There seems to be so much value in planning, but in my organization, there is no artifact of the plan aside from the code produced and whatever PR description of the change summary exists. It makes it incredibly difficult to assess the change in isolation of its' plan/process.
The idea that Claude/Cursor are the new high level programming language for us to work in introduces the problem that we're not actually committing code in this "natural language", we're committing the "compiled" output of our prompting. Which leaves us reviewing the "compiled code" without seeing the inputs (eg: the plan, prompt history, rules, etc.)
I have a design doc subdirectory and instead of "plan mode" I ask the agent to write another design doc, based on a template. It seems to work? I can't say we've looked at completed design docs very often, though.
If branches are tied to linear ids then gh cli and linear mcp is enough for any model to get most of the why context from any commit
Have you considered having it write a plan.md file and saving it to git?