DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to recover GPT with Taste after a broken or changed install with GPT with Taste

Restore the managed Codex files using the recovery guide.

Who it is forA Codex user whose managed prompt files or hook settings were changed or lost after an update or edit.

The problemCodex is no longer picking up the recipe, or the managed state no longer matches the repository.

The outcomeThe managed state is restored to the installed version by following the recovery guide.

What you need first

  • Node.js 22 or newer installed
  • OpenAI Codex (Codex Desktop or the interactive terminal) with access to a GPT model
  • A terminal and a local clone of the NB-Corp/gpt-with-taste repository

Steps

  1. Open docs/recovery.md in the GPT with Taste checkout
  2. Follow the recovery steps for the managed prompt files and model_instructions_file
  3. Run node scripts/check-updates.mjs to confirm the installed components
  4. Run node scripts/install.mjs --hooks again if hooks are part of your setup
  5. Open a new Codex session and confirm the hook definitions are still trusted

Prompt for your agent

In the gpt-with-taste checkout at <repo-path>, follow docs/recovery.md to restore the managed state under the active CODEX_HOME. Report which files were restored and confirm that model_instructions_file points to the main managed prompt file.

Caveat. The README says customized checkouts need the update instructions in docs/install.md, so a recovery can overwrite local edits you wanted to keep.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page