Harness Engineering Guide

Audit, design, and implement AI agent harnesses for any codebase. A harness is the constraints, feedback loops, and verification systems surrounding AI coding agents — improving it is the highest-leverage way to improve AI code quality. Three modes: Audit (scorecard), Implement (set up components), Design (full strategy). Use whenever the user mentions harness engineering, agent guardrails, AI coding quality, AGENTS.md, CLAUDE.md setup, agent feedback loops, entropy management, AI code review, vibe coding quality, harness audit, harness score, AI slop, agent-first engineering. Also trigger whe

223 stars 42 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add NeverSight/learn-skills.dev --skill harness-engineering-guide
Manual install
git clone --depth 1 https://github.com/NeverSight/learn-skills.dev.git /tmp/learn-skills.dev
mkdir -p ~/.claude/skills
cp -r /tmp/learn-skills.dev/data/skills-md/13luiz/skills/harness-engineering-guide ~/.claude/skills/harness-engineering-guide

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Harness Engineering Guide

You are a harness engineering consultant. Your job is to audit, design, and implement the environments, constraints, and feedback loops that make AI coding agents work reliably at production scale.

**Core Insight**: Agent = Model + Harness. The harness is everything surrounding the model: tool access, context management, verification, error recovery, and state persistence. Changing only the harness (not the model) improved LangChain's agent from 52.8% to 66.5% on Terminal Bench 2.0.

## Pre-Assessment Gate

Before running an audit, assess 4 complexity signals to determine audit depth. Use the highest triggered level across all signals.

| Signal | Skip | Quick Audit | Full Audit |
|--------|------|-------------|------------|
| **Codebase size** | <500 LOC | 500–10k LOC | >10k LOC |
| **Contributors** (human + agent) | 1 | 2–5 | >5 |
| **CI maturity** | None | Basic (1–2 jobs) | Multi-job pipeline |
| **AI agent role** | Not used / occasional | Regular assist | Primary development workflow |

**Routing rule**: The audit depth equals the **highest level** triggered by any signal. If even one signal points to Full Audit, route to Full Audit.

> **Note**: These thresholds are experience-based heuristics, not hard boundaries. Projects near a boundary (e.g., ~500 LOC or ~10k LOC) should use auditor judgment — consider project complexity, not just line count. Users can always override with `--quick` or request Full Audit directly.
Read the full skill on GitHub

Details

Skill name
harness-engineering-guide
Path
data/skills-md/13luiz/skills/harness-engineering-guide/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Harness Engineering Guide skill do?

Audit, design, and implement AI agent harnesses for any codebase. A harness is the constraints, feedback loops, and verification systems surrounding AI coding agents — improving it is the highest-leverage way to improve AI code quality. Three modes: Audit (scorecard), Implement (set up components), Design (full strategy). Use whenever the user mentions harness engineering, agent guardrails, AI coding quality, AGENTS.md, CLAUDE.md setup, agent feedback loops, entropy management, AI code review, vibe coding quality, harness audit, harness score, AI slop, agent-first engineering. Also trigger whe

How do I install the Harness Engineering Guide skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add NeverSight/learn-skills.dev --skill harness-engineering-guide. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Harness Engineering Guide popular?

It lives in NeverSight/learn-skills.dev, which has 223 GitHub stars and 42 forks.

Related skills

Council

223

NeverSight/learn-skills.dev

Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems.

Other42

Megaeth Developer

223

NeverSight/learn-skills.dev

End-to-end MegaETH development playbook (Feb 2026). Covers wallet operations, token swaps (Kyber Network), eth_sendRawTransactionSync (EIP-7966) for instant receipts, JSON-RPC batching, real-time mini-block subscriptions, storage-aware contract patterns (Solady RedBlackTreeLib), MegaEVM gas model, WebSocket keepalive, bridging from Ethereum, and debugging with mega-evme. Use when building on MegaETH, managing wallets, sending transactions, or deploying contracts.

Software Development42

Openclaw Stock Skill

223

NeverSight/learn-skills.dev

使用 data.diemeng.chat 提供的接口查询股票日线、分钟线、财务指标等数据,支持 A 股等市场。

Finance & Crypto42

Harness Engineering Zh

223

NeverSight/learn-skills.dev

为 AI Agent 友好的代码库搭建和改进 Harness 工程(包括 AGENTS.md、docs/、Lint 规则、Eval 系统、项目级 Prompt 工程)。触发场景:为 AI Agent 设置新项目/空项目,创建 AGENTS.md 或 CLAUDE.md,关于 Harness 工程的问题,让 Agent 在代码库上更高效地工作。当用户感到沮丧或抱怨 Agent 质量时也会触发(例如:'Agent 总是无视规范'、'它从不听从指令'、'为什么它总是做错 X'、'Agent 坏了')— 因为 Agent 输出质量差几乎总是意味着 Harness 缺失,而不是模型问题。涵盖:Context 工程、架构约束、多 Agent 协作、评估、长运行任务 Harness 以及 Agent 质量问题诊断。

AI, LLMs & Agents42

Harness Engineering

223

NeverSight/learn-skills.dev

Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases. Triggers on: new/empty project setup for AI agents, AGENTS.md or CLAUDE.md creation, harness engineering questions, making agents work better on a codebase. ALSO triggers when users are frustrated or complaining about agent quality — e.g. 'the agent keeps ignoring conventions', 'it never follows instructions', 'why does it keep doing X', 'the agent is broken' — because poor agent output almost always signals harness gaps, not model problems. Cov

AI, LLMs & Agents42

Improve

223

NeverSight/learn-skills.dev

Use after completing a task, before claiming done, before handoff, or when asked "what are some improvements?" Surfaces concrete suggestions grounded in session observations.

AI, LLMs & Agents42

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.