Someone types /request new in Discord and describes what they want. The bot opens a GitHub issue and posts an Approve/Reject card. On approval, Claude Code builds it in GitHub Actions and opens a pull request, and the bot posts the link back and @-mentions whoever asked.
Most “AI builds your feature” demos skip the three parts that make it safe to actually run, and this one treats them as the product:
- A human approval gate before any code is written.
- Containment of untrusted input. Request text is fenced off as data and can’t override the repository’s rules.
- An answer to who pays. Each requester stores their own Anthropic credential once, sealed into a per-user GitHub environment the bot can’t read back. There’s no owner bypass.
The bot itself is modular, and new modules come from a scaffold, so the requests it builds follow the same pattern.