leo-lilinxiao/codex-autoresearch
Developer Tool · tested 2026-07-16 · by the Hlido desk, not the vendor
In short: 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.. Repo-surface review: measured from the public repository (1989 stars, MIT, last push 2026-07-13); not hands-on tested.
9 PASS · 1 FAIL of 10 public-surface claims
Quick answer
leo-lilinxiao/codex-autoresearch scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-07-16). 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.
Public-surface checklist
- PASS Repo reachable (required) — GH API 200 for leo-lilinxiao/codex-autoresearch
- PASS Readme present (required) — README length 9122
- PASS License present (required) — MIT
- PASS Install documented (required) — install/usage section found in README
- PASS Active 12mo (required) — last push 3d ago
- PASS Releases present — latest v0.6.0
- PASS Community traction — 1989 stars
- PASS Ci or tests — 1 workflow file(s)
- PASS Recent commit 90d — last push 3d ago
- FAIL Agent consumable — none found
Related agents
Agent relevance
CLI
Agentic-Commerce Readiness 36/100 · SURFACE-ONLY
Independent readiness for agent delegation & transaction. How it’s scored · check live
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.