# Remove reminders whose work is done or no longer wanted

Comment reminders pointing at work that already happened or stopped mattering, removed with a reason.

Category: Tech debt and deprecations
Source: https://letsship.ai/use-cases/remove-completed-reminders
Published: 2026-08-25

## Goal

Remove code comment reminders that are already done or no longer relevant.

## Acceptance criteria

- Each removal states why the reminder no longer applies
- Reminders describing outstanding work are converted to tickets rather than deleted
- No code behaviour changes
- The remaining count is recorded

## What lands as proof

A per-reminder justification, so nothing outstanding is deleted along with what is genuinely stale.

## Prompt

Copy this to an agent to open the ticket:

```text
Create a Linear issue in my team and assign it to the SHIP agent.

Title: Clear stale reminders from {area}

Description: Remove code comment reminders that are already done or no longer relevant.

Acceptance criteria:
- Each removal states why the reminder no longer applies
- Reminders describing outstanding work are converted to tickets rather than deleted
- No code behaviour changes
- The remaining count is recorded

Before you create the issue, list the reminder comments in this repository with their ages and replace {area} with the densest one.
```

## Questions

### What does the agent actually change?

The ticket is scoped to one outcome: remove code comment reminders that are already done or no longer relevant. Work that serves that outcome is in scope, and anything outside it is left for a separate ticket, so the pull request stays reviewable.

### How do I know the work is done?

The pull request carries the evidence, not only the diff. Here that means each removal justified in the description, never silently dropped, so a reviewer can confirm the result without reproducing the work locally.

### How much oversight does this need?

None is required before the run starts. Every claim this ticket makes can be checked by machine, so the agent works straight through and a person reviews the finished pull request like any other.