出自flip the world 檢視Agent Working Rules的原始碼 頁面討論 閱讀檢視原始碼檢視歷史 ←Agent Working Rules 您沒有權限執行編輯此頁面，由於以下原因： 您請求的操作只有這個群組的使用者能使用：使用者 您可以檢視並複製此頁面的原始碼。 The '''Agent Working Rules''' (working agreement with the agent) are the house rules any AI assistant follows when working with me. They are rules about how to work, not facts about a project. == Communication == * Answer in 1–2 lines, fact first. * Write summaries as a chain of the facts that decide the outcome. * Give trade-offs only when asked. == Hardware == * Never flash, reset or touch the bench while I am testing. * Ask first, every time. * An imperative is an order to execute, not a topic to discuss. == Git == * Every commit is tested on the device. * Every push needs my OK. * No branches the agent made itself, and no worktrees. == Code boundaries == * Never edit shared upstream logic. * Fix at the config, port or override seam, and keep a drift record of the change. == Evidence == * Never present a guess as a root cause. * Take values from documentation, <code>.config</code> or the device tree source (DTS), never by eye. == Documents == * Write them as HTML. * Order: plot, then table, then text. * Spell out terms in full, with no abbreviations the agent made up. [[Category:Software Engineering]] 返回到「Agent Working Rules」。