shareAI-lab/learn-claude-code：README 來源編輯指南

shareAI-lab/learn-claude-code 的 README 將專案描述為「Bash is all you need - A nano claude code,like 「agent harness」, built from 0 to 1」。本文只整理倉庫可直接核對的內容，不把 star、Fork 或宣傳語當成品質證明。README 在「Agency Comes from the Model. An Agent Product = Model + Harness.」下寫到：Before we write any code, one thing needs to be clear.。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「Where Agency Comes From」與相關條目，可以先判斷它是否處理你的實際問題：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.。若需求不同，不應只因專案熱度就採用。本文保留原始專案名、命令與元件名，方便回到一手來源核對。 README 另外列出一項可核對的資訊：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.。這類原文條目可用來設計試跑步驟，但不能取代實際環境測試。

README 將運作方式分散在「Where Agency Comes From」等段落。可確認的線索包括：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.。本文不把未寫出的架構、效能或安全邊界補成結論；真正的執行鏈仍要配合目錄、設定檔與版本標籤檢查。

第一次安裝應從 README 指出的入口開始。目前可核對的命令是： 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 如果倉庫沒有命令，本文不會自行編造步驟，而是建議先閱讀「Agency Comes from the Model. An Agent Product = Model + Harness.」，確認系統依賴、預設埠與首次初始化。

日常使用取決於專案文件。README 的「Where Agency Comes From」段落提到：Humans are the original proof. A biological neural network, refined by millions of years of evolutionary pressure, perceives the world through senses, reasons through a brain, and acts through a body.。設定檔、環境變數、權限與資料目錄只在來源明確時才會記錄；沒有寫出的預設值，應在測試環境驗證並保留回滾副本。 同一部分也提到：2019 -- DeepMind AlphaStar masters StarCraft II. AlphaStar beat a professional player 10-1 on the European server -- top 0.15% of 90,000 players.。