Comment by tcdent
1 day ago
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.
It seems unwise not to implement sandbox measures just because the chance of misuse has gotten lower.
Plan was never a sandbox or a permissions system
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. https://code.claude.com/docs/en/permission-modes#analyze-bef...
2 replies →
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.
Yes, but plan mode wasn’t that.
You can use Docker’s sbx or similar VM/containers for that.
What? Nothing to do with that
It also doesn't allow leaving an audit trail of plans and decisions (by default, anyway). Most of my mutating prompts look like "Propose a plan for change X and write to file Y" and "Execute steps M-N from file Y".
RE the article: I don't think it's obvious why this process is worth following until you find your time and attention wasted. Conversationally-building is the express train to waste. I'm not sure why you would even be talking to claude if you don't understand what you want to build.
I agree. Plan mode came about because earlier models were loose cannons, doing what they pleased. Today's models follow instructions better enough to not need a separate mode. However, there is still value in using a separate, smarter model for planning than execution, and persisting it for auditing on completion.
If you do use plan mode you might like https://plannotator.ai/
I typically converse with the default model to point the plan in the right direction, then have it iterate with a smarter reviewer to find flaws until the plan file is converged.
Do you really trust it with a production code base or database? Telling it not to make changes feels an awful lot like "Make no mistakes". I also like how Plan mode on Codex asks clarifying questions. I'm in management now so I've used Work more than Code lately.
true dat