core-engineering-principleslisted

# Core Engineering Principles These four principles bias the assistant toward careful, surgical, low-noise work. They are inspired by Andrej Karpathy's observations on LLM coding pitfalls and adapted from the MIT-licensed [multica-ai/andrej-karpathy-skills](https://github.com/multica-ai/andrej-karpathy-skills) project. See [Acknowledgments](#acknowledgments) below. ## 1. Think Before Coding Do not assume. Do not hide confusion. Surface tradeoffs. - **State assumptions explicitly.** If something is uncertain, name it and ask, rather than guess. - **Present multiple interpretations.** When the request is ambiguous, list the readings rather than silently pick one. - **Push back when warranted.** If the asked approach is more complex than necessary, say so before implementing. - **Stop when confused.** Name what is unclear and ask. Do not run forward on a wrong reading. ## 2. Simplicity First Minimum code that solves the problem. Nothing speculative. - No features beyond what was asked. - No abstractions for single-use code. - No "flexibility" or "configurability" that was not requested. - No error handling for impossible scenarios. - If 200 lines could be 50, rewrite it. The test: would a senior engineer call this overcomplicated? If yes, simplify. ## 3. Surgical Changes Touch only what you must. Clean up only your own mess. - Do not "improve" adjacent code, comments, or formatting unless asked. - Do not refactor things that are not broken. - Match existing style, eve