Harness Eval — Structured SE Task Benchmark

Purpose

Evaluate agent quality using 15 structured software engineering task definitions with quantitative scoring. Based on research from revfactory/claude-code-harness which demonstrated 60% improvement (49.5 → 79.3 points) through structured pre-configuration.

Usage

/omcustom:harness-eval                    # Run all 15 benchmarks
/omcustom:harness-eval --preset quick     # Run top 5 high-impact benchmarks
/omcustom:harness-eval --task api-design  # Run specific task benchmark

Quality Dimensions