codex-mobile — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

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 friuns2 · Codex Skill · ★ 911

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is codex-mobile safe to install? View the security audit →

About codex-mobile

🔥 codexapp 🚀 Run Codex App UI Anywhere: Linux, Windows, or Termux on Android 🚀 Codex UI in your browser. No drama. One command. Yes, that is your Codex desktop app experience exposed over web UI. Yes, it runs cross-platform. 🤯 What Is This? is a lightweight bridge that gives you a browser-accessible UI for Codex app-server workflows. You run one command. It starts a local web server. You open it from your machine, your LAN, or wherever your setup allows. TL;DR 🧠: Codex app UI, unlo

agentic-aiai-agentsai-assistantai-coding-agentclaudecodexdeepseekgeminigenerative-aiglm

Quick Facts

Stars911
Forks190
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score65.4797512943302/100
Open Issues44
Last Updated2026-05-26
Created2026-02-21
Platformsclaude-code, codex, gemini, node
Est. Tokens~424k

Compatible Skills

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

  • mobile-mcp — semantic(0.29)+complementary+rare_topics+same_lang+similar_pop+shared_platform (65%)
  • codexia — semantic(0.26)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)
  • agent-device — semantic(0.22)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • claude-in-mobile — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)
  • Shelly — semantic(0.33)+complementary+rare_topics+same_lang+shared_platform (55%)

codex-mobile alternative? Top 6 similar tools

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

  • the-pair by timwuhaotian · ⭐ 360

    Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch

  • py-gpt by szczyglis-dev · ⭐ 1.9k

    Desktop AI Assistant powered by GPT-6, GPT-5, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Biel

  • claude-council by hex · ⭐ 699

    Claude Code plugin that asks several AI coding agents the same question and shows their answers side by side.

  • UnrealGenAISupport by prajwalshettydev · ⭐ 632

    Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gem

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • llmio by atopos31 · ⭐ 313

    Unified LLM gateway with weighted load balancing, observability & cost tracking. 统一的 LLM 网关,提供权重负载均衡、可观测性与费用追踪

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is codex-mobile?

codex-mobile is 🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀. It is categorized as a Codex Skill with 911 GitHub stars.

What programming language is codex-mobile written in?

codex-mobile is primarily written in TypeScript. It covers topics such as agentic-ai, ai-agents, ai-assistant.

How do I install or use codex-mobile?

You can find installation instructions and usage details in the codex-mobile GitHub repository at github.com/friuns2/codex-mobile. The project has 911 stars and 190 forks, indicating an active community.

What license does codex-mobile use?

codex-mobile is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to codex-mobile?

The top alternatives to codex-mobile on Agent Skills Hub include the-pair, py-gpt, claude-council. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools