QoderAI/better-harness
A workflow you run inside a coding agent that grades how a session went across five parts, from how the task was understood to whether the changes were checked. It lists the gaps it finds and drafts a scoped fix for each one.
Not tested yetKey files read, not run
How we know
We read the README and key files, not every source file, and did not run it, so the most we can say is Idea adapted or Risky.
Good for
Teams using Claude Code, Codex or Cursor who want a repeatable check on how their agent works, not only on the code it writes.
Not for
Anyone who only wants a quick review of a diff; it is early, has no real adoption yet, and its support for other hosts is untested.
Repo
- Stars
- 2,239
- License
- MITUse it, change it, sell it, closed-source included. Keep the author's copyright notice.
- Maturity
- experimental
- Last push
- 2026-09-10
- Last checked
- 2026-11-14