vibeproxy — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 automazeio · Codex Skill · ★ 3.4k

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

🔒 Is vibeproxy safe to install? View the security audit →

About vibeproxy

VibeProxy Stop paying twice for AI. VibeProxy is a beautiful native macOS menu bar app that lets you use your existing Claude Code, ChatGPT, Gemini, Kimi, Qwen, Antigravity, and Z.AI GLM subscriptions with powerful AI coding tools like Factory Droids. Built on CLIProxyAPIPlus, it handles OAuth authentication, token management, and API routing automatically. One click to authenticate, zero friction to code. <a href="https://www.loom.com/share/5cf54acfc55049afba725ab443dd3

claude-codeclaudecodecli-proxycodexfactory-droidsgpt-5-codex

Quick Facts

Stars3,359
Forks228
LanguageSwift
CategoryCodex Skill
LicenseMIT
Quality Score70.3820218319809/100
Open Issues38
Last Updated2026-09-23
Created2025-10-04
Platformsclaude-code, cli, codex
Est. Tokens~16k

Compatible Skills

These tools work well together with vibeproxy for enhanced workflows:

  • Claude-Usage-Tracker — semantic(0.45)+complementary+rare_topics+same_lang+similar_pop+shared_platform (70%)
  • quotio — semantic(0.40)+complementary+same_lang+similar_pop+shared_platform (59%)
  • Context — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (51%)
  • ghost-os — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (50%)
  • pilot-shell — semantic(0.16)+complementary+rare_topics+similar_pop+shared_platform (50%)

vibeproxy alternative? Top 6 similar tools

Looking for a vibeproxy alternative? If you're comparing vibeproxy 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.

  • anyrouter-check-in by millylee · ⭐ 1.4k

    支持 AnyRouter、AgentRouter 的多平台多账号签到,理论兼容所有基于 NewAPI、OneAPI 的平台。

  • claude-codex-settings by fcakyon · ⭐ 1.2k

    Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM

  • codexia by milisp · ⭐ 915

    Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control

  • awesome-codex-skills by composio-community · ⭐ 16.6k

    A curated list of practical Codex skills for automating workflows across the Codex CLI and API.

  • Trellis by mindfold-ai · ⭐ 14.6k

    The best agent harness.

  • superset by superset-sh · ⭐ 14.5k

    Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscrip

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is vibeproxy?

vibeproxy is Native macOS menu bar app to use your Claude Code & ChatGPT subscriptions with AI coding tools - no API keys needed. It is categorized as a Codex Skill with 3.4k GitHub stars.

What programming language is vibeproxy written in?

vibeproxy is primarily written in Swift. It covers topics such as claude-code, claudecode, cli-proxy.

How do I install or use vibeproxy?

You can find installation instructions and usage details in the vibeproxy GitHub repository at github.com/automazeio/vibeproxy. The project has 3.4k stars and 228 forks, indicating an active community.

What license does vibeproxy use?

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

What are the best alternatives to vibeproxy?

The top alternatives to vibeproxy on Agent Skills Hub include anyrouter-check-in, claude-codex-settings, codexia. 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