Multi-model LLM comparison tool — 17 models, AI judge scoring, web UI + CLI + MCP plugin + Claude Code skill
2 files for Codex, OpenCode and Claude Code: modelmix AGENTS.md, modelmix CLAUDE.md — 79 tokens loaded in every session.
AGENTS.md A 74 tok CLAUDE.md A 5 tok These files are StarShipI/modelmix's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.