{"schema_version":"1.0","skill_id":"ecc-agent-benchmarking","name":"Agent Benchmarking","description":"Head-to-head coding agent comparison tool: YAML task definitions with judge criteria, git worktree isolation per agent run, pass rate/cost/time/consistency metrics, and reproducible benchmarking across Claude Code, Aider, Codex, and other agents.","tools":[],"receipt":null}