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 CaddyGlow · Codex Skill · ★ 274
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ccproxy-api safe to install? View the security audit →
CCProxy API Server CCProxy is a local, plugin-based reverse proxy that unifies access to multiple AI providers (e.g., Claude SDK/API and OpenAI Codex) behind a consistent API. It ships with bundled plugins for providers, logging, tracing, metrics, analytics, and more. Supported Providers Anthropic Claude API/SDK (OAuth2 flow or Claude CLI/SDK token files) OpenAI Codex (ChatGPT backend Responses API using OAuth for paid/pro accounts) GitHub Copilot (chat and completions for free, paid, or business accounts) Each provider adapter exposes the same surface area: OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages. The proxy maintains a shared model-mapping layer so you can reuse the same identifier across providers without rewriting client code. Authentication can reuse existing provider files (e.g., Claude CLI SDK tokens and the Codex CLI credential store), or you can run to complete the OAuth flow from the CLI; stored secrets are picked up automatically by the proxy. Extensibility CCProxy's plugin system lets you add instrumentation and storage layers without patching the core server.
| Stars | 274 |
| Forks | 51 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 70.413431052714/100 |
| Open Issues | 16 |
| Last Updated | 2026-05-02 |
| Created | 2025-07-04 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~336k |
Looking for a ccproxy-api alternative? If you're comparing ccproxy-api 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.
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
Multi-account pool proxy for Windsurf — 113+ models (Claude/GPT/Gemini/Grok/Kimi) via OpenAI & Anthropic APIs,
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat
LLM orchestration toolkit for agent workflows: planner + workers + synthesis, optional router (LLM + learned
Ship RAG based LLM web apps in seconds.
Run Claude agents in secure cloud sandboxes — via API, CLI, or Slack. One call. Full agent. Zero infrastructur
Explore other popular codex skill tools:
ccproxy-api is is a local reverse proxy providing unified access to multiple AI providers (Claude, Codex) through a single interface, using your existing subscriptions without API key billing.. It is categorized as a Codex Skill with 274 GitHub stars.
ccproxy-api is primarily written in Python. It covers topics such as anthropic, anthropic-api, claude.
You can find installation instructions and usage details in the ccproxy-api GitHub repository at github.com/CaddyGlow/ccproxy-api. The project has 274 stars and 51 forks, indicating an active community.
ccproxy-api is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ccproxy-api on Agent Skills Hub include claudex, WindsurfPoolAPI, OmoiOS. 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: