@polydao: I'm sharing with you one of the best papers I've read on Harness Engineering it takes apart Claude Code (Opus 5.5), Cod…
Summary
A tweet recommending a paper on harness engineering that breaks down Claude Code (Opus 5.5), Codex, Gemini CLI and other coding agents into the formula agent = model + harness, covering how agents are built, recurring patterns, future directions, and a checklist for building your own.
View Cached Full Text
Cached at: 10/06/26, 01:51 PM
I’m sharing with you one of the best papers I’ve read on Harness Engineering
it takes apart Claude Code (Opus 5.5), Codex, Gemini CLI and more, and boils all of them down to one line:
agent = model + harness
what you walk away with:
what a harness actually is how today’s coding agents are built under the hood the patterns every one of them repeats where the whole category is heading their checklist for building your own
the model gets the headlines. the harness decides whether the agent works
loop and graph engineering on top of it - in my article below
Similar Articles
@undefinedKi: This might be the most useful paper on AI agents this year. A team at Wavestone AI Lab took apart Claude Code, Codex an…
Wavestone AI Lab dissected 11 coding agents — including Claude Code and Codex — and found they all share a common 7-part harness blueprint (loop, LLM layer, tools, memory, safety, orchestration, extensions), ending with a reusable 90-line harness and 18 design recommendations.
@omarsar0: Build your own harness, folks. This is absolute banger paper from NVIDIA on self-evolving agent harnesses. (bookmark it…
The paper introduces SoL-Pi, an automated harness discovery method that reduces token usage by nearly half and cuts API costs by about a third while maintaining performance on benchmarks using models like GPT-5.6 Sol and Opus 5.
Code as Agent Harness
This survey paper presents a unified view of code as the operational substrate for agent reasoning and execution in agentic systems, organizing the discussion around three layers: harness interface, mechanisms, and scaling.
@tom_doerr: Harness engineering guides for Claude Code and Codex https://github.com/wquguru/harness-books…
A GitHub repository with two books on harness engineering for Claude Code and Codex, exploring how to structure constraints and execution for code-writing AI in real engineering environments.
favorite Agentic Coding Harness
The author compares several agentic coding harnesses (Codex CLI, Claude Code, Gemini CLI, OpenCode, Pi) and finds Pi the leanest and best for local models, praising its simplicity and compatibility with Qwen 27B-MXFP8.