Credentials. Setup asks you to create a tunnel and a restricted API key at OpenAI, so store that key carefully and limit the folders you share.
Who it is forA developer with a local codebase who wants ChatGPT to make changes and check them without copy-pasting code into chat.
The problemChat answers about code cannot be verified against the real project, so every change needs manual copying and testing.
The outcomeChatGPT edits files in a folder you chose and reports the actual test results it received from your machine.
What you need first
- Windows 10/11, macOS 13 Ventura or newer, or a current desktop Linux with a Secret Service keyring
- Chrome 125+, current Edge or Brave for the browser extension
- A ChatGPT account or workspace that can create custom MCP apps
- A tunnel and a restricted API key created at OpenAI for Core setup
Steps
- Install CoS and open Settings → Setup.
- Load the browser extension in Chrome, Edge or Brave and complete step 1 of Setup.
- Share the project folder and choose what ChatGPT may do there (steps 2, 3).
- Connect Core by creating a tunnel and a restricted API key at OpenAI, press Connect, then add the app under Plugins → Add → Add custom MCP server.
- Choose a model, write a task such as fixing one failing test, and send it.
Prompt for your agent
Using the repo totec448-spec/chat-on-steroids, connect ChatGPT to the project folder <project-path> with read and edit access. Ask ChatGPT to fix the failing test named <test-name> and run the test suite. Expected output: a list of changed files and the test command results. Verify that the test results shown come from the local run, not from ChatGPT's own description.
Caveat. This is an independent beta used at your own risk, and shell commands run with your normal user privileges.
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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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