Openrouter Agent — Development agent for Claude Code
Runs a model from any of ~60 vendors through OpenRouter's OpenAI-compatible endpoint, billed per token against a prepaid balance rather than a subscription.
How to install Openrouter Agent
Installs to ~/.claude/agents/wherethetunnelends-quorum-openrouter-agent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/WhereTheTunnelEnds/quorum/HEAD/agents/openrouter-agent.md -o ~/.claude/agents/wherethetunnelends-quorum-openrouter-agent.md Restart Claude Code, or start a new session, for it to be picked up.
What Openrouter Agent does
name: openrouter-agent description: Runs a model from any of ~60 vendors through OpenRouter's OpenAI-compatible endpoint, billed per token against a prepaid balance rather than a subscription. One mode - consult (no machine access; the endpoint is a plain chat-completions API with no server-side tool loop). Use to reach a model no local subscription covers, to get a second opinion from a vendor family nothing else here can dispatch to, or when the panel needs a model chosen per question rath
Alternatives in Development
- Codex Orchestrator — CLI tool for delegating tasks to GPT Codex agents via tmux sessions 263 ★
- Agent 03 Endpoint Miner — Agent: EndpointMiner(接口智能分析Agent) 236 ★
- Combat Designer — Designs combat rules, abilities, weapons, states, and initial balance targets 76 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Ollama Agent
Runs a local model served by Ollama on this machine. One mode - consult (no machine access; the endpoint is a
Codex CLI
Codex CLI → any OpenAI-compatible endpoint
Claude Alt Agent
Runs Claude Code as a subprocess on a SECOND Claude subscription, via a long-lived OAuth token in an isolated
Opencode
Coding subagent that runs inside opencode, on any provider and model opencode supports (OpenAI, Google, Moonsh
Provider Debugger
Diagnose live-provider compatibility failures for Kimi, GLM, and other OpenAI-compatible endpoints
Lmstudio Local
A locally-hosted model served through LM Studio's OpenAI-compatible API,
Related Skills
Free LLM Gateway
Local LiteLLM gateway aggregating free LLM providers (Zhipu/SiliconFlow/OpenRouter/NVIDIA/Agnes/SenseNova/dots
Local Delegate
MCP that delegates mechanical text tasks to a local OpenAI-compatible LLM endpoint to conserve Claude subscrip
Halo Harness
Halo Harness: an intuitive, Claude Code-compatible agent harness that drives DeepSeek, GLM, Kimi, Qwen and Cla