harness-forge
SkillMeta-Harness skill that evolves Claude Code's scaffolding — memory, retrieval, context, and prompts — via a propose-score-Pareto optimization loop.
git clone https://github.com/001TMF/harness-forgeTurn Claude Code into its own Meta-Harness — evolve the scaffolding around a fixed model, natively.
Harness Forge is a Claude Code skill that runs an end-to-end harness-optimization loop — propose → score → keep the Pareto-best → repeat — to improve the code around a fixed model: its memory, retrieval, context construction, summarization, prompt templates, and tool-selection logic. The model never changes; the scaffolding gets better.
It is a native reimplementation of the method in Meta-Harness: End-to-End Optimization of Model Harnesses (Lee, Nair, Zhang, Lee, Khattab & Finn, 2026). The original reference repo ships ~1,260 lines of Python (`claudewrapper.py` + `metaharness.py`) whose job is to drive a headless Claude: spawn a session, parse its output, track tool calls, log everything, loop. Inside Claude Code, that runtime already exists as first-class tools. So Harness Forge keeps only the irreducible domain logic — a…
meta-harness- Source
- community
- Known advisories
- 0
- Maintenance
- maintained
- License
- MIT
- Age
- 1 months