leo-lilinxiaoleo-lilinxiaoCommunityยท2 Agent Skills Included

codex-autoresearch

Autonomous experiment loop that fixes code until targets are met

Runs autonomous, measurable experiments inside a Git repository: change one thing, verify a numeric metric, keep improvements, and revert failures. Eliminates manual trial-and-error when fixing test failures, type errors, coverage gaps, latency, or binary size. Keeps iterating in the foreground or background until your confirmed numeric target is reached, with a full audit history.
npx skills add leo-lilinxiao/codex-autoresearch --all -g -y

All Skills in This Repository (2)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install codex-autoresearch?โ–ผ

Run `npx skills add leo-lilinxiao/codex-autoresearch --all -g -y` in your terminal to install the skill globally.

What does codex-autoresearch do?โ–ผ

It lets Codex run a controlled experiment loop in your Git repo: change one thing, measure a numeric metric, keep improvements, revert failures, and repeat until your target is reached.

What problems can codex-autoresearch fix?โ–ผ

It works for any measurable outcome such as test failures, type errors, code coverage, warnings, latency, binary size, or reproducible security findings.

Is codex-autoresearch safe for my repository?โ–ผ

Yes. Every trial is a Git commit, failed experiments are automatically reverted, and out-of-scope edits or malformed results stop the run with a clear error.

Can codex-autoresearch run overnight in the background?โ–ผ

Yes. It supports a detached background mode where a controller keeps iterating, and you can ask for status, stop, or resume at any time.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’