Prompt evaluation workbench as an MCP server — run evals, compare providers, and test assertions directly from Claude Code or any MCP host.
2 files for Codex, OpenCode and Claude Code: mcp-prompt-lab AGENTS.md, mcp-prompt-lab CLAUDE.md — 241 tokens loaded in every session.
AGENTS.md A 236 tok CLAUDE.md A 5 tok These files are nikolasbarwicki/mcp-prompt-lab'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.