引子 · 不是聊天框，是编排台Intro · Not a Chat Box, an Orchestration Console.
你为 Claude Code 付了 Max，却把它当成一个会改文件的聊天框：问一句、看它写、粘走。官方给它的定位也还是「编码工具」。但计划模式、CLAUDE.md、Skills、subagents、MCP、hooks 拼在一起，它的边界不是「能写什么代码」，而是「一台电脑上的活，有多少能由你派出去、再由你验收」。这一章讲清楚这本书的立场：Claude Code 最小的样子是编辑器，最大的样子是你一个人指挥一支 agent 队的编排台 —— 以及为什么停在聊天框那层，等于把付费买到的后一半白扔。You pay for Max and use Claude Code as a chat box that edits files: ask, watch it write, paste it away. The vendor's own one-liner still calls it a coding tool. But plan mode, CLAUDE.md, Skills, subagents, MCP, and hooks add up to something whose limit isn't 'what code it writes,' but 'how much of a machine's work you can delegate — and then verify.' This chapter sets the book's stance: the editor is Claude Code's smallest form; its largest is one person directing a fleet of agents from a single console — and why stopping at the chat box forfeits the second half of what you pay for.
7 分钟 · 初稿 2026.077 Min · Drafted 2026.07
你大概是这样用 Claude Code 的:开一个终端,敲一句要求,看它改文件,扫两眼 diff,合并。偶尔它自己跑了个测试,你觉得挺神。一天下来,它对你来说是一个会动文件的聊天框 —— 比网页版多省下的,只是复制粘贴。Here's probably how you use Claude Code: open a terminal, type a request, watch it edit files, skim the diff, merge. Now and then it runs a test on its own and you're impressed. By day's end, it's a chat box that can touch files — all it saves over the web app is the copy-paste.这没错,但这是它最小的一层。你的 Pro 或 Max 订阅本来就含它,额度和网页版共用一个池子1注 1Note 1Claude 帮助中心 · Use Claude Code with your Pro or Max plan —— Pro 与 Max 订阅均直接包含 Claude Code:一份订阅同时覆盖 Claude 应用(网页 / 桌面 / 移动)与终端里的 Claude Code,两边用量共享同一个额度池。截至 2026-07-17。Claude Help Center · Use Claude Code with your Pro or Max plan — both Pro and Max include Claude Code: one subscription covers the Claude apps (web / desktop / mobile) and Claude Code in the terminal, with usage drawing on a shared limit pool. As of 2026-07-17. —— 也就是说,你从没为「聊天框」单独付费,你付的钱里装着一台大得多的机器。这本书的立场一句话说完:Claude Code 最小的样子是一个会改文件的编辑器,最大的样子,是你一个人指挥并验收一支 agent 队的编排台。停在聊天框那层,等于把后一半白扔。Not wrong — but that's its smallest layer. Your Pro or Max subscription already includes it, drawing on the same usage pool as the web app1注 1Note 1Claude 帮助中心 · Use Claude Code with your Pro or Max plan —— Pro 与 Max 订阅均直接包含 Claude Code:一份订阅同时覆盖 Claude 应用(网页 / 桌面 / 移动)与终端里的 Claude Code,两边用量共享同一个额度池。截至 2026-07-17。Claude Help Center · Use Claude Code with your Pro or Max plan — both Pro and Max include Claude Code: one subscription covers the Claude apps (web / desktop / mobile) and Claude Code in the terminal, with usage drawing on a shared limit pool. As of 2026-07-17. — which means you never paid separately for a chat box; the price you pay contains a much larger machine. The book's stance in one line: Claude Code's smallest form is an editor that changes files; its largest is the console from which one person directs, and then verifies, a fleet of agents. Stopping at the chat box forfeits the second half.
— I
名字里的「Code」,已经装不下它The 'Code' in the Name No Longer Contains It.
官方文档给它的一句话定位是「agentic coding tool」:读你的代码库、改文件、跑命令;入口有终端、IDE、桌面应用和浏览器四个,连的是同一台引擎。2注 2Note 2Claude Code Docs · Overview —— 官方一句话定位:「agentic coding tool」,读你的代码库、改文件、跑命令;入口有终端、IDE、桌面应用与浏览器,连着同一台引擎(CLAUDE.md、设置、MCP 跨入口通用)。同一页列出的能力还有:MCP 接 Google Drive / Jira / Slack、Routines 定时任务、Channels 接 Telegram / Discord 等消息渠道、agent teams 多 agent 协作、headless(claude -p)与 Agent SDK。截至 2026-07-17。Claude Code Docs · Overview — the official one-liner: an 'agentic coding tool' that reads your codebase, edits files, and runs commands; entrances are the terminal, IDE, desktop app, and browser, all wired to one engine (CLAUDE.md, settings, and MCP carry across). The same page also lists: MCP for Google Drive / Jira / Slack, Routines for scheduled runs, Channels for Telegram / Discord and other message inputs, agent teams, headless (claude -p), and the Agent SDK. As of 2026-07-17.这个定位没有错 —— 只是太谦虚。往同一页文档底下翻:用 MCP 接 Google Drive、Jira、Slack;用 Routines 把活挂到日程上定时跑;用 Channels 把 Telegram、Discord 的消息接成任务;开 agent teams 让几个 agent 并行分工;用 claude -p 把它嵌进脚本和 CI。2注 2Note 2Claude Code Docs · Overview —— 官方一句话定位:「agentic coding tool」,读你的代码库、改文件、跑命令;入口有终端、IDE、桌面应用与浏览器,连着同一台引擎(CLAUDE.md、设置、MCP 跨入口通用)。同一页列出的能力还有:MCP 接 Google Drive / Jira / Slack、Routines 定时任务、Channels 接 Telegram / Discord 等消息渠道、agent teams 多 agent 协作、headless(claude -p)与 Agent SDK。截至 2026-07-17。Claude Code Docs · Overview — the official one-liner: an 'agentic coding tool' that reads your codebase, edits files, and runs commands; entrances are the terminal, IDE, desktop app, and browser, all wired to one engine (CLAUDE.md, settings, and MCP carry across). The same page also lists: MCP for Google Drive / Jira / Slack, Routines for scheduled runs, Channels for Telegram / Discord and other message inputs, agent teams, headless (claude -p), and the Agent SDK. As of 2026-07-17.这些能力没有一个长得像「编码工具」—— 它们长得像一张派活的台子。The docs' one-line positioning is an 'agentic coding tool': it reads your codebase, edits files, runs commands; the entrances number four — terminal, IDE, desktop app, and browser — all wired to the same engine.2注 2Note 2Claude Code Docs · Overview —— 官方一句话定位:「agentic coding tool」,读你的代码库、改文件、跑命令;入口有终端、IDE、桌面应用与浏览器,连着同一台引擎(CLAUDE.md、设置、MCP 跨入口通用)。同一页列出的能力还有:MCP 接 Google Drive / Jira / Slack、Routines 定时任务、Channels 接 Telegram / Discord 等消息渠道、agent teams 多 agent 协作、headless(claude -p)与 Agent SDK。截至 2026-07-17。Claude Code Docs · Overview — the official one-liner: an 'agentic coding tool' that reads your codebase, edits files, and runs commands; entrances are the terminal, IDE, desktop app, and browser, all wired to one engine (CLAUDE.md, settings, and MCP carry across). The same page also lists: MCP for Google Drive / Jira / Slack, Routines for scheduled runs, Channels for Telegram / Discord and other message inputs, agent teams, headless (claude -p), and the Agent SDK. As of 2026-07-17. The positioning isn't wrong — just too modest. Scroll down the same page: wire in Google Drive, Jira, and Slack over MCP; put work on a schedule with Routines; turn Telegram and Discord messages into tasks with Channels; fan out agent teams; embed it into scripts and CI with claude -p.2注 2Note 2Claude Code Docs · Overview —— 官方一句话定位:「agentic coding tool」,读你的代码库、改文件、跑命令;入口有终端、IDE、桌面应用与浏览器,连着同一台引擎(CLAUDE.md、设置、MCP 跨入口通用)。同一页列出的能力还有:MCP 接 Google Drive / Jira / Slack、Routines 定时任务、Channels 接 Telegram / Discord 等消息渠道、agent teams 多 agent 协作、headless(claude -p)与 Agent SDK。截至 2026-07-17。Claude Code Docs · Overview — the official one-liner: an 'agentic coding tool' that reads your codebase, edits files, and runs commands; entrances are the terminal, IDE, desktop app, and browser, all wired to one engine (CLAUDE.md, settings, and MCP carry across). The same page also lists: MCP for Google Drive / Jira / Slack, Routines for scheduled runs, Channels for Telegram / Discord and other message inputs, agent teams, headless (claude -p), and the Agent SDK. As of 2026-07-17. None of these is shaped like a coding tool — they're shaped like a dispatch desk.这本书不列全部功能。它按「一台编排台需要什么」挑出核心的六件,每件一章:3注 3Note 3Claude Code Docs · Extend Claude Code —— 扩展机制总览:CLAUDE.md 是每次会话都加载的持久上下文;Skills 是按需加载的知识与流程;subagents 在隔离上下文里干活、只交回摘要;MCP 接外部服务;hooks 在生命周期事件上必然触发。并明确划线:写在 CLAUDE.md 或 skill 里的指令「是请求,不是保证」—— 必须每次都发生的规矩,要写成 hook。截至 2026-07-17。Claude Code Docs · Extend Claude Code — the extension map: CLAUDE.md is persistent context loaded every session; Skills are on-demand knowledge and workflows; subagents work in isolated context and return only summaries; MCP connects external services; hooks fire deterministically on lifecycle events. And the explicit line: an instruction in CLAUDE.md or a skill is 'a request, not a guarantee' — a rule that must run every time belongs in a hook. As of 2026-07-17.This book doesn't list every feature. It picks the six core pieces by asking what a console needs, one chapter each:3注 3Note 3Claude Code Docs · Extend Claude Code —— 扩展机制总览:CLAUDE.md 是每次会话都加载的持久上下文;Skills 是按需加载的知识与流程;subagents 在隔离上下文里干活、只交回摘要;MCP 接外部服务;hooks 在生命周期事件上必然触发。并明确划线:写在 CLAUDE.md 或 skill 里的指令「是请求,不是保证」—— 必须每次都发生的规矩,要写成 hook。截至 2026-07-17。Claude Code Docs · Extend Claude Code — the extension map: CLAUDE.md is persistent context loaded every session; Skills are on-demand knowledge and workflows; subagents work in isolated context and return only summaries; MCP connects external services; hooks fire deterministically on lifecycle events. And the explicit line: an instruction in CLAUDE.md or a skill is 'a request, not a guarantee' — a rule that must run every time belongs in a hook. As of 2026-07-17.
部件Piece
它替你做什么What it does for you
哪章Chapter
计划模式Plan mode
动手前先交方案,你批准了它才改Proposes before acting; edits only after your approval
第 2 章Ch. 2
CLAUDE.md
项目的长期记忆,每次开工自动加载The project's long-term memory, loaded every session
第 3 章Ch. 3
Skills
把重复的流程收编成资产,用到才加载Codifies repeated routines into assets, loaded on demand
第 4 章Ch. 4
Subagents
独立上下文的分身,干完只交回结论Workers in their own context, handing back only conclusions
第 5 章Ch. 5
MCP
把 issue、工单、数据库接进上下文Wires issues, tickets, and databases into context
第 6 章Ch. 6
Hooks
固定时机自动执行的规矩,不靠模型自觉Rules that fire at set moments, not by the model's goodwill
第 7 章Ch. 7
单看,每一件都不新奇 —— 别的工具也有记忆、也有插件。拼在一起才变质:计划模式让你从「看它写每一行」退到「审方案、验结果」4注 4Note 4Claude Code Docs · Permission modes —— 计划模式:让 Claude 调研、提方案,但不动手改你的源码 —— 它会读文件、跑只读的探索命令、写出一份计划;在你批准计划之前,编辑一律被挡。Shift+Tab 或 /plan 进入。截至 2026-07-17。Claude Code Docs · Permission modes — plan mode 'tells Claude to research and propose changes without making them': it reads files, runs exploratory commands, and writes a plan, but does not edit your source; edits stay blocked until you approve the plan. Enter via Shift+Tab or /plan. As of 2026-07-17.;CLAUDE.md 和 Skills 让你不用每次重新交代;subagents 让活离开你的上下文,headless 让活离开你的终端(第 8 章);hooks 把「希望它记得」换成「到点必然发生」3注 3Note 3Claude Code Docs · Extend Claude Code —— 扩展机制总览:CLAUDE.md 是每次会话都加载的持久上下文;Skills 是按需加载的知识与流程;subagents 在隔离上下文里干活、只交回摘要;MCP 接外部服务;hooks 在生命周期事件上必然触发。并明确划线:写在 CLAUDE.md 或 skill 里的指令「是请求,不是保证」—— 必须每次都发生的规矩,要写成 hook。截至 2026-07-17。Claude Code Docs · Extend Claude Code — the extension map: CLAUDE.md is persistent context loaded every session; Skills are on-demand knowledge and workflows; subagents work in isolated context and return only summaries; MCP connects external services; hooks fire deterministically on lifecycle events. And the explicit line: an instruction in CLAUDE.md or a skill is 'a request, not a guarantee' — a rule that must run every time belongs in a hook. As of 2026-07-17.。每一件都在回答同一个问题:怎么让你少盯一点,而不失控。Taken alone, none is novel — other tools have memory and plugins too. Together they change substance: plan mode moves you from watching every line to approving an approach and checking a result4注 4Note 4Claude Code Docs · Permission modes —— 计划模式:让 Claude 调研、提方案,但不动手改你的源码 —— 它会读文件、跑只读的探索命令、写出一份计划;在你批准计划之前,编辑一律被挡。Shift+Tab 或 /plan 进入。截至 2026-07-17。Claude Code Docs · Permission modes — plan mode 'tells Claude to research and propose changes without making them': it reads files, runs exploratory commands, and writes a plan, but does not edit your source; edits stay blocked until you approve the plan. Enter via Shift+Tab or /plan. As of 2026-07-17.; CLAUDE.md and Skills spare you re-briefing every session; subagents move work out of your context, headless moves it off your terminal (chapter 8); hooks replace 'hope it remembers' with 'fires at the appointed moment'3注 3Note 3Claude Code Docs · Extend Claude Code —— 扩展机制总览:CLAUDE.md 是每次会话都加载的持久上下文;Skills 是按需加载的知识与流程;subagents 在隔离上下文里干活、只交回摘要;MCP 接外部服务;hooks 在生命周期事件上必然触发。并明确划线:写在 CLAUDE.md 或 skill 里的指令「是请求,不是保证」—— 必须每次都发生的规矩,要写成 hook。截至 2026-07-17。Claude Code Docs · Extend Claude Code — the extension map: CLAUDE.md is persistent context loaded every session; Skills are on-demand knowledge and workflows; subagents work in isolated context and return only summaries; MCP connects external services; hooks fire deterministically on lifecycle events. And the explicit line: an instruction in CLAUDE.md or a skill is 'a request, not a guarantee' — a rule that must run every time belongs in a hook. As of 2026-07-17.. Every piece answers the same question: how you watch less without losing the thread.
— II
边界重画:能派多少,验得动多少The Boundary, Redrawn: What You Can Delegate — and Verify.
Claude Code 最省的不是敲代码的时间,而是你从「自己动手」切到「派活 + 验收」的整个工作方式。What Claude Code saves most is not typing time, but the whole shift from doing the work yourself to delegating and verifying it.
本书的第一条判断The first judgment of the book
所以量它的尺子得换。旧尺子问「它能写什么代码」—— 按这把尺子,它和一打同类挤在同一条跑道上。新尺子问「一台电脑上的活,有多少能由你派出去、再由你验收」—— 按这把尺子,写代码只是它顺手的一类活:排查一个线上报错、迁移两千个文件、盯着 CI 修失败、把一夜的日志读成三行结论,都在射程里。So the ruler has to change. The old ruler asks what code it can write — by that ruler it's crowded onto one track with a dozen rivals. The new ruler asks how much of a machine's work you can send out and then verify — by that ruler, writing code is just one job it happens to do: tracing a production error, migrating two thousand files, watching CI and fixing failures, reading a night of logs into three lines, all in range.注意新尺子的后半句。派活是容易的一半;难的一半是确认它真做对了。官方最佳实践排在最前面的一条,不是「写更好的 prompt」,而是给它一个它能自己跑的检查 —— 测试、构建、一张能对比的截图 —— 因为能自动验的活,你才敢真放手。5注 5Note 5Claude Code Docs · Best practices —— 验证一节的第一条:给 Claude 一个它能自己跑的检查 —— 测试、构建、一张能对比的截图;没有检查,「看起来做完了」就是唯一信号,你就是人肉验证回路。并要它交证据(测试输出、跑过的命令与返回)而不是宣称成功。截至 2026-07-17。Claude Code Docs · Best practices — the first rule of the verification section: give Claude a check it can run — tests, a build, a screenshot to compare; without one, 'looks done' is the only signal and you are the verification loop. And have it show evidence (test output, the command it ran and what it returned) rather than claim success. As of 2026-07-17.这本书把「验收」单独设为第 9 章,也是全书的书眼:别的教程教你怎么派活,这本书还要你带着凭据收活。Mind the second half of the new ruler. Delegating is the easy half; the hard half is confirming it got it right. The first rule in the vendor's own best practices isn't better prompts — it's giving it a check it can run itself: tests, a build, a screenshot to compare — because only work that can verify itself is work you dare truly release.5注 5Note 5Claude Code Docs · Best practices —— 验证一节的第一条:给 Claude 一个它能自己跑的检查 —— 测试、构建、一张能对比的截图;没有检查,「看起来做完了」就是唯一信号,你就是人肉验证回路。并要它交证据(测试输出、跑过的命令与返回)而不是宣称成功。截至 2026-07-17。Claude Code Docs · Best practices — the first rule of the verification section: give Claude a check it can run — tests, a build, a screenshot to compare; without one, 'looks done' is the only signal and you are the verification loop. And have it show evidence (test output, the command it ran and what it returned) rather than claim success. As of 2026-07-17. That's why review gets its own chapter 9, the centerpiece of this book: other tutorials teach you to hand work out; this one has you collect it with evidence.
— III
先量一次你的活First, Measure Your Own Work.
往下读之前,先给自己的活拍一张底片:Before reading on, take a baseline photo of your own work:
01
翻两周,挑 5 件你亲手做完的活Scroll back two weeks, pick 5 things you did by hand
不限写代码:排查过的一个报错、迁移过的一批文件、清洗过的一份数据、写过的一份发布说明 —— 挑 5 件当时从头到尾自己动手的。Not just coding: an error you traced, a batch of files you migrated, a dataset you cleaned, release notes you wrote — pick 5 you did end to end yourself.
02
给每件写一条「它能自己跑的检查」Write each one a check it could run itself
想象把这件活派出去:你能不能写出一条测试、一条命令、一个可对比的产出,来判断它做没做对?写得出、写不出、拿不准,各自标上。Imagine delegating it: could you write a test, a command, or a comparable output that decides whether it was done right? Mark each: can, can't, unsure.
03
数「写得出」的有几件Count the 'can' rows
那几件是你现在就能派出去的活;「拿不准」的部分,是这本书接下来九章要补的。读完回来重标一遍 —— 这张表就是你的前后对照。Those are the jobs you could delegate today; the 'unsure' rows are what the next nine chapters fill in. Re-mark the table when you finish — it's your before-and-after.
写代码是它最小的样子,
指挥一支 agent 队才是最大的.
Writing code is its smallest form;
directing a fleet of agents is its largest.
Aklman Library
— 讨论Discussion
讨论Discussion.
评论区初始化中…Initializing comments…
01 / 01
没有匹配结果No matches.
换个关键词，或按 Esc 回到页面Try another keyword, or press Esc to return