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

How to build a multi-part feature with parallel Codex work with Autoprompt Skill

Run a larger feature build in Codex with Autoprompt starting ready, independent work in parallel.

Who it is forA developer or small team starting a feature that spans several layers, such as API and checkout, and using Codex.

The problemLarge feature builds take many sequential steps, and manually splitting and checking each part is slow.

The outcomeAutoprompt scopes the feature, runs independent parts in parallel up to the host limit, and checks the result.

What you need first

  • Node.js 20+
  • Python 3.11+ available as python3 or python, with PyYAML
  • Bash 4.3+ on macOS or Linux, or a native Windows setup as described in the README
  • At least one supported coding agent installed, such as Claude Code or Codex
  • A local project folder to work on

Steps

  1. npm install -g https://github.com/Spielewoy/autoprompt-skill/releases/download/v2.1.0/autoprompt-skill-2.1.0.tgz
  2. autoprompt, then choose Codex, confirm its path, and install
  3. autoprompt doctor codex --strict (inferred, check the README)
  4. autoprompt activate codex --target /absolute/project -- --concurrency wide "build the booking flow from API to checkout" (inferred, check the README)
  5. Review the summary and the changed files before merging.

Prompt for your agent

Using the Spielewoy/autoprompt-skill repo, run `autoprompt activate codex --target <absolute project path> -- --concurrency wide "<your feature goal>"`. Expected output: a built feature across the layers named in the goal and a summary of what changed. Verify that the project's tests pass after the run.

Caveat. Codex on native Windows also requires an administrator-run Autoprompt controller and an initialized official Codex Windows sandbox, so that path needs extra setup.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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