Question
As the staff engineer, you're asked to author the team's shared AGENTS.md / house-rules file — the standing context every engineer's AI agent loads on every task in your large Python service. The goal is that agents produce code that fits your conventions on the first try, across many different contributors. What goes in this file, what's a waste of tokens to include, and what's the most common mistake teams make when they write one?
Treat the AI’s output as a draft to verify, not an answer to trust. Name the specific flaw and the input that triggers it, say how you’d catch it — tests, edge cases, reading critically — and how you’d re-prompt or decompose to get it right.
Vibe coding: describe the solution in plain language (or narrate it) and the coach grades your approach. Generating runnable code from your description is coming next.