4 4
5# 探索 .claude 目錄5# 探索 .claude 目錄
6 6
7> Claude Code 讀取 CLAUDE.md、settings.json、hooks、skills、commands、subagents、rules 和自動記憶的位置。探索您專案中的 .claude 目錄和主目錄中的 ~/.claude。7> Claude Code 讀取 CLAUDE.md、settings.json、hooks、skills、commands、subagents、workflows、rules 和自動記憶的位置。探索您專案中的 .claude 目錄和主目錄中的 ~/.claude。
8
9export const ClaudeExplorer = () => {
10 const A = useMemo(() => ({href, children}) => <a href={href} style={{
11 color: 'var(--ce-accent)',
12 textDecoration: 'none',
13 borderBottom: '1px dotted var(--ce-accent)'
14 }}>{children}</a>, []);
15 const C = useMemo(() => ({children}) => <code style={{
16 fontFamily: 'var(--ce-mono)',
17 fontSize: '0.92em',
18 padding: '1px 4px',
19 borderRadius: '3px',
20 background: 'var(--ce-surface)',
21 border: '0.5px solid var(--ce-border-subtle)'
22 }}>{children}</code>, []);
23 const commandsNote = useMemo(() => <>Commands and skills are now the same mechanism. For new workflows, use <A href="/en/skills">skills/</A> instead: same <C>/name</C> invocation, plus you can bundle supporting files.</>, []);
24 const FILE_TREE = useMemo(() => ({
25 project: {
26 label: 'your-project/',
27 children: [{
28 id: 'claude-md',
29 label: 'CLAUDE.md',
30 type: 'file',
31 icon: 'md',
32 color: '#6A9BCC',
33 badge: 'committed',
34 oneLiner: 'Project instructions Claude reads every session',
35 when: 'Loaded into context at the start of every session',
36 description: 'Project-specific instructions that shape how Claude works in this repository. Put your conventions, common commands, and architectural context here so Claude operates with the same assumptions your team does.',
37 tips: ['Target under 200 lines. Longer files still load in full but may reduce adherence', <>CLAUDE.md loads into every session. If something only matters for specific tasks, move it to a <A href="/en/skills">skill</A> or a path-scoped <A href="/en/memory#organize-rules-with-claude/rules/">rule</A> so it loads only when needed</>, 'List the commands you run most, like build, test, and format, so Claude knows them without you spelling them out each time', <>Run <C>/memory</C> to open and edit CLAUDE.md from within a session</>, <>Also works at <C>.claude/CLAUDE.md</C> if you prefer to keep the project root clean</>],
38 exampleIntro: 'This example is for a TypeScript and React project. It lists the build and test commands, the framework conventions Claude should follow, and project-specific rules like export style and file layout.',
39 example: `# Project conventions
40
41## Commands
42- Build: \`npm run build\`
43- Test: \`npm test\`
44- Lint: \`npm run lint\`
45
46## Stack
47- TypeScript with strict mode
48- React 19, functional components only
49
50## Rules
51- Named exports, never default exports
52- Tests live next to source: \`foo.ts\` -> \`foo.test.ts\`
53- All API routes return \`{ data, error }\` shape`,
54 docsLink: '/en/memory'
55 }, {
56 id: 'mcp-json',
57 label: '.mcp.json',
58 type: 'file',
59 icon: 'json',
60 color: '#9B7BC4',
61 badge: 'committed',
62 oneLiner: 'Project-scoped MCP servers, shared with your team',
63 when: <>Servers connect when the session begins. Tool schemas are deferred by default and load on demand via <A href="/en/mcp#scale-with-mcp-tool-search">tool search</A></>,
64 description: <>Configures Model Context Protocol (MCP) servers that give Claude access to external tools: databases, APIs, browsers, and more. This file holds the project-scoped servers your whole team uses. Personal servers you want to keep to yourself go in <C>~/.claude.json</C> instead.</>,
65 tips: [<>Use environment variable references for secrets: <C>{'${GITHUB_TOKEN}'}</C></>, <>Lives at the project root, not inside <C>.claude/</C></>, <>For servers only you need, run <C>claude mcp add --scope user</C>. This writes to <C>~/.claude.json</C> instead of <C>.mcp.json</C></>],
66 exampleIntro: <>This example configures the GitHub MCP server so Claude can read issues and open pull requests. The <C>{'${GITHUB_TOKEN}'}</C> reference is read from your shell environment when Claude Code starts the server, so the token never lands in the file.</>,
67 example: `{
68 "mcpServers": {
69 "github": {
70 "command": "npx",
71 "args": ["-y", "@modelcontextprotocol/server-github"],
72 "env": {
73 "GITHUB_TOKEN": "\${GITHUB_TOKEN}"
74 }
75 }
76 }
77}`,
78 docsLink: '/en/mcp'
79 }, {
80 id: 'worktreeinclude',
81 label: '.worktreeinclude',
82 type: 'file',
83 icon: 'md',
84 color: '#8FA876',
85 badge: 'committed',
86 oneLiner: 'Gitignored files to copy into new worktrees',
87 when: <>Read when Claude creates a git worktree via <C>--worktree</C>, the <C>EnterWorktree</C> tool, or subagent <C>isolation: worktree</C></>,
88 description: <>Lists gitignored files to copy from your main repository into each new worktree. Worktrees are fresh checkouts, so untracked files like <C>.env</C> are missing by default. Patterns here use <C>.gitignore</C> syntax. Only files that match a pattern and are also gitignored get copied, so tracked files are never duplicated.</>,
89 tips: [<>Lives at the project root, not inside <C>.claude/</C></>, <>Git-only: if you configure a <A href="/en/hooks#worktreecreate">WorktreeCreate hook</A> for a different VCS, this file is not read. Copy files inside your hook script instead</>, <>Also applies to parallel sessions in the <A href="/en/desktop#work-in-parallel-with-sessions">desktop app</A></>],
90 exampleIntro: 'This example copies your local environment files and a secrets config into every worktree Claude creates. Comments start with # and blank lines are ignored, same as .gitignore.',
91 example: `# Local environment
92.env
93.env.local
94
95# API credentials
96config/secrets.json`,
97 docsLink: '/en/worktrees#copy-gitignored-files-into-worktrees'
98 }, {
99 id: 'dot-claude',
100 label: '.claude/',
101 type: 'folder',
102 icon: 'folder',
103 color: 'var(--ce-accent)',
104 oneLiner: 'Project-level configuration, rules, and extensions',
105 description: 'Everything Claude Code reads that is specific to this project. If you use git, commit most files here so your team shares them; a few, like settings.local.json, are automatically gitignored. Each file badge shows which.',
106 children: [{
107 id: 'settings-json',
108 label: 'settings.json',
109 type: 'file',
110 icon: 'json',
111 color: 'var(--ce-text-3)',
112 badge: 'committed',
113 oneLiner: 'Permissions, hooks, and configuration',
114 when: <>Overrides global <C>~/.claude/settings.json</C>. Local settings, CLI flags, and managed settings override this</>,
115 description: 'Settings that Claude Code applies directly. Permissions control which commands and tools Claude can use; hooks run your scripts at specific points in a session. Unlike CLAUDE.md, which Claude reads as guidance, these are enforced whether Claude follows them or not.',
116 contains: [<><A href="/en/permissions">permissions</A>: allow, deny, or prompt before Claude uses specific tools or commands</>, <><A href="/en/hooks">hooks</A>: run your own scripts on events like before a tool call or after a file edit</>, <><A href="/en/statusline">statusLine</A>: customize the line shown at the bottom while Claude works</>, <><A href="/en/settings#available-settings">model</A>: pick a default model for this project</>, <><A href="/en/settings#environment-variables">env</A>: environment variables set in every session</>, <><A href="/en/output-styles">outputStyle</A>: select a custom system-prompt style from output-styles/</>],
117 tips: [<>Bash permission patterns support wildcards: <C>Bash(npm test *)</C> matches any command starting with <C>npm test</C></>, <>Array settings like <C>permissions.allow</C> combine across all scopes; scalar settings like <C>model</C> use the most specific value</>],
118 exampleIntro: <>This example allows <C>npm test</C> and <C>npm run</C> commands without prompting, blocks <C>rm -rf</C>, and runs Prettier on files after Claude edits or writes them.</>,
119 example: `{
120 "permissions": {
121 "allow": [
122 "Bash(npm test *)",
123 "Bash(npm run *)"
124 ],
125 "deny": [
126 "Bash(rm -rf *)"
127 ]
128 },
129 "hooks": {
130 "PostToolUse": [{
131 "matcher": "Edit|Write",
132 "hooks": [{
133 "type": "command",
134 "command": "jq -r '.tool_input.file_path' | xargs npx prettier --write"
135 }]
136 }]
137 }
138}`,
139 docsLink: '/en/settings'
140 }, {
141 id: 'settings-local-json',
142 label: 'settings.local.json',
143 type: 'file',
144 icon: 'json',
145 color: 'var(--ce-text-3)',
146 badge: 'gitignored',
147 oneLiner: 'Your personal settings overrides for this project',
148 when: 'Highest of the user-editable settings files; CLI flags and managed settings still take precedence',
149 description: 'Personal settings that take precedence over the project defaults. Same JSON format as settings.json, but not committed. Use this when you need different permissions or defaults than the team config.',
150 tips: [<>Same schema as settings.json. Array settings like <C>permissions.allow</C> combine across scopes; scalar settings like <C>model</C> use the local value</>, <>Claude Code adds this file to <C>~/.config/git/ignore</C> the first time it writes one. If you use a custom <C>core.excludesFile</C>, add the pattern there too. To share the ignore rule with your team, also add it to the project <C>.gitignore</C></>],
151 exampleIntro: 'This example adds Docker permissions on top of whatever the team settings.json allows.',
152 example: `{
153 "permissions": {
154 "allow": [
155 "Bash(docker *)"
156 ]
157 }
158}`,
159 docsLink: '/en/settings'
160 }, {
161 id: 'rules',
162 label: 'rules/',
163 type: 'folder',
164 icon: 'folder',
165 color: '#9B7BC4',
166 oneLiner: 'Topic-scoped instructions, optionally gated by file paths',
167 when: <>Rules without <C>paths:</C> load at session start. Rules with <C>paths:</C> load when a matching file enters context</>,
168 description: [<>Project instructions split into topic files that can load conditionally based on file paths. A rule without <C>paths:</C> frontmatter loads at session start like CLAUDE.md; a rule with <C>paths:</C> loads only when Claude reads a matching file.</>, <>Like CLAUDE.md, rules are guidance Claude reads, not configuration Claude Code enforces. For guaranteed behavior use <A href="/en/hooks">hooks</A> or <A href="/en/permissions">permissions</A>.</>],
169 tips: [<>Use <C>paths:</C> frontmatter with globs to scope rules to directories or file types</>, <>Subdirectories work: <C>.claude/rules/frontend/react.md</C> is discovered automatically</>, 'When CLAUDE.md approaches 200 lines, start splitting into rules'],
170 docsLink: '/en/memory#organize-rules-with-claude/rules/',
171 children: [{
172 id: 'rule-testing',
173 label: 'testing.md',
174 type: 'file',
175 icon: 'md',
176 color: '#9B7BC4',
177 badge: 'committed',
178 oneLiner: 'Test conventions scoped to test files',
179 when: <>Loaded when Claude reads a file matching the <C>paths:</C> globs below</>,
180 description: <>An example rule that only loads when Claude is working on test files. The <C>paths:</C> globs in the frontmatter define which files trigger it; here, anything ending in .test.ts or .test.tsx. For other files, this rule is not loaded into context.</>,
181 example: `---
182paths:
183 - "**/*.test.ts"
184 - "**/*.test.tsx"
185
186# Testing Rules
187
188- Use descriptive test names: "should [expected] when [condition]"
189- Mock external dependencies, not internal modules
190- Clean up side effects in afterEach`
191 }, {
192 id: 'rule-api',
193 label: 'api-design.md',
194 type: 'file',
195 icon: 'md',
196 color: '#9B7BC4',
197 badge: 'committed',
198 oneLiner: 'API conventions scoped to backend code',
199 when: <>Loaded when Claude reads a file matching the <C>paths:</C> glob below</>,
200 description: <>A second example showing a rule scoped to backend code. The <C>paths:</C> glob matches files under src/api/, so these conventions load only when Claude is editing API routes.</>,
201 example: `---
202paths:
203 - "src/api/**/*.ts"
204
205# API Design Rules
206
207- All endpoints must validate input with Zod schemas
208- Return shape: { data: T } | { error: string }
209- Rate limit all public endpoints`
210 }]
211 }, {
212 id: 'skills',
213 label: 'skills/',
214 type: 'folder',
215 icon: 'folder',
216 color: '#D4A843',
217 oneLiner: 'Reusable prompts you or Claude invoke by name',
218 when: <>Invoked with <C>/skill-name</C> or when Claude matches the task to a skill</>,
219 description: <>Each skill is a folder with a SKILL.md file plus any supporting files it needs. By default, both you and Claude can invoke a skill. Use frontmatter to control that: <C>disable-model-invocation: true</C> for user-only workflows like <C>/deploy</C>, or <C>user-invocable: false</C> to hide from the <C>/</C> menu while Claude can still invoke it.</>,
220 tips: [<>Skills accept arguments: <C>/deploy staging</C> passes "staging" as <C>$ARGUMENTS</C>. Use <C>$0</C>, <C>$1</C>, and so on for positional access</>, <>The <C>description</C> frontmatter determines when Claude auto-invokes the skill</>, 'Bundle reference docs alongside SKILL.md. Claude knows the skill directory path and can read supporting files when you mention them'],
221 docsLink: '/en/skills',
222 children: [{
223 id: 'skill-review',
224 label: 'security-review/',
225 type: 'folder',
226 icon: 'folder',
227 color: '#D4A843',
228 oneLiner: 'A skill bundling SKILL.md with supporting files',
229 children: [{
230 id: 'skill-review-md',
231 label: 'SKILL.md',
232 type: 'file',
233 icon: 'md',
234 color: '#D4A843',
235 badge: 'committed',
236 oneLiner: 'Entrypoint: trigger, invocability, instructions',
237 when: <>User types <C>/security-review <target></C>; Claude cannot auto-invoke this skill</>,
238 description: [<>This skill uses <C>disable-model-invocation: true</C> so only you can trigger it; Claude never invokes it on its own.</>, <>The <C>!`...`</C> line runs a shell command and injects its output into the prompt. <C>$ARGUMENTS</C> substitutes whatever you typed after the skill name. Claude sees the skill directory path, so mentioning a bundled file like checklist.md lets Claude read it.</>],
239 example: `---
240description: Reviews code changes for security vulnerabilities, authentication gaps, and injection risks
241disable-model-invocation: true
242argument-hint: <branch-or-path>
243
244## Diff to review
245
246!\`git diff $ARGUMENTS\`
247
248Audit the changes above for:
249
2501. Injection vulnerabilities (SQL, XSS, command)
2512. Authentication and authorization gaps
2523. Hardcoded secrets or credentials
253
254Use checklist.md in this skill directory for the full review checklist.
255
256Report findings with severity ratings and remediation steps.`
257 }, {
258 id: 'skill-checklist',
259 label: 'checklist.md',
260 type: 'file',
261 icon: 'md',
262 color: '#D4A843',
263 badge: 'committed',
264 oneLiner: 'Supporting file bundled with the skill',
265 when: 'Claude reads it on demand while running the skill',
266 description: <>Skills can bundle any supporting files: reference docs, templates, scripts. The skill directory path is prepended to SKILL.md, so Claude can read bundled files by name. For scripts in bash injection commands, use the <C>{'${CLAUDE_SKILL_DIR}'}</C> placeholder.</>,
267 example: `# Security Review Checklist
268
269## Input Validation
270- [ ] All user input sanitized before DB queries
271- [ ] File upload MIME types validated
272- [ ] Path traversal prevented on file operations
273
274## Authentication
275- [ ] JWT tokens expire after 24 hours
276- [ ] API keys stored in environment variables
277- [ ] Passwords hashed with bcrypt or argon2`
278 }]
279 }]
280 }, {
281 id: 'commands',
282 label: 'commands/',
283 type: 'folder',
284 icon: 'folder',
285 color: '#788C5D',
286 oneLiner: <>Single-file prompts invoked with <C>/name</C></>,
287 note: commandsNote,
288 when: <>User types <C>/command-name</C></>,
289 description: <>A file at <C>commands/deploy.md</C> creates <C>/deploy</C> the same way a skill at <C>skills/deploy/SKILL.md</C> does, and both can be auto-invoked by Claude. Skills use a directory with SKILL.md, letting you bundle reference docs, templates, or scripts alongside the prompt.</>,
290 tips: [<>Use <C>$ARGUMENTS</C> in the file to accept parameters: <C>/fix-issue 123</C></>, 'If a skill and command share a name, the skill takes precedence', 'New commands should usually be skills instead; commands remain supported'],
291 docsLink: '/en/skills',
292 children: [{
293 id: 'cmd-example',
294 label: 'fix-issue.md',
295 type: 'file',
296 icon: 'md',
297 color: '#788C5D',
298 badge: 'committed',
299 oneLiner: <>Invoked as <C>/fix-issue <number></C></>,
300 note: commandsNote,
301 description: [<>An example command for fixing a GitHub issue. Type <C>/fix-issue 123</C> and the <C>!`...`</C> line runs <C>gh issue view 123</C> in your shell, injecting the output into the prompt before Claude sees it.</>, <><C>$ARGUMENTS</C> substitutes whatever you typed after the command name. For positional access, use <C>$0</C> <C>$1</C> and so on.</>],
302 example: `---
303argument-hint: <issue-number>
304
305!\`gh issue view $ARGUMENTS\`
306
307Investigate and fix the issue above.
308
3091. Trace the bug to its root cause
3102. Implement the fix
3113. Write or update tests
3124. Summarize what you changed and why`
313 }]
314 }, {
315 id: 'output-styles',
316 label: 'output-styles/',
317 type: 'folder',
318 icon: 'folder',
319 color: '#5AA7A7',
320 oneLiner: 'Project-scoped output styles, if your team shares any',
321 when: 'Applied at session start when selected via the outputStyle setting',
322 description: <>Output styles are usually personal, so most live in <C>~/.claude/output-styles/</C>. Put one here if your team shares a style, like a review mode everyone uses. See <A href="#ce-global-output-styles">the Global tab</A> for the full explanation and example.</>,
323 docsLink: '/en/output-styles',
324 children: []
325 }, {
326 id: 'agents',
327 label: 'agents/',
328 type: 'folder',
329 icon: 'folder',
330 color: '#C46686',
331 oneLiner: 'Specialized subagents with their own context window',
332 when: 'Runs in its own context window when you or Claude invoke it',
333 description: 'Each markdown file defines a subagent with its own system prompt, tool access, and optionally its own model. Subagents run in a fresh context window, keeping the main conversation clean. Useful for parallel work or isolated tasks.',
334 tips: ['Each agent gets a fresh context window, separate from your main session', <>Restrict tool access per agent with the <C>tools:</C> frontmatter field</>, 'Type @ and pick an agent from the autocomplete to delegate directly'],
335 docsLink: '/en/sub-agents',
336 children: [{
337 id: 'agent-reviewer',
338 label: 'code-reviewer.md',
339 type: 'file',
340 icon: 'md',
341 color: '#C46686',
342 badge: 'committed',
343 oneLiner: 'Subagent for isolated code review',
344 when: 'Claude spawns it for review tasks, or you @-mention it from the autocomplete',
345 description: <>An example subagent restricted to read-only tools. The <C>description</C> frontmatter tells Claude when to delegate to it automatically; <C>tools:</C> limits it to Read, Grep, and Glob so it can inspect code but never edit. The body becomes the subagent's system prompt.</>,
346 example: `---
347name: code-reviewer
348description: Reviews code for correctness, security, and maintainability
349tools: Read, Grep, Glob
350
351You are a senior code reviewer. Review for:
352
3531. Correctness: logic errors, edge cases, null handling
3542. Security: injection, auth bypass, data exposure
3553. Maintainability: naming, complexity, duplication
356
357Every finding must include a concrete fix.`
358 }]
359 }, {
360 id: 'agent-memory',
361 label: 'agent-memory/',
362 type: 'folder',
363 icon: 'folder',
364 color: '#C46686',
365 badge: 'committed',
366 autogen: true,
367 oneLiner: 'Subagent persistent memory, separate from your main session auto memory',
368 when: 'First 200 lines (capped at 25KB) of MEMORY.md loaded into the subagent system prompt when it runs',
369 description: <>Subagents with <C>memory: project</C> in their frontmatter get a dedicated memory directory here. This is distinct from your <A href="/en/memory#auto-memory">main session auto memory</A> at <C>~/.claude/projects/</C>: each subagent reads and writes its own MEMORY.md, not yours.</>,
370 tips: [<>Only created for subagents that set the <C>memory:</C> frontmatter field</>, <>This directory holds project-scoped subagent memory, meant to be shared with your team. To keep memory out of version control use <C>memory: local</C>, which writes to <C>.claude/agent-memory-local/</C> instead. For cross-project memory use <C>memory: user</C>, which writes to <C>~/.claude/agent-memory/</C></>, <>The main session auto memory is a different feature; see <C>~/.claude/projects/</C> in the Global tab</>],
371 docsLink: '/en/sub-agents#enable-persistent-memory',
372 children: [{
373 id: 'agent-memory-sub',
374 label: '<agent-name>/',
375 type: 'folder',
376 icon: 'folder',
377 color: '#C46686',
378 autogen: true,
379 children: [{
380 id: 'agent-memory-md',
381 label: 'MEMORY.md',
382 type: 'file',
383 icon: 'md',
384 color: '#C46686',
385 badge: 'committed',
386 autogen: true,
387 oneLiner: 'The subagent writes and maintains this file automatically',
388 when: 'Loaded into the subagent system prompt when the subagent starts',
389 description: <>Works the same as your <A href="/en/memory#auto-memory">main auto memory</A>: the subagent creates and updates this file itself. You do not write it. The subagent reads it at the start of each task and writes back what it learns.</>,
390 example: `# code-reviewer memory
391
392## Patterns seen
393- Project uses custom Result<T, E> type, not exceptions
394- Auth middleware expects Bearer token in Authorization header
395- Tests use factory functions in test/factories/
396
397## Recurring issues
398- Missing null checks on API responses (src/api/*)
399- Unhandled promise rejections in background jobs`
400 }]
401 }]
402 }]
403 }]
404 },
405 global: {
406 label: '~/',
407 children: [{
408 id: 'claude-json',
409 label: '.claude.json',
410 type: 'file',
411 icon: 'json',
412 color: 'var(--ce-text-3)',
413 badge: 'local',
414 oneLiner: 'App state and UI preferences',
415 when: <>Read at session start for your preferences and MCP servers. Claude Code writes back to it when you change settings in <C>/config</C> or approve trust prompts</>,
416 description: <>Holds state that does not belong in settings.json: theme, OAuth session, per-project trust decisions, your personal MCP servers, and UI toggles. Mostly managed through <C>/config</C> rather than editing directly.</>,
417 tips: [<>IDE toggles like <C>autoConnectIde</C> and <C>externalEditorContext</C> live here, not in settings.json</>, <>The <C>projects</C> key tracks per-project state like trust-dialog acceptance and last-session metrics. Permission rules you approve in-session go to <C>.claude/settings.local.json</C> instead</>, <>MCP servers here are yours only: user scope applies across all projects, local scope is per-project but not committed. Team-shared servers go in <C>.mcp.json</C> at the project root instead</>],
418 example: `{
419 "autoConnectIde": true,
420 "externalEditorContext": true,
421 "mcpServers": {
422 "my-tools": {
423 "command": "npx",
424 "args": ["-y", "@example/mcp-server"]
425 }
426 }
427}`,
428 docsLink: '/en/settings#global-config-settings'
429 }, {
430 id: 'global-dot-claude',
431 label: '.claude/',
432 type: 'folder',
433 icon: 'folder',
434 color: 'var(--ce-accent)',
435 oneLiner: 'Your personal configuration across all projects',
436 description: 'The global counterpart to your project .claude/ directory. Files here apply to every project you work in and are never committed to any repository.',
437 children: [{
438 id: 'global-claude-md',
439 label: 'CLAUDE.md',
440 type: 'file',
441 icon: 'md',
442 color: '#6A9BCC',
443 badge: 'local',
444 oneLiner: 'Personal preferences across every project',
445 when: 'Loaded at the start of every session, in every project',
446 description: 'Your global instruction file. Loaded alongside the project CLAUDE.md at session start, so both are in context together. When instructions conflict, project-level instructions take priority. Keep this to preferences that apply everywhere: response style, commit format, personal conventions.',
447 tips: ['Keep it short since it loads into context for every project, alongside that project\'s own CLAUDE.md', 'Good for response style, commit format, and personal conventions'],
448 example: `# Global preferences
449
450- Keep explanations concise
451- Use conventional commit format
452- Show the terminal command to verify changes
453- Prefer composition over inheritance`,
454 docsLink: '/en/memory'
455 }, {
456 id: 'global-settings',
457 label: 'settings.json',
458 type: 'file',
459 icon: 'json',
460 color: 'var(--ce-text-3)',
461 badge: 'local',
462 oneLiner: 'Default settings for all projects',
463 when: 'Your defaults. Project and local settings.json override any keys you also set there',
464 description: [<>Same keys as project <C>settings.json</C>: permissions, hooks, model, environment variables, and the rest. Put settings here that you want in every project, like permissions you always allow, a preferred model, or a notification hook that runs regardless of which project you're in.</>, <>Settings follow a precedence order: project <C>settings.json</C> overrides any matching keys you set here. This is different from CLAUDE.md, where global and project files are both loaded into context rather than merged key by key.</>],
465 example: `{
466 "permissions": {
467 "allow": [
468 "Bash(git log *)",
469 "Bash(git diff *)"
470 ]
471 }
472}`,
473 docsLink: '/en/settings'
474 }, {
475 id: 'keybindings',
476 label: 'keybindings.json',
477 type: 'file',
478 icon: 'json',
479 color: 'var(--ce-text-3)',
480 badge: 'local',
481 oneLiner: 'Custom keyboard shortcuts',
482 when: 'Read at session start and hot-reloaded when you edit the file',
483 description: <>Rebind keyboard shortcuts in the interactive CLI. Run <C>/keybindings</C> to create or open this file with a schema reference. Ctrl+C, Ctrl+D, Ctrl+M, and Caps Lock are reserved and cannot be rebound.</>,
484 exampleIntro: <>This example binds <C>Ctrl+E</C> to open your external editor and unbinds <C>Ctrl+U</C> by setting it to <C>null</C>. The <C>context</C> field scopes bindings to a specific part of the CLI, here the main chat input.</>,
485 example: `{
486 "$schema": "https://www.schemastore.org/claude-code-keybindings.json",
487 "$docs": "https://code.claude.com/docs/en/keybindings",
488 "bindings": [
489 {
490 "context": "Chat",
491 "bindings": {
492 "ctrl+e": "chat:externalEditor",
493 "ctrl+u": null
494 }
495 }
496 ]
497}`,
498 docsLink: '/en/keybindings'
499 }, {
500 id: 'themes',
501 label: 'themes/',
502 type: 'folder',
503 icon: 'folder',
504 color: '#5AA7A7',
505 oneLiner: 'Custom color themes',
506 when: <>Read at session start and hot-reloaded when files change. Listed in <C>/theme</C></>,
507 description: <>Each <C>.json</C> file defines a custom color theme: a built-in <C>base</C> preset plus an <C>overrides</C> map of color tokens. Create one interactively with <C>/theme</C> or write the JSON by hand. Selecting a custom theme stores <C>custom:<slug></C> as your theme preference.</>,
508 example: `{
509 "name": "Dracula",
510 "base": "dark",
511 "overrides": {
512 "claude": "#bd93f9",
513 "error": "#ff5555",
514 "success": "#50fa7b"
515 }
516}`,
517 docsLink: '/en/terminal-config#create-a-custom-theme',
518 children: []
519 }, {
520 id: 'global-projects',
521 label: 'projects/',
522 type: 'folder',
523 icon: 'folder',
524 color: '#E8A45C',
525 autogen: true,
526 oneLiner: "Auto memory: Claude's notes to itself, per project",
527 when: 'MEMORY.md loaded at session start; topic files read on demand',
528 description: 'Auto memory lets Claude accumulate knowledge across sessions without you writing anything. Claude saves notes as it works: build commands, debugging insights, architecture notes. Each project gets its own memory directory keyed by the repository path.',
529 tips: [<>On by default. Toggle with <C>/memory</C> or <C>autoMemoryEnabled</C> in settings</>, 'MEMORY.md is the index loaded each session. The first 200 lines, or 25KB, whichever comes first, are read', 'Topic files like debugging.md are read on demand, not at startup', 'These are plain markdown. Edit or delete them anytime'],
530 docsLink: '/en/memory#auto-memory',
531 children: [{
532 id: 'memory-dir',
533 label: '<project>/memory/',
534 type: 'folder',
535 icon: 'folder',
536 color: '#E8A45C',
537 autogen: true,
538 oneLiner: "Claude's accumulated knowledge for one project",
539 children: [{
540 id: 'memory-md',
541 label: 'MEMORY.md',
542 type: 'file',
543 icon: 'md',
544 color: '#E8A45C',
545 badge: 'local',
546 autogen: true,
547 oneLiner: 'Claude writes and maintains this file automatically',
548 when: 'First 200 lines (capped at 25KB) loaded at session start',
549 description: 'Claude creates and updates this file as it works; you do not write it yourself. It acts as an index that Claude reads at the start of every session, pointing to topic files for detail. You can edit or delete it, but Claude will keep updating it.',
550 example: `# Memory Index
551
552## Project
553- [build-and-test.md](build-and-test.md): npm run build (~45s), Vitest, dev server on 3001
554- [architecture.md](architecture.md): API client singleton, refresh-token auth
555
556## Reference
557- [debugging.md](debugging.md): auth token rotation and DB connection troubleshooting`,
558 docsLink: '/en/memory'
559 }, {
560 id: 'memory-topic',
561 label: 'debugging.md',
562 type: 'file',
563 icon: 'md',
564 color: '#E8A45C',
565 badge: 'local',
566 autogen: true,
567 oneLiner: 'Topic notes Claude writes when MEMORY.md gets long',
568 when: 'Claude reads this when a related task comes up',
569 description: 'An example of a topic file Claude creates when MEMORY.md grows too long. Claude picks the filename based on what it splits out: debugging.md, architecture.md, build-commands.md, or similar. You never create these yourself. Claude reads a topic file back only when the current task relates to it.',
570 example: `---
571name: Debugging patterns
572description: Auth token rotation and database connection troubleshooting for this project
573type: reference
574
575## Auth Token Issues
576- Refresh token rotation: old token invalidated immediately
577- If 401 after refresh: check clock skew between client and server
578
579## Database Connection Drops
580- Connection pool: max 10 in dev, 50 in prod
581- Always check \`docker compose ps\` first`
582 }]
583 }]
584 }, {
585 id: 'global-rules',
586 label: 'rules/',
587 type: 'folder',
588 icon: 'folder',
589 color: '#9B7BC4',
590 oneLiner: 'User-level rules that apply to every project',
591 when: <>Rules without <C>paths:</C> load at session start. Rules with <C>paths:</C> load when a matching file enters context</>,
592 description: 'Same as project .claude/rules/ but applies everywhere. Use this for conventions you want across all your work, like personal code style or commit message format.',
593 docsLink: '/en/memory#organize-rules-with-claude/rules/',
594 children: []
595 }, {
596 id: 'global-skills',
597 label: 'skills/',
598 type: 'folder',
599 icon: 'folder',
600 color: '#D4A843',
601 oneLiner: 'Personal skills available in every project',
602 when: <>Invoked with <C>/skill-name</C> in any project</>,
603 description: 'Skills you built for yourself that work everywhere. Same structure as project skills: each is a folder with SKILL.md, scoped to your user account instead of a single project.',
604 docsLink: '/en/skills',
605 children: []
606 }, {
607 id: 'global-commands',
608 label: 'commands/',
609 type: 'folder',
610 icon: 'folder',
611 color: '#788C5D',
612 oneLiner: 'Personal single-file commands available in every project',
613 note: commandsNote,
614 when: <>User types <C>/command-name</C> in any project</>,
615 description: 'Same as project commands/ but scoped to your user account. Each markdown file becomes a command available everywhere.',
616 docsLink: '/en/skills',
617 children: []
618 }, {
619 id: 'global-output-styles',
620 label: 'output-styles/',
621 type: 'folder',
622 icon: 'folder',
623 color: '#5AA7A7',
624 oneLiner: 'Custom system-prompt sections that adjust how Claude works',
625 when: 'Applied at session start when selected via the outputStyle setting',
626 description: [<>Each markdown file defines an output style: a section appended to the system prompt that, by default, also drops the built-in software-engineering task instructions. Use this to adapt Claude Code for uses beyond coding, or to add teaching or review modes.</>, <>Select a built-in or custom style with <C>/config</C> or the <C>outputStyle</C> key in settings. Styles here are available in every project; project-level styles with the same name take precedence.</>],
627 tips: ['Built-in styles Explanatory and Learning are included with Claude Code; custom styles go here', <>Set <C>keep-coding-instructions: true</C> in frontmatter to keep the default task instructions alongside your additions</>, 'Changes take effect on the next session since the system prompt is fixed at startup for caching'],
628 docsLink: '/en/output-styles',
629 children: [{
630 id: 'output-style-example',
631 label: 'teaching.md',
632 type: 'file',
633 icon: 'md',
634 color: '#5AA7A7',
635 badge: 'local',
636 oneLiner: 'Example style that adds explanations and leaves small changes for you',
637 when: <>Active when <C>outputStyle</C> in settings is set to <C>teaching</C></>,
638 description: <>This style appends instructions to the system prompt: Claude adds a "Why this approach" note after each task and leaves TODO(human) markers for changes under 10 lines instead of writing them itself. Select it by setting <C>outputStyle</C> to the filename without .md, or to the <C>name</C> field if you set one in frontmatter.</>,
639 example: `---
640description: Explains reasoning and asks you to implement small pieces
641keep-coding-instructions: true
642
643After completing each task, add a brief "Why this approach" note
644explaining the key design decision.
645
646When a change is under 10 lines, ask the user to implement it
647themselves by leaving a TODO(human) marker instead of writing it.`
648 }]
649 }, {
650 id: 'global-agents',
651 label: 'agents/',
652 type: 'folder',
653 icon: 'folder',
654 color: '#C46686',
655 oneLiner: 'Personal subagents available in every project',
656 when: 'Claude delegates or you @-mention in any project',
657 description: 'Subagents defined here are available across all your projects. Same format as project agents.',
658 docsLink: '/en/sub-agents',
659 children: []
660 }, {
661 id: 'global-agent-memory',
662 label: 'agent-memory/',
663 type: 'folder',
664 icon: 'folder',
665 color: '#C46686',
666 autogen: true,
667 oneLiner: <>Persistent memory for subagents with <C>memory: user</C></>,
668 when: 'Loaded into the subagent system prompt when the subagent starts',
669 description: <>Subagents with <C>memory: user</C> in their frontmatter store knowledge here that persists across all projects. For project-scoped subagent memory, see <C>.claude/agent-memory/</C> instead.</>,
670 docsLink: '/en/sub-agents#enable-persistent-memory',
671 children: []
672 }]
673 }]
674 }
675 }), []);
676 const BADGE_STYLES = useMemo(() => ({
677 committed: {
678 bg: 'rgba(85,138,66,0.08)',
679 color: 'var(--ce-badge-committed)',
680 border: 'rgba(85,138,66,0.15)',
681 label: 'committed'
682 },
683 gitignored: {
684 bg: 'rgba(217,119,87,0.06)',
685 color: 'var(--ce-badge-gitignored)',
686 border: 'rgba(217,119,87,0.15)',
687 label: 'gitignored'
688 },
689 local: {
690 bg: 'rgba(115,114,108,0.06)',
691 color: 'var(--ce-badge-local)',
692 border: 'rgba(115,114,108,0.12)',
693 label: 'local only'
694 },
695 autogen: {
696 bg: 'rgba(232,164,92,0.1)',
697 color: 'var(--ce-badge-autogen)',
698 border: 'rgba(232,164,92,0.2)',
699 label: 'Claude writes'
700 }
701 }), []);
702 const allNodes = useMemo(() => {
703 const flatten = (nodes, acc, path, parentId) => {
704 for (const node of nodes) {
705 const nextPath = [...path, node.label];
706 acc[node.id] = {
707 ...node,
708 path: nextPath,
709 parentId
710 };
711 if (node.children) flatten(node.children, acc, nextPath, node.id);
712 }
713 return acc;
714 };
715 const project = flatten(FILE_TREE.project.children, {}, [FILE_TREE.project.label]);
716 const global = flatten(FILE_TREE.global.children, {}, [FILE_TREE.global.label]);
717 for (const id in project) project[id].root = 'project';
718 for (const id in global) global[id].root = 'global';
719 return {
720 ...project,
721 ...global
722 };
723 }, [FILE_TREE]);
724 const allFolderIds = useMemo(() => Object.keys(allNodes).filter(id => allNodes[id].type === 'folder'), [allNodes]);
725 const DEFAULT_EXPANDED = ['dot-claude', 'rules', 'skills', 'skill-review', 'commands', 'agents', 'agent-memory', 'agent-memory-sub', 'global-dot-claude', 'global-output-styles', 'global-projects', 'memory-dir'];
726 const [mounted, setMounted] = useState(false);
727 const [activeRoot, setActiveRoot] = useState('project');
728 const [selectedId, setSelectedId] = useState('claude-md');
729 const [expandedFolders, setExpandedFolders] = useState(() => new Set(DEFAULT_EXPANDED));
730 const [forceMobile, setForceMobile] = useState(false);
731 const [copiedId, setCopiedId] = useState(null);
732 const [isFullscreen, setIsFullscreen] = useState(false);
733 const copyTimeoutRef = useRef(null);
734 const rootRef = useRef(null);
735 useEffect(() => {
736 setMounted(true);
737 const applyHash = scroll => {
738 const hash = window.location.hash.slice(1);
739 if (!hash.startsWith('ce-')) return;
740 const id = hash.slice(3);
741 const node = allNodes[id];
742 if (!node) return;
743 setActiveRoot(node.root);
744 setSelectedId(id);
745 setExpandedFolders(new Set(allFolderIds));
746 if (scroll && rootRef.current) rootRef.current.scrollIntoView({
747 behavior: 'smooth',
748 block: 'start'
749 });
750 };
751 applyHash(false);
752 const onHashChange = () => applyHash(true);
753 const onFsChange = () => setIsFullscreen(!!document.fullscreenElement);
754 window.addEventListener('hashchange', onHashChange);
755 document.addEventListener('fullscreenchange', onFsChange);
756 return () => {
757 if (copyTimeoutRef.current) clearTimeout(copyTimeoutRef.current);
758 window.removeEventListener('hashchange', onHashChange);
759 document.removeEventListener('fullscreenchange', onFsChange);
760 };
761 }, []);
762 useEffect(() => {
763 if (!mounted || !rootRef.current) return;
764 const hash = window.location.hash.slice(1);
765 if (hash.startsWith('ce-') && allNodes[hash.slice(3)]) {
766 rootRef.current.scrollIntoView({
767 behavior: 'smooth',
768 block: 'start'
769 });
770 }
771 }, [mounted]);
772 if (!mounted) return null;
773 const selected = allNodes[selectedId];
774 const tree = FILE_TREE[activeRoot];
775 const isCopied = copiedId === selected.id;
776 const toggleFolder = id => {
777 const next = new Set(expandedFolders);
778 next.has(id) ? next.delete(id) : next.add(id);
779 setExpandedFolders(next);
780 };
781 const switchRoot = root => {
782 if (root === activeRoot) return;
783 setActiveRoot(root);
784 const firstId = FILE_TREE[root].children[0].id;
785 setSelectedId(firstId);
786 try {
787 history.replaceState(null, '', '#ce-' + firstId);
788 } catch (e) {}
789 };
790 const toggleFullscreen = () => {
791 if (!rootRef.current) return;
792 if (document.fullscreenElement) document.exitFullscreen(); else rootRef.current.requestFullscreen().catch(() => {});
793 };
794 const selectNode = n => {
795 setSelectedId(n.id);
796 if (n.type === 'folder' && !expandedFolders.has(n.id)) toggleFolder(n.id);
797 try {
798 history.replaceState(null, '', '#ce-' + n.id);
799 } catch (e) {}
800 };
801 const iconBtn = {
802 width: 28,
803 flexShrink: 0,
804 borderRadius: '6px',
805 border: 'none',
806 cursor: 'pointer',
807 background: 'transparent',
808 color: 'var(--ce-text-4)',
809 display: 'flex',
810 alignItems: 'center',
811 justifyContent: 'center'
812 };
813 const visibleFolderIds = allFolderIds.filter(id => allNodes[id].root === activeRoot);
814 const allExpanded = visibleFolderIds.every(id => expandedFolders.has(id));
815 const toggleAllFolders = () => {
816 const next = new Set(expandedFolders);
817 visibleFolderIds.forEach(id => allExpanded ? next.delete(id) : next.add(id));
818 setExpandedFolders(next);
819 };
820 const onTreeKeyDown = e => {
821 if (!['ArrowDown', 'ArrowUp', 'ArrowRight', 'ArrowLeft'].includes(e.key)) return;
822 const visible = [];
823 const walk = nodes => {
824 for (const n of nodes) {
825 visible.push(n.id);
826 if (n.children && expandedFolders.has(n.id)) walk(n.children);
827 }
828 };
829 walk(tree.children);
830 const i = visible.indexOf(selectedId);
831 if (i === -1) return;
832 e.preventDefault();
833 if (e.key === 'ArrowDown' && i < visible.length - 1) selectNode(allNodes[visible[i + 1]]); else if (e.key === 'ArrowUp' && i > 0) selectNode(allNodes[visible[i - 1]]); else if (e.key === 'ArrowRight' && selected.type === 'folder') {
834 if (!expandedFolders.has(selectedId)) toggleFolder(selectedId); else if (selected.children && selected.children.length) selectNode(allNodes[selected.children[0].id]);
835 } else if (e.key === 'ArrowLeft') {
836 if (selected.type === 'folder' && expandedFolders.has(selectedId)) toggleFolder(selectedId); else if (selected.parentId) selectNode(allNodes[selected.parentId]);
837 }
838 };
839 const copyExample = (id, text) => {
840 const done = () => {
841 setCopiedId(id);
842 if (copyTimeoutRef.current) clearTimeout(copyTimeoutRef.current);
843 copyTimeoutRef.current = setTimeout(() => setCopiedId(null), 2000);
844 };
845 const fallback = () => {
846 const ta = document.createElement('textarea');
847 ta.value = text;
848 ta.style.position = 'fixed';
849 ta.style.opacity = '0';
850 document.body.appendChild(ta);
851 ta.select();
852 try {
853 if (document.execCommand('copy')) done();
854 } catch (e) {}
855 document.body.removeChild(ta);
856 };
857 if (navigator.clipboard) {
858 navigator.clipboard.writeText(text).then(done, fallback);
859 } else {
860 fallback();
861 }
862 };
863 const renderIcon = (icon, color, size) => {
864 const sz = size || 14;
865 if (icon === 'folder') {
866 return <svg width={sz} height={sz} viewBox="0 0 14 14" fill="none">
867 <path d="M1.5 3.5a1 1 0 0 1 1-1h2.6l1 1.2h5.4a1 1 0 0 1 1 1v5.8a1 1 0 0 1-1 1h-9a1 1 0 0 1-1-1V3.5z" fill={color} fillOpacity="0.15" stroke={color} strokeWidth="1" />
868 </svg>;
869 }
870 if (icon === 'json') {
871 return <svg width={sz} height={sz} viewBox="0 0 14 14" fill="none">
872 <rect x="2" y="1.5" width="10" height="11" rx="1.5" fill={color} fillOpacity="0.15" stroke={color} strokeWidth="1" />
873 <text x="7" y="9" fontSize="6" fontFamily="monospace" fill={color} textAnchor="middle" fontWeight="700">{'{}'}</text>
874 </svg>;
875 }
876 return <svg width={sz} height={sz} viewBox="0 0 14 14" fill="none">
877 <rect x="2" y="1.5" width="10" height="11" rx="1.5" fill={color} fillOpacity="0.15" stroke={color} strokeWidth="1" />
878 <line x1="4.5" y1="5" x2="9.5" y2="5" stroke={color} strokeWidth="1" />
879 <line x1="4.5" y1="7" x2="9.5" y2="7" stroke={color} strokeWidth="1" />
880 <line x1="4.5" y1="9" x2="8" y2="9" stroke={color} strokeWidth="1" />
881 </svg>;
882 };
883 const renderNode = (node, depth) => {
884 const isFolder = node.type === 'folder';
885 const isExpanded = expandedFolders.has(node.id);
886 const isSelected = selectedId === node.id;
887 return <div key={node.id}>
888 <button role="treeitem" tabIndex={-1} onClick={() => selectNode(node)} aria-selected={isSelected} aria-expanded={isFolder ? isExpanded : undefined} style={{
889 display: 'flex',
890 alignItems: 'center',
891 gap: '5px',
892 width: '100%',
893 padding: `4px 8px 4px ${8 + depth * 16}px`,
894 background: isSelected ? 'var(--ce-accent-bg)' : 'transparent',
895 borderTop: 'none',
896 borderRight: 'none',
897 borderBottom: 'none',
898 borderLeft: isSelected ? '2px solid var(--ce-accent)' : '2px solid transparent',
899 outline: 'none',
900 cursor: 'pointer',
901 textAlign: 'left',
902 fontFamily: 'var(--ce-mono)',
903 fontSize: '13.5px',
904 color: isSelected ? 'var(--ce-accent)' : 'var(--ce-text-2)',
905 fontWeight: isSelected ? 550 : 400,
906 transition: 'all 0.1s'
907 }}>
908 {isFolder ? <span onClick={e => {
909 e.stopPropagation();
910 toggleFolder(node.id);
911 }} style={{
912 fontSize: '14px',
913 color: 'var(--ce-text-4)',
914 width: '20px',
915 height: '20px',
916 display: 'inline-flex',
917 alignItems: 'center',
918 justifyContent: 'center',
919 cursor: 'pointer',
920 borderRadius: '4px',
921 marginLeft: '-6px',
922 flexShrink: 0
923 }} onMouseEnter={e => {
924 e.currentTarget.style.background = 'var(--ce-arrow-hover)';
925 e.currentTarget.style.color = 'var(--ce-text-2)';
926 }} onMouseLeave={e => {
927 e.currentTarget.style.background = 'transparent';
928 e.currentTarget.style.color = 'var(--ce-text-4)';
929 }}>{isExpanded ? '▾' : '▸'}</span> : <span style={{
930 width: '14px',
931 flexShrink: 0
932 }} />}
933 {renderIcon(node.icon, node.color)}
934 <span style={{
935 flex: 1,
936 overflow: 'hidden',
937 textOverflow: 'ellipsis',
938 whiteSpace: 'nowrap'
939 }}>{node.label}</span>
940 {node.badge && BADGE_STYLES[node.badge] && <span title={BADGE_STYLES[node.badge].label} style={{
941 width: 6,
942 height: 6,
943 borderRadius: '50%',
944 background: BADGE_STYLES[node.badge].color,
945 flexShrink: 0,
946 opacity: 0.7
947 }} />}
948 </button>
949 {isFolder && isExpanded && node.children && <div role="group">{node.children.map(child => renderNode(child, depth + 1))}</div>}
950 </div>;
951 };
952 return <>
953 <style>{`
954 .ce-root {
955 --ce-mono: var(--font-mono, ui-monospace, monospace);
956 --ce-accent: #D97757;
957 --ce-accent-bg: rgba(217,119,87,0.06);
958 --ce-accent-border: rgba(217,119,87,0.12);
959 --ce-bg: #fff;
960 --ce-surface: #FAFAF7;
961 --ce-surface-hover: #F0EEE6;
962 --ce-border: #E8E6DC;
963 --ce-border-subtle: #F0EEE6;
964 --ce-text: #141413;
965 --ce-text-2: #5E5D59;
966 --ce-text-3: #73726C;
967 --ce-text-4: #9C9A92;
968 --ce-text-5: #B8B6AE;
969 --ce-sep: #D1CFC5;
970 --ce-code-header: #F5F4ED;
971 --ce-code-bg: #1A1918;
972 --ce-arrow-hover: rgba(0,0,0,0.08);
973 --ce-badge-committed: #3d6b2e;
974 --ce-badge-gitignored: #b85c3a;
975 --ce-badge-local: #5e5d59;
976 --ce-badge-autogen: #b07520;
977 --ce-when-text: #4a7fb5;
978 }
979 .dark .ce-root {
980 --ce-bg: #1a1918;
981 --ce-surface: #232221;
982 --ce-surface-hover: #2e2d2b;
983 --ce-border: #3a3936;
984 --ce-border-subtle: #2e2d2b;
985 --ce-text: #e8e6dc;
986 --ce-text-2: #c4c2b8;
987 --ce-text-3: #9c9a92;
988 --ce-text-4: #73726c;
989 --ce-text-5: #5e5d59;
990 --ce-sep: #4a4946;
991 --ce-code-header: #2e2d2b;
992 --ce-code-bg: #0d0d0c;
993 --ce-arrow-hover: rgba(255,255,255,0.08);
994 --ce-badge-committed: #6fa85c;
995 --ce-badge-gitignored: #e08a60;
996 --ce-badge-local: #9c9a92;
997 --ce-badge-autogen: #e8a45c;
998 --ce-when-text: #8bb4e0;
999 }
1000 .ce-mobile-fallback { display: none; border: 1px solid rgba(0,0,0,0.1); background: rgba(0,0,0,0.03); }
1001 .dark .ce-mobile-fallback { border-color: rgba(255,255,255,0.15); background: rgba(255,255,255,0.04); }
1002 @media (max-width: 700px) {
1003 .ce-root:not(.ce-force) { display: none !important; }
1004 .ce-mobile-fallback { display: block; }
1005 }
1006 `}</style>
1007 {!forceMobile && <div className="ce-mobile-fallback" style={{
1008 padding: '14px 16px',
1009 borderRadius: '8px',
1010 fontSize: '14px'
1011 }}>
1012 The interactive explorer works best on a larger screen. See the <a href="#file-reference" style={{
1013 color: '#D97757'
1014 }}>file reference table</a> below, or <button onClick={() => setForceMobile(true)} style={{
1015 border: 'none',
1016 background: 'none',
1017 padding: 0,
1018 color: '#D97757',
1019 textDecoration: 'underline',
1020 cursor: 'pointer',
1021 font: 'inherit'
1022 }}>show the explorer anyway</button>.
1023 </div>}
1024 <div ref={rootRef} className={forceMobile ? 'ce-root ce-force' : 'ce-root'} style={{
1025 borderRadius: isFullscreen ? 0 : '12px',
1026 border: '1px solid var(--ce-border)',
1027 background: 'var(--ce-bg)',
1028 display: 'flex',
1029 alignItems: 'stretch',
1030 overflow: 'hidden',
1031 fontFamily: 'var(--font-sans, -apple-system, sans-serif)',
1032 ...isFullscreen && ({
1033 height: '100vh'
1034 })
1035 }}>
1036 {}
1037 <div style={{
1038 width: 'min(240px, 35%)',
1039 minWidth: '180px',
1040 flexShrink: 0,
1041 borderRight: '1px solid var(--ce-border-subtle)',
1042 background: 'var(--ce-surface)',
1043 display: 'flex',
1044 flexDirection: 'column'
1045 }}>
1046 <div style={{
1047 padding: '8px 8px 4px',
1048 borderBottom: '1px solid var(--ce-border-subtle)',
1049 display: 'flex',
1050 gap: '4px'
1051 }}>
1052 {['project', 'global'].map(root => <button key={root} onClick={() => switchRoot(root)} style={{
1053 flex: 1,
1054 padding: '6px 0',
1055 borderRadius: '6px',
1056 border: 'none',
1057 cursor: 'pointer',
1058 fontFamily: 'var(--ce-mono)',
1059 fontSize: '11.5px',
1060 background: activeRoot === root ? 'var(--ce-accent-bg)' : 'transparent',
1061 color: activeRoot === root ? 'var(--ce-accent)' : 'var(--ce-text-4)',
1062 fontWeight: activeRoot === root ? 600 : 430
1063 }}>
1064 {root === 'project' ? 'Project' : 'Global (~/)'}
1065 </button>)}
1066 <button onClick={toggleAllFolders} title={allExpanded ? 'Collapse all' : 'Expand all'} style={{
1067 ...iconBtn,
1068 fontSize: 11
1069 }}>
1070 {allExpanded ? '⊟' : '⊞'}
1071 </button>
1072 <button onClick={toggleFullscreen} title={isFullscreen ? 'Exit fullscreen' : 'Fullscreen'} style={{
1073 ...iconBtn,
1074 fontSize: 13
1075 }}>
1076 {isFullscreen ? '⤡' : '⛶'}
1077 </button>
1078 </div>
1079 <div role="tree" aria-label="Configuration files" tabIndex={0} onKeyDown={onTreeKeyDown} style={{
1080 padding: '6px 0',
1081 overflowY: 'auto',
1082 flex: 1,
1083 outline: 'none'
1084 }}>
1085 {tree.children.map(node => renderNode(node, 0))}
1086 </div>
1087 </div>
1088
1089 {}
1090 <div style={{
1091 flex: 1,
1092 minWidth: 0,
1093 padding: '20px 24px',
1094 minHeight: '400px',
1095 overflowY: 'auto'
1096 }}>
1097 <span aria-live="polite" style={{
1098 position: 'absolute',
1099 width: 1,
1100 height: 1,
1101 overflow: 'hidden',
1102 clip: 'rect(0 0 0 0)'
1103 }}>{selected.label} selected</span>
1104 {}
1105 <div style={{
1106 fontFamily: 'var(--ce-mono)',
1107 fontSize: '11px',
1108 color: 'var(--ce-text-4)',
1109 marginBottom: '10px',
1110 cursor: 'default'
1111 }}>
1112 {selected.path.map((seg, i) => <span key={i}>
1113 <span style={{
1114 color: i === selected.path.length - 1 ? 'var(--ce-accent)' : 'var(--ce-text-4)'
1115 }}>{seg.replace(/\/$/, '')}</span>
1116 {i < selected.path.length - 1 && <span style={{
1117 color: 'var(--ce-sep)'
1118 }}> / </span>}
1119 </span>)}
1120 </div>
1121
1122 {}
1123 <div style={{
1124 display: 'flex',
1125 alignItems: 'flex-start',
1126 gap: '10px',
1127 marginBottom: '10px'
1128 }}>
1129 <span style={{
1130 flexShrink: 0,
1131 display: 'flex'
1132 }}>{renderIcon(selected.icon, selected.color, 24)}</span>
1133 <div style={{
1134 flex: 1,
1135 minWidth: 0
1136 }}>
1137 <div style={{
1138 fontSize: '22px',
1139 fontWeight: 600,
1140 color: 'var(--ce-text)',
1141 letterSpacing: '-0.3px',
1142 lineHeight: '26px'
1143 }}>{selected.label}</div>
1144 {selected.oneLiner && <div style={{
1145 fontSize: '15px',
1146 color: 'var(--ce-text-3)',
1147 marginTop: '3px'
1148 }}>{selected.oneLiner}</div>}
1149 </div>
1150 <div style={{
1151 display: 'flex',
1152 gap: '4px',
1153 flexShrink: 0
1154 }}>
1155 {[selected.autogen && 'autogen', selected.badge].filter(Boolean).map(k => {
1156 const s = BADGE_STYLES[k];
1157 if (!s) return null;
1158 return <span key={k} style={{
1159 fontFamily: 'var(--ce-mono)',
1160 fontSize: '10px',
1161 fontWeight: 600,
1162 textTransform: 'uppercase',
1163 letterSpacing: '0.3px',
1164 padding: '2px 6px',
1165 borderRadius: '4px',
1166 background: s.bg,
1167 color: s.color,
1168 border: `0.5px solid ${s.border}`
1169 }}>{s.label}</span>;
1170 })}
1171 </div>
1172 </div>
1173
1174 {}
1175 {selected.note && <div style={{
1176 padding: '10px 12px',
1177 borderRadius: '8px',
1178 marginBottom: '14px',
1179 background: 'rgba(217,119,87,0.06)',
1180 border: '1px solid rgba(217,119,87,0.2)',
1181 borderLeft: '3px solid var(--ce-accent)',
1182 fontSize: '15px',
1183 color: 'var(--ce-text-2)',
1184 lineHeight: 1.6
1185 }}>
1186 {selected.note}
1187 </div>}
1188
1189 {}
1190 {selected.when && <div style={{
1191 padding: '8px 12px',
1192 borderRadius: '6px',
1193 background: 'rgba(106,155,204,0.06)',
1194 border: '0.5px solid rgba(106,155,204,0.12)',
1195 fontSize: '15px',
1196 color: 'var(--ce-when-text)',
1197 marginBottom: '16px'
1198 }}>
1199 <div style={{
1200 fontSize: '10px',
1201 fontWeight: 700,
1202 textTransform: 'uppercase',
1203 letterSpacing: '0.4px',
1204 opacity: 0.65,
1205 marginBottom: '3px'
1206 }}>When it loads</div>
1207 <div style={{
1208 fontWeight: 500
1209 }}>{selected.when}</div>
1210 </div>}
1211
1212 {}
1213 {selected.description && <div style={{
1214 fontSize: '16px',
1215 color: 'var(--ce-text-2)',
1216 lineHeight: 1.65,
1217 marginBottom: '16px'
1218 }}>
1219 {Array.isArray(selected.description) ? selected.description.map((para, i) => <div key={i} style={{
1220 marginBottom: i < selected.description.length - 1 ? '12px' : 0
1221 }}>{para}</div>) : selected.description}
1222 </div>}
1223
1224 {}
1225 {selected.contains && selected.contains.length > 0 && <div style={{
1226 marginBottom: '16px'
1227 }}>
1228 <div style={{
1229 fontSize: '11px',
1230 fontWeight: 700,
1231 color: 'var(--ce-text-4)',
1232 textTransform: 'uppercase',
1233 letterSpacing: '0.4px',
1234 marginBottom: '8px'
1235 }}>Common keys</div>
1236 {selected.contains.map((item, i) => <div key={i} style={{
1237 display: 'flex',
1238 gap: '7px',
1239 fontSize: '15px',
1240 color: 'var(--ce-text-2)',
1241 lineHeight: 1.5,
1242 marginBottom: '5px'
1243 }}>
1244 <span style={{
1245 fontSize: '7px',
1246 color: 'var(--ce-text-4)',
1247 marginTop: '6px'
1248 }}>●</span>
1249 <span>{item}</span>
1250 </div>)}
1251 </div>}
1252
1253 {}
1254 {selected.tips && selected.tips.length > 0 && <div style={{
1255 padding: '12px 14px',
1256 borderRadius: '8px',
1257 background: 'var(--ce-surface)',
1258 border: '1px solid var(--ce-border-subtle)',
1259 marginBottom: '16px'
1260 }}>
1261 <div style={{
1262 fontSize: '11px',
1263 fontWeight: 700,
1264 color: 'var(--ce-accent)',
1265 textTransform: 'uppercase',
1266 letterSpacing: '0.4px',
1267 marginBottom: '6px'
1268 }}>Tips</div>
1269 {selected.tips.map((tip, i) => <div key={i} style={{
1270 display: 'flex',
1271 gap: '7px',
1272 fontSize: '14.5px',
1273 color: 'var(--ce-text-2)',
1274 marginBottom: i < selected.tips.length - 1 ? '5px' : 0
1275 }}>
1276 <span style={{
1277 fontSize: '7px',
1278 color: 'var(--ce-accent)',
1279 marginTop: '6px'
1280 }}>●</span>
1281 <span>{tip}</span>
1282 </div>)}
1283 </div>}
1284
1285 {}
1286 {selected.example && <div style={{
1287 marginBottom: '16px'
1288 }}>
1289 {selected.exampleIntro && <div style={{
1290 fontSize: '15px',
1291 color: 'var(--ce-text-2)',
1292 lineHeight: 1.6,
1293 marginBottom: '10px'
1294 }}>
1295 {selected.exampleIntro}
1296 </div>}
1297 <div style={{
1298 display: 'flex',
1299 justifyContent: 'space-between',
1300 alignItems: 'center',
1301 padding: '6px 10px',
1302 background: 'var(--ce-code-header)',
1303 border: '1px solid var(--ce-border)',
1304 borderRadius: '8px 8px 0 0'
1305 }}>
1306 <span style={{
1307 fontFamily: 'var(--ce-mono)',
1308 fontSize: '11px',
1309 fontWeight: 600,
1310 color: 'var(--ce-text-3)'
1311 }}>{selected.label}</span>
1312 <button onClick={() => copyExample(selected.id, selected.example)} style={{
1313 padding: '3px 8px',
1314 borderRadius: '4px',
1315 fontSize: '11px',
1316 fontWeight: 600,
1317 cursor: 'pointer',
1318 transition: 'all 0.15s',
1319 background: isCopied ? 'rgba(85,138,66,0.08)' : 'var(--ce-code-header)',
1320 border: isCopied ? '0.5px solid rgba(85,138,66,0.2)' : '0.5px solid var(--ce-border)',
1321 color: isCopied ? '#558A42' : 'var(--ce-text-3)'
1322 }}>
1323 {isCopied ? '✓ Copied' : 'Copy'}
1324 </button>
1325 </div>
1326 <pre style={{
1327 margin: 0,
1328 padding: '12px 14px',
1329 background: 'var(--ce-code-bg)',
1330 color: '#E8E6DC',
1331 fontFamily: 'var(--ce-mono)',
1332 fontSize: '13px',
1333 lineHeight: 1.65,
1334 borderRadius: '0 0 8px 8px',
1335 overflowX: 'auto',
1336 whiteSpace: 'pre'
1337 }}>{selected.example}</pre>
1338 </div>}
1339
1340 {}
1341 {selected.docsLink && <a href={selected.docsLink} style={{
1342 display: 'inline-flex',
1343 padding: '5px 12px',
1344 borderRadius: '6px',
1345 background: 'var(--ce-accent-bg)',
1346 border: '1px solid var(--ce-accent-border)',
1347 color: 'var(--ce-accent)',
1348 fontSize: '12px',
1349 fontWeight: 600,
1350 textDecoration: 'none'
1351 }}>Full docs →</a>}
1352
1353 {}
1354 {selected.children && selected.children.length > 0 && <div style={{
1355 marginTop: '20px'
1356 }}>
1357 <div style={{
1358 fontSize: '11px',
1359 fontWeight: 700,
1360 color: 'var(--ce-text-4)',
1361 textTransform: 'uppercase',
1362 letterSpacing: '0.4px',
1363 marginBottom: '8px'
1364 }}>Contents</div>
1365 <div style={{
1366 display: 'flex',
1367 flexDirection: 'column',
1368 gap: '4px'
1369 }}>
1370 {selected.children.map(child => <button key={child.id} onClick={() => selectNode(child)} style={{
1371 display: 'flex',
1372 alignItems: 'center',
1373 gap: '8px',
1374 padding: '6px 8px',
1375 width: '100%',
1376 background: 'var(--ce-surface)',
1377 borderRadius: '6px',
1378 border: 'none',
1379 cursor: 'pointer',
1380 textAlign: 'left',
1381 transition: 'background 0.1s'
1382 }} onMouseEnter={e => e.currentTarget.style.background = 'var(--ce-surface-hover)'} onMouseLeave={e => e.currentTarget.style.background = 'var(--ce-surface)'}>
1383 {renderIcon(child.icon, child.color, 13)}
1384 <span style={{
1385 fontFamily: 'var(--ce-mono)',
1386 fontSize: '12px',
1387 color: 'var(--ce-text-2)'
1388 }}>{child.label}</span>
1389 {child.oneLiner && <span style={{
1390 fontSize: '11px',
1391 color: 'var(--ce-text-4)',
1392 overflow: 'hidden',
1393 textOverflow: 'ellipsis',
1394 whiteSpace: 'nowrap'
1395 }}>{child.oneLiner}</span>}
1396 </button>)}
1397 </div>
1398 </div>}
1399 </div>
1400 </div>
1401 </>;
1402};
1403 8
1404Claude Code 從您的專案目錄和主目錄中的 `~/.claude` 讀取指令、設定、skills、subagents 和記憶。將專案檔案提交到 git 以與您的團隊共享；`~/.claude` 中的檔案是個人設定，適用於您的所有專案。9Claude Code 從您的專案目錄和主目錄中的 `~/.claude` 讀取指令、設定、skills、subagents 和記憶。將專案檔案提交到 git 以與您的團隊共享；`~/.claude` 中的檔案是個人設定，適用於您的所有專案。
1405 10
1414 12
1415大多數使用者只編輯 `CLAUDE.md` 和 `settings.json`。目錄的其餘部分是可選的：根據需要新增 skills、rules 或 subagents。13大多數使用者只編輯 `CLAUDE.md` 和 `settings.json`。目錄的其餘部分是可選的：根據需要新增 skills、rules 或 subagents。
1416 14
1417## 探索目錄15<h2 id="explore-the-directory">
16 探索目錄
17</h2>
1418 18
1419點擊樹中的檔案以查看每個檔案的功能、何時載入以及範例。19點擊樹中的檔案以查看每個檔案的功能、何時載入以及範例。
1420 20
1421<ClaudeExplorer />21<h2 id="what-s-not-shown">
1422 22 未顯示的內容
1423## 未顯示的內容23</h2>
1424 24
1425探索器涵蓋您編寫和編輯的檔案。一些相關檔案位於其他位置：25探索器涵蓋您編寫和編輯的檔案。一些相關檔案位於其他位置：
1426 26
1432 32
1433`~/.claude` 還保存 Claude Code 在您工作時寫入的資料：文字記錄、提示歷史記錄、檔案快照、快取和日誌。請參閱下方的[應用程式資料](#application-data)。33`~/.claude` 還保存 Claude Code 在您工作時寫入的資料：文字記錄、提示歷史記錄、檔案快照、快取和日誌。請參閱下方的[應用程式資料](#application-data)。
1434 34
1435## 選擇正確的檔案35<h2 id="choose-the-right-file">
36 選擇正確的檔案
37</h2>
1436 38
1437不同類型的自訂設定位於不同的檔案中。使用此表格找到變更應該位於何處。39不同類型的自訂設定位於不同的檔案中。使用此表格找到變更應該位於何處。
1438 40
1445| 將個人覆蓋保留在 git 之外 | `settings.local.json` | 僅專案 | [Settings scopes](/zh-TW/settings#settings-files) |47| 將個人覆蓋保留在 git 之外 | `settings.local.json` | 僅專案 | [Settings scopes](/zh-TW/settings#settings-files) |
1446| 新增您使用 `/name` 叫用的提示或功能 | `skills/<name>/SKILL.md` | 專案或全域 | [Skills](/zh-TW/skills) |48| 新增您使用 `/name` 叫用的提示或功能 | `skills/<name>/SKILL.md` | 專案或全域 | [Skills](/zh-TW/skills) |
1447| 定義具有自己工具的專門 subagent | `agents/*.md` | 專案或全域 | [Subagents](/zh-TW/sub-agents) |49| 定義具有自己工具的專門 subagent | `agents/*.md` | 專案或全域 | [Subagents](/zh-TW/sub-agents) |
50| 透過指令碼協調許多 subagent | `workflows/*.js` | 專案或全域 | [Dynamic workflows](/zh-TW/workflows) |
1448| 透過 MCP 連接外部工具 | `.mcp.json` | 僅專案 | [MCP](/zh-TW/mcp) |51| 透過 MCP 連接外部工具 | `.mcp.json` | 僅專案 | [MCP](/zh-TW/mcp) |
1449| 變更 Claude 格式化回應的方式 | `output-styles/*.md` | 專案或全域 | [Output styles](/zh-TW/output-styles) |52| 變更 Claude 格式化回應的方式 | `output-styles/*.md` | 專案或全域 | [Output styles](/zh-TW/output-styles) |
1450 53
1451## 檔案參考54<h2 id="file-reference">
55 檔案參考
56</h2>
1452 57
1453此表列出探索器涵蓋的每個檔案。專案範圍的檔案位於您的儲存庫中的 `.claude/` 下（或 `CLAUDE.md`、`.mcp.json` 和 `.worktreeinclude` 的根目錄）。全域範圍的檔案位於 `~/.claude/` 中，適用於所有專案。58此表列出探索器涵蓋的每個檔案。專案範圍的檔案位於您的儲存庫中的 `.claude/` 下（或 `CLAUDE.md`、`.mcp.json` 和 `.worktreeinclude` 的根目錄）。全域範圍的檔案位於 `~/.claude/` 中，適用於所有專案。
1454 59
1465點擊檔案名稱以在上方的探索器中開啟該節點。70點擊檔案名稱以在上方的探索器中開啟該節點。
1466 71
1467| 檔案 | 範圍 | 提交 | 功能 | 參考 |72| 檔案 | 範圍 | 提交 | 功能 | 參考 |
1468| --------------------------------------------------- | ----- | -- | ----------------------------- | ------------------------------------------------------------------ |73| --------------------------------------------------- | ----- | -- | ----------------------------------------------------------- | ------------------------------------------------------------------ |
1469| [`CLAUDE.md`](#ce-claude-md) | 專案和全域 | ✓ | 每個工作階段載入的指令 | [Memory](/zh-TW/memory) |74| [`CLAUDE.md`](#ce-claude-md) | 專案和全域 | ✓ | 每個工作階段載入的指令 | [Memory](/zh-TW/memory) |
1470| [`rules/*.md`](#ce-rules) | 專案和全域 | ✓ | 主題範圍的指令，可選擇路徑限制 | [Rules](/zh-TW/memory#organize-rules-with-claude/rules/) |75| [`rules/*.md`](#ce-rules) | 專案和全域 | ✓ | 主題範圍的指令，可選擇路徑限制 | [Rules](/zh-TW/memory#organize-rules-with-claude/rules/) |
1471| [`settings.json`](#ce-settings-json) | 專案和全域 | ✓ | 權限、hooks、環境變數、模型預設值 | [Settings](/zh-TW/settings) |76| [`settings.json`](#ce-settings-json) | 專案和全域 | ✓ | 權限、hooks、環境變數、模型預設值 | [Settings](/zh-TW/settings) |
1476| [`commands/*.md`](#ce-commands) | 專案和全域 | ✓ | 單檔案提示；與 skills 相同的機制 | [Skills](/zh-TW/skills) |81| [`commands/*.md`](#ce-commands) | 專案和全域 | ✓ | 單檔案提示；與 skills 相同的機制 | [Skills](/zh-TW/skills) |
1477| [`output-styles/*.md`](#ce-output-styles) | 專案和全域 | ✓ | 自訂系統提示部分 | [Output styles](/zh-TW/output-styles) |82| [`output-styles/*.md`](#ce-output-styles) | 專案和全域 | ✓ | 自訂系統提示部分 | [Output styles](/zh-TW/output-styles) |
1478| [`agents/*.md`](#ce-agents) | 專案和全域 | ✓ | Subagent 定義及其自己的提示和工具 | [Subagents](/zh-TW/sub-agents) |83| [`agents/*.md`](#ce-agents) | 專案和全域 | ✓ | Subagent 定義及其自己的提示和工具 | [Subagents](/zh-TW/sub-agents) |
84| [`workflows/*.js`](#ce-workflows) | 專案和全域 | ✓ | Claude 撰寫並從 `/workflows` 儲存的動態工作流程指令碼；每個檔案都會變成 `/<name>` 命令 | [Dynamic workflows](/zh-TW/workflows) |
1479| [`agent-memory/<name>/`](#ce-agent-memory) | 專案和全域 | ✓ | Subagents 的持久記憶 | [Persistent memory](/zh-TW/sub-agents#enable-persistent-memory) |85| [`agent-memory/<name>/`](#ce-agent-memory) | 專案和全域 | ✓ | Subagents 的持久記憶 | [Persistent memory](/zh-TW/sub-agents#enable-persistent-memory) |
1480| [`~/.claude.json`](#ce-claude-json) | 僅全域 | | 應用程式狀態、OAuth、UI 切換、個人 MCP 伺服器 | [Global config](/zh-TW/settings#global-config-settings) |86| [`~/.claude.json`](#ce-claude-json) | 僅全域 | | 應用程式狀態、OAuth、UI 切換、個人 MCP 伺服器 | [Global config](/zh-TW/settings#global-config-settings) |
1481| [`projects/<project>/memory/`](#ce-global-projects) | 僅全域 | | 自動記憶：Claude 在工作階段間對自己的筆記 | [Auto memory](/zh-TW/memory#auto-memory) |87| [`projects/<project>/memory/`](#ce-global-projects) | 僅全域 | | 自動記憶：Claude 在工作階段間對自己的筆記 | [Auto memory](/zh-TW/memory#auto-memory) |
1482| [`keybindings.json`](#ce-keybindings) | 僅全域 | | 自訂快捷鍵 | [Keybindings](/zh-TW/keybindings) |88| [`keybindings.json`](#ce-keybindings) | 僅全域 | | 自訂快捷鍵 | [Keybindings](/zh-TW/keybindings) |
1483| [`themes/*.json`](#ce-themes) | 僅全域 | | 自訂色彩主題 | [Custom themes](/zh-TW/terminal-config#create-a-custom-theme) |89| [`themes/*.json`](#ce-themes) | 僅全域 | | 自訂色彩主題 | [Custom themes](/zh-TW/terminal-config#create-a-custom-theme) |
1484 90
1485## 檢查已載入的內容91<h2 id="troubleshoot-configuration">
1486 92 疑難排解設定
1487探索器顯示可以存在的檔案。若要查看在您目前工作階段中實際載入的內容，請使用這些命令：93</h2>
1488
1489| 命令 | 顯示 |
1490| -------------- | ------------------------------------- |
1491| `/context` | 按類別的權杖使用情況：系統提示、記憶檔案、skills、MCP 工具和訊息 |
1492| `/memory` | 載入了哪些 CLAUDE.md 和 rules 檔案，加上自動記憶項目 |
1493| `/agents` | 已設定的 subagents 及其設定 |
1494| `/hooks` | 作用中的 hook 設定 |
1495| `/mcp` | 已連接的 MCP 伺服器及其狀態 |
1496| `/skills` | 來自專案、使用者和 plugin 來源的可用 skills |
1497| `/permissions` | 目前的允許和拒絕規則 |
1498| `/doctor` | 安裝和設定診斷 |
1499 94
1500首先執行 `/context` 以取得概觀，然後執行特定命令以調查您想要的區域。95如果設定、hook 或檔案未生效，請參閱[偵錯您的設定](/zh-TW/debug-your-config)以取得檢查命令和症狀優先查詢表。
1501 96
1502## 應用程式資料97<h2 id="application-data">
98 應用程式資料
99</h2>
1503 100
1504除了您編寫的設定外，`~/.claude` 還保存 Claude Code 在工作階段期間寫入的資料。這些檔案是純文字。任何通過工具的內容都會在磁碟上的文字記錄中結束：檔案內容、命令輸出、貼上的文字。101除了您編寫的設定外，`~/.claude` 還保存 Claude Code 在工作階段期間寫入的資料。這些檔案是純文字。任何通過工具的內容都會在磁碟上的文字記錄中結束：檔案內容、命令輸出、貼上的文字。
1505 102
1506### 自動清理103<h3 id="cleaned-up-automatically">
104 自動清理
105</h3>
1507 106
1508下列路徑中的檔案在啟動時被刪除，一旦它們的年齡超過 [`cleanupPeriodDays`](/zh-TW/settings#available-settings)。預設值為 30 天。107下列路徑中的檔案在啟動時被刪除，一旦它們的年齡超過 [`cleanupPeriodDays`](/zh-TW/settings#available-settings)。預設值為 30 天。
1509 108
1521| `shell-snapshots/` | Bash tool 使用的擷取 shell 環境。在正常退出時移除。掃描會清除任何在當機後遺留的檔案。 |120| `shell-snapshots/` | Bash tool 使用的擷取 shell 環境。在正常退出時移除。掃描會清除任何在當機後遺留的檔案。 |
1522| `backups/` | 在設定遷移前取得的 `~/.claude.json` 的時間戳記副本 |121| `backups/` | 在設定遷移前取得的 `~/.claude.json` 的時間戳記副本 |
1523| `feedback-bundles/` | 由 `/feedback` 在第三方提供者上寫入的已編輯文字記錄存檔，用於傳送到您的 Anthropic 帳戶團隊 |122| `feedback-bundles/` | 由 `/feedback` 在第三方提供者上寫入的已編輯文字記錄存檔，用於傳送到您的 Anthropic 帳戶團隊 |
123| `todos/`、`statsig/`、`logs/` | 舊版本的舊版目錄。不再寫入。掃描會移除其內容，然後移除空目錄。 |
1524 124
1525### 保留直到您刪除它們125<h3 id="kept-until-you-delete-them">
126 保留直到您刪除它們
127</h3>
1526 128
1527以下路徑不受自動清理覆蓋，並無限期保留。129以下路徑不受自動清理覆蓋，並無限期保留。
1528 130
1531| `history.jsonl` | 您輸入的每個提示，帶有時間戳記和專案路徑。用於向上箭頭回憶。 |133| `history.jsonl` | 您輸入的每個提示，帶有時間戳記和專案路徑。用於向上箭頭回憶。 |
1532| `stats-cache.json` | 由 `/usage` 顯示的彙總權杖和成本計數 |134| `stats-cache.json` | 由 `/usage` 顯示的彙總權杖和成本計數 |
1533| `remote-settings.json` | 您組織的[伺服器管理設定](/zh-TW/server-managed-settings)的快取副本。僅在您的組織已設定時出現。在每次啟動時重新整理。 |135| `remote-settings.json` | 您組織的[伺服器管理設定](/zh-TW/server-managed-settings)的快取副本。僅在您的組織已設定時出現。在每次啟動時重新整理。 |
1534| `todos/` | 舊版每個工作階段的任務清單。不再由目前版本寫入；可安全刪除。 |
1535 136
1536其他小型快取和鎖定檔案會根據您使用的功能而出現，可安全刪除。137其他小型快取和鎖定檔案會根據您使用的功能而出現，可安全刪除。
1537 138
1538### 純文字儲存139<h3 id="plaintext-storage">
140 純文字儲存
141</h3>
1539 142
1540文字記錄和歷史記錄在靜止時未加密。作業系統檔案權限是唯一的保護。如果工具讀取 `.env` 檔案或命令列印認證，該值會寫入 `projects/<project>/<session>.jsonl`。若要減少暴露：143文字記錄和歷史記錄在靜止時未加密。作業系統檔案權限是唯一的保護。如果工具讀取 `.env` 檔案或命令列印認證，該值會寫入 `projects/<project>/<session>.jsonl`。若要減少暴露：
1541 144
1543* 設定 [`CLAUDE_CODE_SKIP_PROMPT_HISTORY`](/zh-TW/env-vars) 環境變數以跳過在任何模式中寫入文字記錄和提示歷史記錄。在非互動模式中，您可以改為在 `-p` 旁邊傳遞 `--no-session-persistence`，或在 Agent SDK 中設定 `persistSession: false`。146* 設定 [`CLAUDE_CODE_SKIP_PROMPT_HISTORY`](/zh-TW/env-vars) 環境變數以跳過在任何模式中寫入文字記錄和提示歷史記錄。在非互動模式中，您可以改為在 `-p` 旁邊傳遞 `--no-session-persistence`，或在 Agent SDK 中設定 `persistSession: false`。
1544* 使用[權限規則](/zh-TW/permissions)拒絕讀取認證檔案147* 使用[權限規則](/zh-TW/permissions)拒絕讀取認證檔案
1545 148
1546### 清除本機資料149<h3 id="clear-local-data">
150 清除本機資料
151</h3>
1547 152
1548執行 `claude project purge` 以刪除 Claude Code 為一個專案保存的狀態：153執行 `claude project purge` 以刪除 Claude Code 為一個專案保存的狀態。該命令需要 Claude Code v2.1.124 或更新版本。它會刪除：
1549 154
1550* `projects/` 下的文字記錄和自動記憶155* `projects/` 下的文字記錄和自動記憶
1551* 每個工作階段的 `tasks/`、`debug/` 和 `file-history/` 項目156* 每個工作階段的 `tasks/`、`debug/` 和 `file-history/` 項目
1588| `~/.claude/stats-cache.json` | 由 `/usage` 顯示的歷史總計 |193| `~/.claude/stats-cache.json` | 由 `/usage` 顯示的歷史總計 |
1589| `~/.claude/remote-settings.json` | 無。在下次啟動時重新擷取。 |194| `~/.claude/remote-settings.json` | 無。在下次啟動時重新擷取。 |
1590| `~/.claude/debug/`、`~/.claude/plans/`、`~/.claude/paste-cache/`、`~/.claude/image-cache/`、`~/.claude/session-env/`、`~/.claude/tasks/`、`~/.claude/shell-snapshots/`、`~/.claude/backups/` | 沒有面向使用者的內容 |195| `~/.claude/debug/`、`~/.claude/plans/`、`~/.claude/paste-cache/`、`~/.claude/image-cache/`、`~/.claude/session-env/`、`~/.claude/tasks/`、`~/.claude/shell-snapshots/`、`~/.claude/backups/` | 沒有面向使用者的內容 |
1591| `~/.claude/todos/` | 無。舊版目錄不由目前版本寫入。 |196| `~/.claude/todos/`、`~/.claude/statsig/`、`~/.claude/logs/` | 無。舊版目錄不由目前版本寫入。 |
1592 197
1593不要刪除 `~/.claude.json`、`~/.claude/settings.json` 或 `~/.claude/plugins/`：這些保存您的驗證、偏好設定和已安裝的 plugins。198不要刪除 `~/.claude.json`、`~/.claude/settings.json` 或 `~/.claude/plugins/`：這些保存您的驗證、偏好設定和已安裝的 plugins。
1594 199
1595## 相關資源200<h2 id="related-resources">
201 相關資源
202</h2>
1596 203
1597* [管理 Claude 的記憶](/zh-TW/memory)：寫入和組織 CLAUDE.md、rules 和自動記憶204* [管理 Claude 的記憶](/zh-TW/memory)：寫入和組織 CLAUDE.md、rules 和自動記憶
1598* [設定設定](/zh-TW/settings)：設定權限、hooks、環境變數和模型預設值205* [設定設定](/zh-TW/settings)：設定權限、hooks、環境變數和模型預設值
