Comment by brokencode
1 day ago
You can just tell it to write out a plan.md file.
I greatly prefer this, since it lets me iterate on the plan with Claude for a while without it repeatedly asking if I’m ready to implement the plan.
Once I’m satisfied, I usually start a fresh session and tell it to implement the plan.
For smaller plans, you don’t need the file. Just ask it to come up with a plan. I don’t recall the last time it just started implementing if I only asked for a plan.
This is the process I generally use too. Small plans you can just ask for, and big plans you work through building a plan.md file before you build it.
That also makes it easier to adversarially review the plan (I have Fable write the plan, then review it with Astra and another Fable instance).