Updated 1mo ago
by leo-lilinxiao
codex-autoresearch
Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.
3.1k GitHub stars (3,124)
+357 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | +1 |
| Oct 2 | +7 |
| Oct 3 | +6 |
| Oct 4 | +10 |
| Oct 5 | +4 |
| Oct 6 | +6 |
| Oct 7 | +12 |
| Oct 8 | +9 |
| Oct 9 | +26 |
| Oct 10 | +10 |
| Oct 11 | +20 |
| Oct 12 | +19 |
| Oct 13 | +21 |
| Oct 14 | +18 |
| Oct 15 | +13 |
| Oct 16 | +9 |
| Oct 17 | +28 |
| Oct 18 | 0 |
| Oct 19 | +7 |
| Oct 20 | +9 |
| Oct 21 | +21 |
| Oct 22 | +4 |
| Oct 23 | +8 |
| Oct 24 | +7 |
| Oct 25 | +7 |
| Oct 26 | +6 |
| Oct 27 | +13 |
| Oct 28 | +6 |
| Oct 29 | +15 |
| Oct 30 | +19 |
| Oct 31 | +2 |
| Nov 1 | +3 |
| Nov 2 | +9 |
| Nov 3 | +14 |
| Nov 4 | +13 |
| Nov 5 | +9 |
- 1 skill (1 skills found in its SKILL.md files)
- 130 forks (130 forks)
- 1mo ago last update (Last updated 1mo ago)
Install
Skills CLI
npx skills add leo-lilinxiao/codex-autoresearch
Asks which agents to install it for. Add -g to install it for every project.
Claude Code
git clone https://github.com/leo-lilinxiao/codex-autoresearchcp -r "codex-autoresearch" ~/.claude/skills/codex-autoresearch
Copies the codex-autoresearch skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project).
Plugin
/plugin marketplace add leo-lilinxiao/codex-autoresearch
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
codex-autoresearch
Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits.
SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.