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 maxnowack · Claude Skill · ★ 414
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is anthropic-proxy safe to install? View the security audit →
anthropic-proxy A proxy server that transforms Anthropic API requests to OpenAI format and sends it to openrouter.ai. This enables you to use Anthropic's API format while connecting to OpenAI-compatible endpoints. Usage With this command, you can start the proxy server with your OpenRouter API key on port 3000: Environment variables: : Your OpenRouter API key (required when using OpenRouter) : Custom base URL for the transformed OpenAI-format message (default: ) : The port the proxy server should listen on (default: 3000) : The reasoning model to use (default: ) : The completion model to use (default: ) : Set to to enable debug logging Note: When is set to a custom URL, the is not required. Claude Code To use the proxy server as a backend for Claude Code, you have to set the to the URL of the proxy server: License Licensed under MIT license. Copyright (c) 2025 Max Nowack Contributions Contributions are welcome. Please open issues and/or file Pull Requests.
| Stars | 414 |
| Forks | 45 |
| Language | JavaScript |
| Category | Claude Skill |
| Quality Score | 64.650666258248/100 |
| Open Issues | 7 |
| Last Updated | 2025-04-28 |
| Created | 2025-03-14 |
| Platforms | claude-code, node |
| Est. Tokens | ~3k |
These tools work well together with anthropic-proxy for enhanced workflows:
Looking for a anthropic-proxy alternative? If you're comparing anthropic-proxy with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligen
everything-claude-code 中文翻译项目：完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a
The complete guide to Claude Code: CLAUDE.md, hooks, skills, MCP servers, and commands
Run LLM prompts from your shell
Explore other popular claude skill tools:
anthropic-proxy is Proxy server that converts Anthropic API requests to OpenAI format and sends it to OpenRouter. It's used to use Claude Code with OpenRouter instead of the Anthropic API. It is categorized as a Claude Skill with 414 GitHub stars.
anthropic-proxy is primarily written in JavaScript. It covers topics such as anthropic, claude-code, llm.
You can find installation instructions and usage details in the anthropic-proxy GitHub repository at github.com/maxnowack/anthropic-proxy. The project has 414 stars and 45 forks, indicating an active community.
The top alternatives to anthropic-proxy on Agent Skills Hub include ccproxy, everything-claude-code-zh, vllm-mlx. 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: