Open-source Harness Engineering repo turns coding-agent guidance into mechanical guardrails for Claude Code
blaizedsouza · x · 2026-10-23
A reference guide + Claude Code plugin tackles the problem Karpathy named — agents ignoring instructions no matter how carefully AGENTS.md is written — by replacing prose guidance with mechanical enforcement.
What it ships:
- Reference guide mapping 20+ best practices from OpenAI, Anthropic, Augment Code, and practitioners like Karpathy and Boris Cherny to concrete patterns
- /readiness skill: scores your codebase across 8 pillars and 5 maturity levels, saves reports for delta tracking
- /setup skill: Socratic-question-driven setup scaffolding CLAUDE.md files, path-scoped rules, plus enforcement scripts (secret scanning, file size limits, test colocation, generated docs, drift detection) wired into git hooks so bad code gets blocked before it lands
Core idea: instructions can't constrain agents; hooks, linters, and lazily-loaded rules can — without wasting the agent's finite attention. MIT licensed, works with any stack.
More from coding & agent
- DAB, a cross-database agent benchmark, hits EMNLP Oral; best model only 38% pass@1 — adityagp · 2026-10-24
- 27B open-source model beats GPT-5.5 at computer tasks via evolved interfaces, at 1.5% the cost — alex_verem · 2026-10-23
- 27B open-source model beats GPT-5.5 and Opus 4.8 on desktop tasks at 1.5% of the cost — alex_verem · 2026-10-23
- Interactive 3D AI server explainer built in one prompt with Claude and the open-source colorfigures skill — Promptmethus · 2026-10-23
- poem turns Codex sessions into chats — approve agent tasks from your iPhone — patrickreza · 2026-10-23
- Watching AI test your app like a real, picky customer — randal_olson · 2026-10-23