Runpod Vllm Claude Code — DevOps skill for Claude Code
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
Related Skills
Litellm
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - Bedrock, Azure, OpenAI, Verte
Cloud ChatAgent
A production-ready, cloud-native Agentic AI Platform powered by AWS Bedrock (Anthropic Claude 3.5 Sonnet / Cla
Claude2api
Claude2API 是基于 Go + Docker 构建的 Claude.ai API 兼容网关、账号池与网页镜像服务,支持 OpenAI Chat Completions、Responses 和 Anthropic
Deploy Forged MCP
Deploy an MCP server generated by forge-from-openapi --target=mcp-server; detect transport, deploy, smoke-test
Rollcall
Fleet smoke test. Reports status of all agents (local + remote), AI infrastructure, media stack, and monitorin
Ship It
The full code-change cycle: scope → write → smoke test → commit → review checkpoint → deploy → after-change-mo
Related Agents
LLM Integrator
LLM integration specialist who connects to OpenAI/Anthropic/Ollama APIs, designs prompt templates, implements
Sf Org Verifier
Verifies a Salesforce change in the live org after deployment - smoke probes, data and limit queries, log capt
Deploy Smoke Test
Deploy an IRIS interop production and smoke-test it end-to-end — start the production, feed a sample input, th