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 BenedictKing · Codex Skill · ★ 4.0k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ccx safe to install? View the security audit →
Claude / OpenAI Chat / Codex Responses / Gemini API Proxy - CCX CCX is a high-performance AI API proxy and protocol translation gateway for Claude, OpenAI Chat / Codex Responses, and Gemini. It provides a unified entrypoint, built-in web administration, failover, multi-key management, channel orchestration, and model routing. Features Integrated backend + frontend architecture with single-port deployment Dual-key authentication with and optional Web admin console for channel management, testing, and monitoring Support for Claude Messages, OpenAI Chat Completions, Codex Responses, and Gemini APIs Protocol conversion across Claude Messages, OpenAI Chat, Gemini, and Responses Smart scheduling with priorities, promotion windows, health checks, and circuit breaking Per-channel API key rotation, proxy support, custom headers, and model allowlists Model remapping, fast mode, and verbosity controls Streaming and non-streaming support Responses session tracking for multi-turn workflows Screenshots Channel Orchestration Visual channel management with drag-and-drop priority adjustment and real-time health monitoring. /A2A (agent-to-a
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
Explore other popular codex skill tools:
ccx is Claude / Codex / Gemini API Proxy - CCX. It is categorized as a Codex Skill with 4.0k GitHub stars.
ccx is primarily written in Go. It covers topics such as claude, codex, gemini.
You can find installation instructions and usage details in the ccx GitHub repository at github.com/BenedictKing/ccx. The project has 4.0k stars and 323 forks, indicating an active community.
ccx is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ccx on Agent Skills Hub include ai-guide, unity-mcp, deepchat. 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: