Who it is forA project lead with a growing pile of untriaged GitHub issues who wants each one routed before anyone starts coding.
The problemReading every issue to decide whether it is small enough to automate, needs a spec, or lacks a fact takes time and is easy to do inconsistently.
The outcomeEach issue carries one queue label and a structured handoff comment with expected files, completion condition, gate level, and confidence, and any issue needing product intent is parked for a human spec.
What you need first
- A GitHub project you control, with permission to create labels and manage its pull requests
- Claude Code installed, or Codex if you use the Codex adapter
- A clone of the addyosmani/factory repository
- Your project's real test, lint, and build commands, since the gates run them
- A human-owned docs/factory/CHARTER.md that defines scope, risk, and the review-queue limit
Steps
- Confirm the charter in
docs/factory/CHARTER.mdstates what work the Factory may attempt. - Run the interactive triage stage in your coding agent against the target repository.
- Review the labels and the queue snapshot the triage stage produces.
- Move any issue marked
factory:ready-to-specinto the human-guided spec workflow with its four approval gates. - Open
/factoryto check what now needs you.
Prompt for your agent
Using the addyosmani/factory skills in <target-repo>, run the triage stage on the open untriaged GitHub issues. Expected output: a list of issues with the factory:* label applied to each and a one-line reason. Verify that no code was changed and that every issue has exactly one queue label.
Caveat. The README describes interactive triage for both Claude Code and Codex, but the unattended hourly triage schedule is supplied only for Claude cloud routines.
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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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