No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by TheGreenCedar · Codex Skill · ★ 836
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codex-autoresearch safe to install? View the security audit →
Codex Autoresearch Measured improvement loops for Codex Try it - Install - How it works - Dashboard - Docs - Changelog Codex Autoresearch helps Codex turn "make this better" into a measured loop. Give Codex a goal, a benchmark contract, and a safe edit scope. Codex can run small experiment packets, keep or discard changes with evidence, preserve ASI and metrics across context loss, and package useful work for review. Inspired by the AI-focused karpathy/autoresearch and pi-autoresearch. Codex Autoresearch adapts the measured-loop idea for Codex plugin workflows, repo-local benchmarks, durable session files, an evidence trail, live dashboards, and reviewable finalization. Try it Ask Codex to use Codex Autoresearch. Broad prompts work: You can also hand it a sharper investigation: text Use $Codex Autoresearch to figure out why my graphql
| Stars | 836 |
| Forks | 59 |
| Language | TypeScript |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 71.9604508649819/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-06 |
| Created | 2026-04-20 |
| Platforms | codex, node |
| Est. Tokens | ~15k |
These tools work well together with codex-autoresearch for enhanced workflows:
Looking for a codex-autoresearch alternative? If you're comparing codex-autoresearch with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then run
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with gradin
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Ka
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
Curated list of AutoResearch use cases with optimization traces and open source implementations
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Ka
Explore other popular codex skill tools:
codex-autoresearch is A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss, Li. It is categorized as a Codex Skill with 836 GitHub stars.
codex-autoresearch is primarily written in TypeScript. It covers topics such as agent-skills, autonomous-agents, autoresearch.
You can find installation instructions and usage details in the codex-autoresearch GitHub repository at github.com/TheGreenCedar/codex-autoresearch. The project has 836 stars and 59 forks, indicating an active community.
codex-autoresearch is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to codex-autoresearch on Agent Skills Hub include evo, CORAL, awesome-autoresearch. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: