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 haiou-666 · Codex Skill · ★ 265
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is haiou-codex safe to install? View the security audit →
haiou-codex 海鸥 codeX 版 海鸥 codeX 版是一套面向 Codex 的本地增强配置包，通过自定义 AGENTS.md、模块化 Prompt 和专业 Skill，为 Codex 增加更直接的中文技术人格与安全研究工作流。
| Stars | 265 |
| Forks | 48 |
| Category | Codex Skill |
| Quality Score | 31.607620251862/100 |
| Last Updated | 2026-08-10 |
| Created | 2026-07-10 |
| Platforms | codex |
| Est. Tokens | ~15k |
Looking for a haiou-codex alternative? If you're comparing haiou-codex 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.
Free, open-source desktop manager for AI Agent Skills. Write a skill once, sync it to 32 AI coding tools (Clau
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen
Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex
开源了Codex Skills等集合，大部分是自己实际需要搞得，需要的自取。欢迎star
Skills for agentic development on Solana
A Codex/Claude skill that maintains per-repo operating theory documents.
Explore other popular codex skill tools:
haiou-codex is 海鸥 codeX 版 海鸥 codeX 版是一套面向 Codex 的本地增强配置包，通过自定义 AGENTS.md、模块化 Prompt 和专业 Skill，为 Codex 增加更直接的中文技术人格与安全研究工作流。. It is categorized as a Codex Skill with 265 GitHub stars.
You can find installation instructions and usage details in the haiou-codex GitHub repository at github.com/haiou-666/haiou-codex. The project has 265 stars and 48 forks, indicating an active community.
The top alternatives to haiou-codex on Agent Skills Hub include Skills-Manager, ai-maestro, upskill. 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: