by TheGreenCedar · Codex Skill · ★ 832
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: OpenAI Codex Skills
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 832 |
| Forks | 59 |
| Language | TypeScript |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 72/100 |
| Open Issues | 2 |
| Last Updated | 2026-10-02 |
| Created | 2026-04-20 |
| Platforms | codex, node |
| Est. Tokens | ~15k |
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.
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
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
Curated list of AutoResearch use cases with optimization traces and open source implementations
Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code
GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with sem
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: