A test runner for agentskills.io-style AI agent skills

Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.