by lich0821
Intelligent API gateway for Claude Code and Codex CLI - rotate endpoints, monitor usage, and seamlessly integrate OpenAI, Gemini, and other platforms.
# Add to your Claude Code skills
git clone https://github.com/lich0821/ccNexusGuides for using cli tools skills like ccNexus.
Last scanned: 5/4/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-04T06:42:48.050Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}ccNexus is an open-source cli tools skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by lich0821. Intelligent API gateway for Claude Code and Codex CLI - rotate endpoints, monitor usage, and seamlessly integrate OpenAI, Gemini, and other platforms. It has 970 GitHub stars.
Yes. ccNexus passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/lich0821/ccNexus" and add it to your Claude Code skills directory (see the Installation section above).
ccNexus is primarily written in Go. It is open-source under lich0821 on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other CLI Tools skills you can browse and compare side by side. Open the CLI Tools category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh ccNexus against similar tools.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
access_token/refresh_token,自动轮换、自动刷新、失效隔离与状态管理/v1/models,支持缓存与按需刷新ccNexus.exetar -xzf ccNexus-linux-amd64.tar.gz && ./ccNexus点击「添加端点」,填写 API 地址、密钥,选择转换器(Claude / OpenAI Chat / OpenAI Responses / Gemini)。
如需使用 Codex Token Pool:
Codex Token Poolaccess_token + refresh_token)~/.claude/settings.json
{
"env": {
"ANTHROPIC_AUTH_TOKEN": "随便写,不重要",
"ANTHROPIC_BASE_URL": "http://127.0.0.1:3000",
"CLAUDE_CODE_MAX_OUTPUT_TOKENS": "64000", // 有些模型可能不支持 64k
}
// 其他配置
}
只需要配置 ~/.codex/config.toml:
model_provider = "ccNexus"
model = "gpt-5-codex"
preferred_auth_method = "apikey"
[model_providers.ccNexus]
name = "ccNexus"
base_url = "http://localhost:3000/v1"
wire_api = "responses" # 或 "chat"
# 其他配置
~/.codex/auth.json 可以忽略了。
ccNexus 默认监听 3000 端口,可通过 CLI 参数 -port 或环境变量 CCNEXUS_PORT 覆盖。/v1/models 默认走缓存;如需强制刷新,可使用启用的 refresh 参数能力。