It's sure baffling how Anthropic has kept Claude Code's plan mode so linear and inflexible. It may ask a couple of questions before writing it, but there's always going to be parts that need editing. Yet there's no good "Sounds good, but it needs these edits" option after it presents you the plan. It gives you (paraphrased) "1. Proceed with auto-edits 2. Proceed without auto-edits 3. Cancel the plan". Note that 3 doesn't even write the plan to the file at all, even if it's 95% fine. So your options are either A. Pick 1 or 2, immediately press escape to interrupt, then tell it to make edits or B. Pick 3, tell it to make edits, after which it has to write the entire plan from scratch again.

This is such bad UX that it really feels like either 1. Anthropic employees don't use Claude Code much - this seems incredibly unlikely or 2. It's intended to burn output tokens as it has to write a huge plan again.

IMO Superpowers isn't the ideal solution because it too lacks flexibility, but including the "plan sketch" stage is sure an improvement.

Is that true? What is your experience of it?

For me, I am a solid KISS believer, so I have not yet found a better framework than just plain old Claude Code. But happy to move to a better workflow, if it's real.

Fetch and follow instructions from https://raw.githubusercontent.com/obra/superpowers/refs/head...

it's like curl|bash but with added LLM agents...

but maybe it's my fault.

I recommend trying. it doesn't hurt. Just don't believe it's a silver bullet. It's still the same Claude.

The way I use Claude is quite similar to what super powers does under the hood anyways. Like I always ask things like this: "if I want to do X, what questions do you need to ask me to have all the information you need to make it happen"