autoharness turns your Claude Code sessions into a self-maintaining skills layer
dr_cintas · x · 2026-10-01
autoharness is a self-learning skill layer for Claude Code that watches the work you already do and turns it into skills—no separate data collection or replay loops. It runs automatically once a session has done enough work, or you can type /learn to save a lesson immediately.
Skill hygiene:
- Merges skills covering the same scenario instead of piling up near-copies
- Updates skills while they're in use
- Archives unused ones
- Only touches skills it wrote—yours stay untouched
Why it matters: with the same model, a better harness took CORE-Bench from 42% to 78%, yet people still rebuild harnesses by hand for each new model. autoharness bets the skill layer can maintain itself. Two commands to install inside Claude Code.
More from coding & agent
- headcount: Open-Source Repo Gives Your AI Agent a 16-Department, 172-Skill Company — alex_verem · 2026-10-01
- Open-source 'headcount' gives your AI agent 172 specialists across 16 departments, free — alex_verem · 2026-10-01
- AI coding agents write insecure Supabase RLS policies — dev's CLI scan finds 12 high-severity issues — Real_KingZeotic · 2026-10-01
- AI Agent Polled Every 15 Minutes and Snagged a Fully-Booked 6-Seat Tokyo Restaurant in 13 Hours — armand_ruiz · 2026-10-01
- Higgsfield launches ChatGPT extension bringing computer use into Codex — SimplyAnnisa · 2026-10-01
- LibraryDesignBench tests whether AI agents can design and effectively use code libraries — a1zhang · 2026-10-01