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

How to build planned project features in parallel with subagents with Web GPT

Split a project's planned features across Web GPT extra-high subagents that run at the same time.

Credentials. Subagents run with full terminal access as your OS user in the project, so limit the work to projects you have assigned.

Who it is forA developer with a list of planned features in one project who wants them worked on at the same time.

The problemWorking through several planned features one at a time takes longer than the work needs.

The outcomeEach planned feature is developed by its own subagent in the project, and the results are reported back to Codex.

What you need first

  • Codex with the WebGPT skill installed from https://github.com/Nhahan/WebGPT/tree/main/skills/webgpt
  • A ChatGPT account you can sign in to on the web
  • Permission for the local Worker, accountless HTTPS forwarding, and full terminal access as your OS user for the assigned project
  • A terminal on the machine where Codex runs

Steps

  1. Install the skill by pasting the install prompt from the README into Codex, then let Codex follow references/setup.md.
  2. Make sure the planned features for the project are written down where Codex can read them.
  3. In Codex, tell it: Use webgpt xh as subagents to develop this project's planned features in parallel.
  4. Review each feature branch or change Codex reports and run the project's own tests before accepting it.

Prompt for your agent

Using the WebGPT repo (Nhahan/WebGPT), ask Codex to run webgpt xh subagents on the planned features of <project path>. Expect one completed change per planned feature and a short report from each subagent. Verify each change with the project's existing tests before merging.

Caveat. The README gives no details on how parallel subagent results are merged, so review every change before accepting it.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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