codex-app — repository deleted, archived audit

Quick Facts

About codex-app

整理 Codex Desktop App 的官方下载方式：macOS 直接下载 Codex.dmg，Windows 使用微软官方下载链接，并附安装后配置教程入口。很多用户下载安装 Codex Desktop App 后，打开软件却发现还不能直接使用。本文就带你从 下载安装、配置 API Key 到 切换中文界面，一步一步完成设置，让你顺利用上 Codex 桌面客户端。

Compatible Skills

These tools work well together with codex-app for enhanced workflows:

• alpha-insights — semantic(0.31)+complementary+rare_topics+similar_pop+shared_platform (50%)
• agent-sessions — semantic(0.19)+complementary+similar_pop+shared_platform (47%)
• codex-mcp-server — semantic(0.19)+complementary+similar_pop+shared_platform (47%)

codex-app alternative? Top 6 similar tools

Looking for a codex-app alternative? If you're comparing codex-app 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.

• codex-profiles by Ducksss · ⭐ 186

  Named CODEX_HOME profiles and ChatGPT Desktop windows with separate local state, without copying tokens

• copilot-tunnel-proxy by noviaidrl · ⭐ 120

  GitHub Copilot as Local AI API Bridge for Claude Code 2026

• codex-session-export by MeXenon · ⭐ 113

  Codex session conversation chat export markdown interactive terminal tool.

• grace-marketplace by osovv · ⭐ 246

  GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with sem

• speckit-agent-skills by dceoy · ⭐ 151

  Agent skills for Spec Kit

• codex-app by MatterTherapistZen · ⭐ 135

  codex app - AI coding tool for writing, reviewing, and debugging code. Comprehensive guide with setup instruct

More Codex Skill Tools

Explore other popular codex skill tools:

• superset ⭐ 15.5k
• humanizer ⭐ 57.5k
• refly ⭐ 7.5k
• nano-banana-pro-prompts-recommend-skill ⭐ 1.9k
• pi-skills ⭐ 2.5k
• skillkit ⭐ 1.5k
• ai-maestro ⭐ 831
• upskill ⭐ 762
• Claude-to-IM-skill ⭐ 2.9k
• learning-opportunities ⭐ 2.4k

How this security grade is produced

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:

• SlowMist agent-security taxonomy
• Liu et al., An Empirical Study of Agent Skill Security (2026)
• Our census dataset (DOI 10.5281/zenodo.21292799) · Hugging Face mirror
• How we grade: all 42 rules, the source tiers and known limits
• Full methodology & who runs this