by jrenaldi79 · Codex Skill · ★ 39
Harness Engineering and Best Practices for Coding Agents A reference guide and Claude Code plugin for long-running AI coding agent harnesses Andrej Karpathy put it bluntly: "The agents do not listen to my instructions." They bloat abstractions, copy-paste code blocks, and ignore style guidance, no matter how carefully you write your AGENTS.md. If the person who coined "context engineering" can't get agents to follow written rules, the answer isn't better prompting. It's mechanical enforcement: git hooks that
| Stars | 39 |
| Forks | 5 |
| Language | JavaScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 67.3128173741324/100 |
| Open Issues | 1 |
| Last Updated | 2026-03-26 |
| Created | 2026-03-11 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~35k |
These tools work well together with harness-engineering for enhanced workflows:
Explore other popular codex skill tools:
harness-engineering is Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+ best practices. Bootstrap with one command.. It is categorized as a Codex Skill with 39 GitHub stars.
harness-engineering is primarily written in JavaScript. It covers topics such as agents-md, ai-agents, ai-coding.
You can find installation instructions and usage details in the harness-engineering GitHub repository at github.com/jrenaldi79/harness-engineering. The project has 39 stars and 5 forks, indicating an active community.
harness-engineering is released under the MIT license, making it free to use and modify according to the license terms.