Skip to content

Latest commit

 

History

History
72 lines (52 loc) · 2.71 KB

File metadata and controls

72 lines (52 loc) · 2.71 KB

Harness Engineering

Your model is not the bottleneck.

Your harness is.

if your agent only works when AGENTS.md keeps growing:
  you do not have alignment
  you have prompt debt

fix:
  smaller root router
  harder verification gates
  repo-specific evals

Public Entry

What This Repo Ships

What It Solves

Most agent failure still comes from the same four boring causes:

  • the repo is illegible
  • verification is weak
  • old paths still grow
  • autonomy exceeds the fences

This skill packages the counter-pattern into something a repo can actually enforce:

  1. shrink the root instruction surface into a router
  2. pin durable truth into named docs and commands
  3. fence bad paths with scripts, CI, and compatibility boundaries
  4. prove the change with meaningful verification and repo-specific evals

OpenClaw Proof

  • Root context shrank from 229 lines to 66
  • Historical benchmark: 92.0 review-loop vs 47.3 single-pass
  • Release chain now guards skill data, landing pages, schema, sitemap, and smoke coverage together

Quick Start

  1. Read SKILL.md.
  2. Run python scripts/harness_audit.py <repo-root>.
  3. Use references/prompt-kit.md to choose the smallest intervention.
  4. Use references/eval-playbook.md when you need repo-specific evals.

Community

  • WeChat group: scan the QR code below for the OpenClaw / Harness Engineering community.

OpenClaw 微信群二维码