The real reason why plan mode is dead is because you can just conversationally instruct the agent to not make changes to the repository or to make changes to selected documents only, and it will listen. There was a time when we needed to enforce this via selected tool use, but we have surpassed that.
Plan mode does have different permission controls though? Its difficult for me to parse the docs on this but it does seem to imply more than just a prompt although less than a full sandbox. <a href="https://code.claude.com/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode" rel="nofollow">https://code.claude.com/docs/en/permission-modes#analyze-bef...
The way it worked originally was it would trigger a different system prompt, and then the permissions system would prompt you (even on YOLO mode) before running any non-readonly actions.
Cursor would also write a plan document, which was useful when working on larger tasks (due to context size). I still find that part useful today.
Plan forced the model to write down and outline what it was going to do before writing the code. As Boris said up thread, he created it to prevent it from just rushing into writing code. So that regard, it did act like a permission system.
It helps to think more abstractly when approaching problems like this.
tcdent · · focus · HN ↗
Feathercrown · · focus · HN ↗
monster_truck · · focus · HN ↗
ImaCake · · focus · HN ↗
fy20 · · focus · HN ↗
Cursor would also write a plan document, which was useful when working on larger tasks (due to context size). I still find that part useful today.
8note · · focus · HN ↗
genxy · · focus · HN ↗
It helps to think more abstractly when approaching problems like this.