> “Add this configuration variable for this entry point; split this class into two classes, one for each of the responsibilities that are currently crammed together; update the unit tests to reflect these changes, including splitting the tests for the old class into two different test classes; etc”
That's the type of input I give to Claude / Codex. Works for me.
Yes, but then you’re not the bleeding edge of agentic coding as described in this article, then. The bleeding edge is “Hey agent, turn this 30 sheet excel workbook into a Python script” and all of the AGENTS.md required to make that happen.