# Work the aged low-priority queue one ticket at a time

A real defect filed months ago, triaged as low, and never picked up. Reproduced, fixed, and covered by a test.

Category: Bug backlog and defect hunting
Source: https://letsship.ai/use-cases/work-the-aged-low-priority-queue
Published: 2026-08-25

## Goal

Reproduce, fix, and cover one aged low-priority bug.

## Acceptance criteria

- The bug is reproduced before anything is changed
- A test fails against the current code and passes with the fix
- The fix addresses the cause rather than the symptom described in the report
- If it cannot be reproduced, that is recorded on the ticket with what was tried

## What lands as proof

A test that fails on the unfixed code, which proves the reproduction was real rather than assumed.

## 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: Fix {bug}

Description: Reproduce, fix, and cover one aged low-priority bug.

Acceptance criteria:
- The bug is reproduced before anything is changed
- A test fails against the current code and passes with the fix
- The fix addresses the cause rather than the symptom described in the report
- If it cannot be reproduced, that is recorded on the ticket with what was tried

Before you create the issue, sort this repository's open bugs by age, pick the oldest one that is still relevant, and replace {bug} with it.
```

## Questions

### What does the agent actually change?

The ticket is scoped to one outcome: reproduce, fix, and cover one aged low-priority bug. 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 a failing test that now passes, in the same pull request as the fix, 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.