Hey great question! It has a universal tool called plan and run-code, so basically when it gets a task it will determine what API access it has in the GitHub codespace, for example:

Write me a 10 Slides google slides presentation on the current news -> Claude will hit the plan tool -> come up with plan and recognize it has access to a codespace with the googleapis npm installed and it has a scoped Google User Token -> it will then write code to create the slide deck -> You can then approve or deny that code -> if approved the code is executed to create the slide deck -> then you can approve whether to share the result with Claude or not

Got it! In the future I think you can actually cache and reuse this code, and some flows will run automagically!

Hey yeah! We actually support this, so any code you want to execute you can save it as a reusuable code snippet that we call a "keyboard-shortcut".