shareAI-lab/learn-claude-code：README 来源编辑指南

shareAI-lab/learn-claude-code 的 README 将项目描述为"Bash is all you need - A nano claude code,like 「agent harness」, built from 0 to 1"。本文只整理仓库能直接核验的内容，不把星标、Fork 或宣传语当成质量证明。README 在"Agency Comes from the Model. An Agent Product = Model + Harness."下的说明是：Before we write any code, one thing needs to be clear.。这给出的首先是项目边界，而不是已经完成的生产验证。

从 README 的"Where Agency Comes From"和相关条目看，读者可以先判断它是否解决自己的具体问题：2019 -- OpenAI Five conquers Dota 2. Five neural networks played 45,000 years of Dota 2 against themselves over 10 months, then defeated OG -- the TI8 world champions -- 2-0 in a live match.。如果你的目标与这段说明不一致，就不应仅凭项目热度采用它。这里保留原项目名、命令和组件名，方便回到一手来源核对。 README 还列出了另一条可核对的信息：2013 -- DeepMind DQN plays Atari. A single neural network, receiving only raw pixels and game scores, learned 7 Atari 2600 games -- surpassing prior algorithms and beating human experts in 3 of them.。这类原文条目可以帮助读者设计试运行步骤，但不能代替自己的环境测试。

README 把工作方式分散写在"Where Agency Comes From"等段落中。可确认的线索包括：At the core of every agent is a neural network -- a Transformer, an RNN, a trained function -- shaped by billions of gradient updates on sequences of perception, reasoning, and action. Agency was never bestowed by the surrounding code.。这篇整理没有把未写出的架构、性能或安全边界补成结论；真正的运行链仍应结合仓库目录、配置文件和版本标签检查。

第一次安装应从 README 给出的入口开始。当前可复核的命令是： Harness = Tools + Knowledge + Observation + Action Interfaces + Permissions Tools: file I/O, shell, network, database, browser Knowledge: product docs, domain references, API specs, style guides Observation: git diff, error logs, browser state, sensor data Action: CLI commands, API calls, UI interactions Permissions: sandbox isolation, approval workflows, trust boundaries 如果仓库没有提供命令，本文不会替它编造安装步骤，而是建议先打开 README 的"Agency Comes from the Model. An Agent Product = Model + Harness."部分，确认系统依赖、默认端口和首次初始化动作。