[FEATURE] Create a signal to let Claude know that a script has finished

Resolved 💬 4 comments Opened Dec 31, 2025 by ChrisGVE Closed Feb 15, 2026

Preflight Checklist

  • [x] I have searched existing requests and this feature hasn't been requested yet
  • [x] This is a single feature request (not multiple features)

Problem Statement

When running experiments with Claude, scripts (bash or Python) are running for long period of time. Instead of having Claude checking regularly the status, which is suboptimal and consumes tokens for nothing, it would be better to have a way to callback Claude that an operation has completed.

Proposed Solution

I do not have a specific solution in mind. I was hoping that hooks could be used for that, but I've asked Claude Opus 4.5 about this eventuality and it could not find a way.

Alternative Solutions

At the moment, I am doing the monitoring, and I inform Claude Code when the execution has ended.

Priority

High - Significant impact on productivity

Feature Category

API and model interactions

Use Case Example

Typically when testing different models and pitching them against each other to evaluate their relative performance. It involves long runs which I have to monitor, I know that it is possible to create notifications for when runs are completed, but I might not always be there to trigger the next iteration with Claude (i.e. if the scripts ends in the middle of the night)

Additional Context

_No response_

View original on GitHub ↗

This issue has 4 comments on GitHub. Read the full discussion on GitHub ↗