Clippy for Rust for example. The LLM makes so much code so fast and then passes it through these tools and actually understands what the tools say and it goes and makes the changes. I have created a whole tool chain that I put in a pre commit text file in my repos and tell the LLM something like "Look in this text file and use every tool you see listed to improve code quality".

That being said, I doubt it can turn a non-dev into a dev still, it just makes competent devs way better still.

I still need to be able to understand what it is doing and what the tools are for to even have a chance to give it the guardrails it should follow.