harness-forge — tool profile and history

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).

Active

Canonical source ↗

Language
Python
License
MIT
Created
Last activity
Topics
  • agent-skills
  • agents
  • claude-code
  • claude-skill
  • llm
  • meta-harness
  • pareto-optimization
  • prompt-optimization

Install git clone https://github.com/001TMF/harness-forge ~/.claude/skills/harness-forge

Current measurement

76GitHub stars-1 (-1.3 %)
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
76GitHub stars
76GitHub stars
76GitHub stars
76GitHub stars
77GitHub stars
77GitHub stars
76GitHub stars
76GitHub stars
76GitHub stars
76GitHub stars
76GitHub stars
76GitHub stars
76GitHub stars
75GitHub stars
75GitHub stars
75GitHub stars
75GitHub stars
75GitHub stars
75GitHub stars
75GitHub stars
75GitHub stars
75GitHub stars
75GitHub stars

Classifications

Domains
Type
Agent skills
Use cases

These entries declare the same topics. No similarity is inferred: only the shared topics are stated.