Feature request: The ability to queue up messages

Status Closed — not planned
Maintainer reply ✓ Yes — 8enmann
Activity 15 comments · opened Mar 16, 2025 · closed Jan 15, 2026
💡 Likely answer: A maintainer (8enmann, collaborator) responded on this thread — see the highlighted reply below.

I mostly just use Claude Code on auto-pilot mode, and say yes (and remember) to most things. It's great, and rarely needs correction! But it would be even better if I could queue up messages. For example, if I have it performing a long task, but think of something else I want done in the mean time, I can queue up the next message and let it run in the background. I was thinking perhaps by using a key combination when submitting. I've had many situations when this would be optimal. Just wanted to express interest in this as a feature idea, if anyone is interested in developing it. Thank you.

View original on GitHub ↗

15 Comments

8enmann collaborator · 1 year ago

Working on it!

max-sixty · 1 year ago

this is in!

mihailmariusiondev · 1 year ago

Hey any updates on this? it would be awesome

cyberhuman · 11 months ago

I miss this functionality, too! I have many ideas while pop up while Claude Code is vibing, but I can't queue them up immediately because they'll start interfering with the current to-do list. It would be nice to queue up the next task(s) so that it's picked up only after the current to-do list is done.

Melnikovartem · 10 months ago

+1 - this would really help improve the coding experience, as I often get ideas for the next milestones in the project while waiting for the agent to finish the current task.

FishRaposo · 10 months ago

Cursor has a feature similar to this, just having the option to schedule a message for after everything is done, rather than just the current task, would already be of MASSIVE help

trilliamn · 10 months ago

+1 - this would be a game changer for productivity. Tried this in Cursor and now I miss it in CC. Its especially useful in cases where I want to fully separate concerns to ensure the model isn't doing two things at once. I'd rather fully separate the requests and have them come one after another.

Maybe a simple UX could be:

While CC is executing some task, user types up a new prompt...

  • Enter: Inject directly into ongoing task (interrupting)
  • CMD+Enter: Queue up to send this message AFTER all tasks are completed.
github-actions[bot] · 8 months ago

This issue has been inactive for 30 days. If the issue is still occurring, please comment to let us know. Otherwise, this issue will be automatically closed in 30 days for housekeeping purposes.

tedjames · 8 months ago

Any chance this could be implemented? Would be an incredible way to make CC more capable at long-running tasks!!

Mikescher · 8 months ago
Any chance this could be implemented? Would be an incredible way to make CC more capable at long-running tasks!!

Perhaps this helps you:
I had the same problem last week and ended up writing a quick shell-script which auto-runs all prompts from a .claude-queue/ directory (every prompt is a markdown file): claude-queue.
Its not optimal, and the claude session is non-interactive - but it kinda worked for me...

github-actions[bot] · 7 months ago

This issue has been automatically closed due to 60 days of inactivity. If you're still experiencing this issue, please open a new issue with updated information.

ravshansbox contributor · 7 months ago

A ticket with 26 votes just gets auto-closed...

MalteJ · 7 months ago
A ticket with 26 votes just gets auto-closed...

27! I want this too! :D

marcindulak · 7 months ago

This issue was closed incorrectly despite recent human comments. This behavior of the bot is reported at https://github.com/anthropics/claude-code/issues/16497. Please upvote that issue, so maybe it gets noticed.

github-actions[bot] · 7 months ago

This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.