Repository navigation
Request: 'stash' prompt drafts (to write a different one first) #4479
Description
What feature would you like to see?
Use case:
I'm writing a very long prompt. Then I decide I want to use a different model (such as gpt-5-codex-high). I want to "stash" the prompt draft, run /model, and then return to editing my prompt.
Are you interested in implementing this feature?
No response
Additional information
No response
Activity
etraut-openai commentedon Nov 28, 2025
Thanks for the feature request. This hasn't received any upvotes in over two months, so I'm going to close.
jtheisen commentedon Oct 7, 2026
I think this may now be worth thinking about again, because now Codex allows session management.
Having session management, it's much more desirable to either
in order to clarify stuff in a different session before continuing.
sourabhshegane commentedon Oct 10, 2026
In case it helps anyone landing here: prompt-shelf wraps the
codexCLI and adds this. Ctrl+F parks the draft and clears the box, you run/modelor anything else, then Ctrl+Q brings the draft back. It also keeps named lists for things you reuse or want to come back to (for example "Ideas", "To explore", "Common"), so a passing thought or a prompt you type every day is one Ctrl+Q away too. Disclosure: I'm the author.