marks97

Runpod Vllm Claude Code — DevOps skill for Claude Code

DevOps community

Deploy any HuggingFace model to RunPod as a vLLM server, bridge it to Claude Code (which speaks Anthropic's Messages API, not OpenAI's), smoke-test that tool-calling actually works end to end, and tea.

How to install Runpod Vllm Claude Code

This entry records only its repository, not the path inside it, so there is no exact command to give. Open marks97/runpod-vllm-claude-code and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Runpod Vllm Claude Code does

Deploy any HuggingFace model to RunPod as a vLLM server, bridge it to Claude Code (which speaks Anthropic's Messages API, not OpenAI's), smoke-test that tool-calling actually works end to end, and tear everything down with zero trace (pod,

Alternatives in DevOps

  • Claude Code Router — Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the m 30.1k ★
  • Claude Code GitHub Actions — by Anthropic - Official GitHub Actions integration for Claude Code with examples and documentation for automat 6.4k ★
  • 16 Testing — Prompt 16: Add Test Infrastructure & Smoke Tests 2.3k ★

README

Runpod Vllm Claude Code

A [Claude Code](https://code.claude.com/docs/en/skills) skill.

Deploy any HuggingFace model to RunPod as a vLLM server, bridge it to Claude Code (which speaks Anthropic's Messages API, not OpenAI's), smoke-test that tool-calling actually works end to end, and tear everything down with zero trace (pod, network volumes, local processes, scratch files). Use this whenever you want to run a model on RunPod, try a model with Claude Code, test whether a HF/GGUF/abliterated checkpoint supports tool use, benchmark a model for coding-agent use, or spin up/kill a disposable GPU inference box. Also trigger it for anything about hooking Claude Code up to a non-Anthropic backend (vLLM, Ollama, LM Studio) via ANTHROPIC_BASE_URL, or questions like 'what GPU do I need to run X' and 'how much will it cost to run this model'.

Install

Via [skills.sh](https://skills.sh):

npx skills add marks97/runpod-vllm-claude-code

Or manually — copy the `runpod-vllm-claude-code/` folder into your `.claude/skills/` directory.

Usage

Once installed, Claude invokes this skill automatically when your request matches what it does (see the triggers in [`runpod-vllm-claude-code/SKILL.md`](runpod-vllm-claude-code/SKILL.md)). You can also ask for it by name.

See [`runpod-vllm-claude-code/SKILL.md`](runpod-vllm-claude-code/SKILL.md) for the full workflow, scripts, and options.

License

MIT © Marc Amoros