Skip to content
MMake Prompt AI Get Started
Home > ChatGPT Guide > /debug
Custom prompt shortcut / Software Development

/debug — ChatGPT Prompt Guide

Explore the /debug custom ChatGPT prompt shortcut with a practical template, examples, and review steps. Learn how to refine outputs for your workflow.

What does /debug do?

Purpose: Trace a login redirect loop across authentication and session boundaries.

This is a custom prompt convention, not a built-in or official ChatGPT slash command. Entering the slash text alone does not guarantee that ChatGPT will invoke a special tool. Use the complete structured prompt below or configure your own app to interpret this shortcut.

Key decision for this workflow

Check SameSite/Secure cookie handling, proxy HTTPS headers, returnUrl validation, and session expiry.

Copy-ready task brief

/debug Objective: Trace a login redirect loop across authentication and session boundaries. Inputs: Redirect chain, HTTP status codes, Location headers, cookie attributes, and auth middleware. Deliverable: A request-by-request timeline identifying the first incorrect redirect.

Reusable prompt template

/debug Objective: Trace a login redirect loop across authentication and session boundaries. Available materials: Redirect chain, HTTP status codes, Location headers, cookie attributes, and auth middleware. Required output: A request-by-request timeline identifying the first incorrect redirect. Acceptance test: Check SameSite/Secure cookie handling, proxy HTTPS headers, returnUrl validation, and session expiry. Boundary: Do not publish session tokens or credentials in diagnostics; reproduce with a throwaway account. Return the requested deliverable first, then a brief verification checklist and any unresolved questions.

How to use this shortcut

  1. Collect the source inputs: Redirect chain, HTTP status codes, Location headers, cookie attributes, and auth middleware.
  2. Run /debug with the copy-ready task brief above.
  3. Request the concrete output: A request-by-request timeline identifying the first incorrect redirect.
  4. Check the result: Check SameSite/Secure cookie handling, proxy HTTPS headers, returnUrl validation, and session expiry.

Quality checks and limitations

Acceptance criteria: Check SameSite/Secure cookie handling, proxy HTTPS headers, returnUrl validation, and session expiry. Limitation: Do not publish session tokens or credentials in diagnostics; reproduce with a throwaway account.

Related tools and learning

Continue with the 35 prompt generators, the technical AI Guides, and the Image Guides for deeper examples.

/code/refactor/codeaudit/frontend/longformscript/facelessvideo

Worked example: Investigate a login redirect loop

Illustrative output: Capture request/response status codes and Location headers, identify conflicting cookie and canonical redirect rules, then reproduce in an isolated environment.

Review and limitations

Do not remove security controls to make the loop disappear.

Field workflow: inputs, decisions, and validation

When to use this shortcut: Trace a login redirect loop across authentication and session boundaries.

What to provide: Redirect chain, HTTP status codes, Location headers, cookie attributes, and auth middleware.

What to request: A request-by-request timeline identifying the first incorrect redirect.

Practical method: Check SameSite/Secure cookie handling, proxy HTTPS headers, returnUrl validation, and session expiry.

Important limitation: Do not publish session tokens or credentials in diagnostics; reproduce with a throwaway account.

Frequently asked questions

Is /debug an official ChatGPT command? No. It is a reusable custom shorthand from this catalog. Does it work without a plugin? You can copy the full prompt into an assistant; automatic slash-command routing requires application logic. Can the output be trusted without review? No. Review accuracy, safety, and suitability before use.