Credentials. You store a provider API key on your machine, so keep it out of chats, screenshots and issue reports.
Remote script. The Skill is installed from a URL, so review what the agent installs before you approve it.
Who it is forA developer who has chosen a cheap API and wants Codex, Claude Code or another listed app set up with it without editing config files by hand.
The problemPointing a coding agent at a new API means editing config files, storing a key safely and checking that the model name and group are right.
The outcomeYour chosen app is configured to use the API, with a backup of the previous file and a check that the key, group and model name work without spending credit.
What you need first
- An AI agent you already use, such as Codex, Claude Code or Cursor
- A model name or kind of use (chat, coding, long output) to compare
- For connecting an API: a grandet.ai sign-up, a top-up and a token created in the group the site names
Steps
- Sign up and top up on the site yourself, then create the token in the group Grandet names.
- Run one command in your own terminal to store the key; typing is hidden and the key never enters the chat.
- Ask your agent to connect the API to your app, and review the exact configuration change it shows you.
- Confirm the change so the file is backed up and written, then let the check run.
- Say undo if you want the previous setup restored.
Prompt for your agent
Using the Grandet Skill connect program for <app name, for example Codex or Claude Code>, connect the chosen API for <model name>. Show the configuration change before writing, confirm the backup was made, and report the result of the key, group and model name check.
Caveat. Connecting covers only the apps Grandet names, such as Codex, Claude Code, OpenCode and Gemini CLI; other apps get only a field card and documentation link.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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