Harness Harness — Development skill for Claude Code

Harness Harness

**The self-improving agentic harness for Claude Code (which is a harness for Claude LLM).**

Coding agents harness LLMs. But who harnesses these coding agents?

Meet **Harness Harness** — a self-organizing harness that works alongside your existing hooks and keeps your agent **focused**, **updated**, **reminded**, **refueled**, and **learning** over time, automatically.

**Disclaimer:** Harness Harness currently works with Claude Code only. Support for other coding agents is on the way. Use at your own risk (and enjoyment). All comments and suggestions are welcome.

What It Does

Claude Code is a harness for the Claude LLM. Harness Harness is a harness for Claude Code. It observes what context your agent actually uses, measures its effectiveness, and continuously evolves to deliver better results — without you having to manually tune anything.

• Focused — Intent-based routing loads only the rules that matter for each task. Frontend work gets design system rules. Backend work gets API conventions. No more dumping everything into every prompt.
• Updated — Session state (objectives, decisions, blockers) persists to the filesystem. When Claude's context compacts, nothing is lost. Your agent always knows what it was doing.
• Reminded — Budget-aware assembly fills four priority slots (identity, route rules, working memory, traces) within a token budget. The right rules are always present, in the right order.
• Refueled — After compaction, critical context is re-injected automatically. Your agent recovers from context compression instead of losing its way.
• Learning — Every rule is scored by how often Claude actually references it. Weekly analysis generates proposals to optimize your config. Rules that help get promoted. Rules that waste tokens get demoted. The harness improves itself.

How It Works

You send a message
    ↓
Smart Assembler classifies intent (frontend? backend? docs?)
    ↓
Loads the matching route confi