{"repo":"001TMF/harness-forge","free":true,"listed":false,"github":"https://github.com/001TMF/harness-forge","clone":"git clone https://github.com/001TMF/harness-forge.git","description":"Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts) via a native propose→score→Pareto loop. Native reimplementation of Meta-Harness (Lee et al. 2026).","language":"Python","stars":75,"topics":["agent-skills","agents","claude-code","claude-skill","llm","meta-harness","pareto-optimization","prompt-optimization"],"license":"MIT","category":"ai-agents","readme_excerpt":"Turn Claude Code into its own Meta-Harness — evolve the scaffolding around a fixed model, natively. -555) 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 ( claude wrapper.py + meta harness.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 cheap scorer — and expresses the entire outer loop as native orchestration. The whole search becomes 75 lines instead of 1,260. --- The idea in one picture The proposer is the mutation operator. The frontier is the search memory. The model is frozen throughout — which is exactly why this fits a fixed / off-the-shelf-API deployment, where you can't change the weights and the gain has to come from the harness. The paper's headline result was +7.7 accuracy points at 4× fewer context tokens on text classification — a pure harness-side win. Harness Forge re","default_branch":null,"files":null,"tree":[],"storefront":"/r/001TMF","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/001TMF/harness-forge/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}