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.
- ✓Recently active
- ✓Clear description
- !No standard license detected
git clone https://github.com/10xChengTu/harness-engineering && cp harness-engineering/*.md ~/.claude/agents/2 items in this repository
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。
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. Covers: context engineering, architectural constraints, multi-agent coordination, evaluation, long-running agent harness, and diagnosis of agent quality issues.
Subagents overview
What people ask about harness-engineering
What is 10xChengTu/harness-engineering?
+
10xChengTu/harness-engineering is subagents for the Claude AI ecosystem. 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. It has 99 GitHub stars and its last recorded update is dated 2026-08-02.
How do I install harness-engineering?
+
You can install harness-engineering by cloning the repository (https://github.com/10xChengTu/harness-engineering) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is 10xChengTu/harness-engineering safe to use?
+
Our security agent has analyzed 10xChengTu/harness-engineering and assigned a Trust Score of 49/100 (tier: Caution). See the full breakdown of passed checks and flags on this page.
Who maintains 10xChengTu/harness-engineering?
+
10xChengTu/harness-engineering is maintained by 10xChengTu. The last recorded GitHub activity is dated 2026-08-02, with 0 open issues.
Are there alternatives to harness-engineering?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy harness-engineering to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/10xchengtu-harness-engineering)<a href="https://claudewave.com/repo/10xchengtu-harness-engineering"><img src="https://claudewave.com/api/badge/10xchengtu-harness-engineering" alt="Featured on ClaudeWave: 10xChengTu/harness-engineering" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.