---
title: Diagnose a failure without changing code
description: Get the root cause and the evidence for it, with no edits until you decide on a fix.
url: https://openplanr.dev/docs/prompts/diagnose-without-fixing
updated: 2026-10-06
related:
  - https://openplanr.dev/docs/prompts/investigate-first.md
  - https://openplanr.dev/docs/prompts/track-down-a-flaky-test.md
  - https://openplanr.dev/docs/prompts/diagnose-setup.md
---

# Diagnose a failure without changing code

Get the root cause and the evidence for it, with no edits until you decide on a fix.

## Prompt

Claude Code:

```text
/investigate Why does checkout fail for carts with a discount code? Find the cause, but don't change any code yet.
```

If /investigate runs another command, use /planr:investigate.

Codex:

```text
$investigate Why does checkout fail for carts with a discount code? Find the cause, but don't change any code yet.
```

With the OpenPlanr plugin for Codex, use $planr:investigate.

Cursor:

```text
@planr-investigate Why does checkout fail for carts with a discount code? Find the cause, but don't change any code yet.
```

Cursor applies the planr-investigate rule when you mention it in chat.

Parts to fill in, shown with their example text:

- The failure: checkout fail for carts with a discount code

## Why this works

Without a request to fix, Investigate stays diagnostic. It reports the established cause or the strongest remaining hypotheses, the checks it ran, and what is still uncertain.

## Make it stick

[OpenPlanr Investigate](https://openplanr.dev/docs/skills/investigate.md)
