cli — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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 codeproxy-ai · Codex Skill · ★ 56

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

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

About cli

@codeproxy/cli 中文版 → README.zh-CN.md @codeproxy/cli is a local proxy server that converts any Chat Completions or Anthropic Messages API into the OpenAI Responses API format. It lets Codex, Claude Code, or any Responses-API client use models from DeepSeek, GLM, Kimi, and more. Built on @codeproxy/core. Quick Start Point your Responses-API client at : With config file See config.example.json for a full example. Top-level fields Default thinking config for all upstreams. Anthropic format: . Set

claude-codecodexdeepseekglmkimi

Quick Facts

Stars56
Forks3
LanguageTypeScript
CategoryCodex Skill
Quality Score69.2842284715218/100
Last Updated2026-05-25
Created2026-05-09
Platformsclaude-code, cli, codex, node
Est. Tokens~17k

Compatible Skills

These tools work well together with cli for enhanced workflows:

  • codex-collab — semantic(0.19)+complementary+shared_fw(anthropic,openai)+same_lang+similar_pop+shared_platform (73%)
  • kimi-code-mcp — semantic(0.20)+complementary+shared_fw(anthropic)+rare_topics+same_lang+similar_pop+shared_platform (70%)
  • token_proxy — semantic(0.38)+complementary+shared_fw(anthropic,openai)+similar_pop+shared_platform (64%)

cli alternative? Top 6 similar tools

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

  • sub-agents-mcp by shinpr · ⭐ 98

    Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.

  • sub-agents-skills by shinpr · ⭐ 83

    Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Kimi, Curs

  • tmux-bridge-mcp by howardpen9 · ⭐ 94

    Standalone MCP server for cross-pane AI agent communication via tmux. Lets Claude Code, Gemini CLI, Codex, and

  • claude-code-supervisor by guyskk · ⭐ 81

    Auto-review and iterate until quality work is delivered - a better alternative to ralph-claude-code. Switch be

  • deepcontext-mcp by Wildcard-Official · ⭐ 275

    DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

  • openclaw-guide by liyupi · ⭐ 184

    开源OpenClaw中文文档站,OpenClaw中文指南,支持小龙虾 AI 智能体安装部署、消息渠道接入、Agent 架构、Skills 技能配置、模型提供商、CLI 命令参考、网关运维、安全沙箱等全方位文档。覆盖 Wh

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is cli?

cli is @codeproxy/cli is a local proxy server that converts any Chat Completions or Anthropic Messages API into the OpenAI Responses API format. It lets Codex, Claude Code, or any Responses-API client use mo. It is categorized as a Codex Skill with 56 GitHub stars.

What programming language is cli written in?

cli is primarily written in TypeScript. It covers topics such as claude-code, codex, deepseek.

How do I install or use cli?

You can find installation instructions and usage details in the cli GitHub repository at github.com/codeproxy-ai/cli. The project has 56 stars and 3 forks, indicating an active community.

What are the best alternatives to cli?

The top alternatives to cli on Agent Skills Hub include sub-agents-mcp, sub-agents-skills, tmux-bridge-mcp. 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