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

How to install GPT with Taste hooks into Codex with GPT with Taste

Add the recipe and scoped hook reminders to Codex for multi-turn work.

Who it is forA developer using Codex Desktop for multi-turn coding tasks who wants GPT to keep its standing priorities across turns.

The problemCodex answers each request with default behavior, and reminders about judgment and craft fade across a long session.

The outcomeCodex loads the recipe as its model instructions, and hook reminders fire on user submissions, child startup and supported wait results in a new session.

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. Run git clone https://github.com/NB-Corp/gpt-with-taste.git
  2. Run cd gpt-with-taste
  3. Run node scripts/install.mjs --hooks
  4. In Codex Desktop open Settings → Hooks (or run /hooks in the interactive terminal), review and trust the three installed definitions, and enable only the events you want
  5. Open a new Codex session after installation

Prompt for your agent

Clone https://github.com/NB-Corp/gpt-with-taste into <target-folder>, run `node scripts/install.mjs --hooks` from that folder, and report the files written under the active CODEX_HOME. Verify that model_instructions_file now points to the main managed prompt file and that your model, provider and AGENTS.md settings were not changed.

Caveat. The README says to review and trust the hook definitions yourself, and that later child-input coverage depends on the client entry point.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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