14 14 

15Multiple independent Claude Code sessions coordinated by a team lead, with a shared task list and peer-to-peer messaging. Unlike [subagents](#subagent), which run within a single session and report only to the parent, teammates each have their own context window and you can interact with any of them directly. Agent teams are experimental and must be enabled by setting `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`.15Multiple independent Claude Code sessions coordinated by a team lead, with a shared task list and peer-to-peer messaging. Unlike [subagents](#subagent), which run within a single session and report only to the parent, teammates each have their own context window and you can interact with any of them directly. Agent teams are experimental and must be enabled by setting `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`.

16 16 

17Learn more: [Run agent teams](/en/agent-teams)17Learn more: [Run agent teams](/docs/en/agent-teams)

18 18 

19### Agentic coding19### Agentic coding

20 20 

21A workflow where the AI can read files, run commands, and make changes autonomously while you watch, redirect, or step away, as opposed to chat-based assistants that only respond with text you must apply yourself. Claude Code is agentic because it has [tools](#tool) that let it act, not just advise.21A workflow where the AI can read files, run commands, and make changes autonomously while you watch, redirect, or step away, as opposed to chat-based assistants that only respond with text you must apply yourself. Claude Code is agentic because it has [tools](#tool) that let it act, not just advise.

22 22 

23Learn more: [How Claude Code works](/en/how-claude-code-works)23Learn more: [How Claude Code works](/docs/en/how-claude-code-works)

24 24 

25### Agentic harness25### Agentic harness

26 26 

27The tools, context management, and execution environment that turn a language model into a capable coding agent. Claude Code is the harness; Claude is the model inside it. The harness supplies file access, shell execution, permission gating, memory loading, and the loop that chains actions together.27The tools, context management, and execution environment that turn a language model into a capable coding agent. Claude Code is the harness; Claude is the model inside it. The harness supplies file access, shell execution, permission gating, memory loading, and the loop that chains actions together.

28 28 

29Learn more: [How Claude Code works](/en/how-claude-code-works)29Learn more: [How Claude Code works](/docs/en/how-claude-code-works)

30 30 

31### Agentic loop31### Agentic loop

32 32 

33The cycle Claude works through for every task: gather context, take action, verify results, and repeat until done. Each tool use returns information that informs the next step. You can interrupt the loop at any point to redirect. Most extension points, including [hooks](#hook), [skills](#skill), and [MCP](#mcp-model-context-protocol), plug into specific phases of this loop.33The cycle Claude works through for every task: gather context, take action, verify results, and repeat until done. Each tool use returns information that informs the next step. You can interrupt the loop at any point to redirect. Most extension points, including [hooks](#hook), [skills](#skill), and [MCP](#mcp-model-context-protocol), plug into specific phases of this loop.

34 34 

35Learn more: [How Claude Code works](/en/how-claude-code-works#the-agentic-loop)35Learn more: [How Claude Code works](/docs/en/how-claude-code-works#the-agentic-loop)

36 36 

37### Artifact37### Artifact

38 38 

39A live, interactive web page Claude Code publishes from your session to a private URL on claude.ai, so you can see output visually or share it instead of reading terminal text. The page updates in place when the session republishes. Artifacts you create from Claude Code appear in the same gallery as artifacts created in claude.ai conversations. Sharing depends on your plan: on Pro and Max, a public link that anyone can open; on Team and Enterprise, sharing within your organization, plus public links once an Owner enables them.39A live, interactive web page Claude Code publishes from your session to a private URL on claude.ai, so you can see output visually or share it instead of reading terminal text. The page updates in place when the session republishes. Artifacts you create from Claude Code appear in the same gallery as artifacts created in claude.ai conversations. Sharing depends on your plan: on Pro and Max, a public link that anyone can open; on Team and Enterprise, sharing within your organization, plus public links once an Owner enables them.

40 40 

41Learn more: [Share session output as artifacts](/en/artifacts)41Learn more: [Share session output as artifacts](/docs/en/artifacts)

42 42 

43### Auto memory43### Auto memory

44 44 

45Notes Claude writes for itself based on your corrections and preferences, stored per git repository under `~/.claude/projects/`. All worktrees of the same repository share one auto memory directory. The first 200 lines or 25 KB of the `MEMORY.md` index loads at the start of every session. Auto memory is the Claude-written counterpart to [CLAUDE.md](#claude-md), which you write.45Notes Claude writes for itself based on your corrections and preferences, stored per git repository under `~/.claude/projects/`. All worktrees of the same repository share one auto memory directory. The first 200 lines or 25 KB of the `MEMORY.md` index loads at the start of every session. Auto memory is the Claude-written counterpart to [CLAUDE.md](#claude-md), which you write.

46 46 

47Learn more: [Auto memory](/en/memory#auto-memory)47Learn more: [Auto memory](/docs/en/memory#auto-memory)

48 48 

49### Auto mode49### Auto mode

50 50 

51A [permission mode](#permission-mode) where a separate classifier model reviews actions in the background, so most run without approval prompts; explicit ask rules still prompt. The classifier blocks scope escalation, untrusted infrastructure, and [prompt injection](#prompt-injection). It never sees tool results, so injected instructions cannot influence its decisions.51A [permission mode](#permission-mode) where a separate classifier model reviews actions in the background, so most run without approval prompts; explicit ask rules still prompt. The classifier blocks scope escalation, untrusted infrastructure, and [prompt injection](#prompt-injection). It never sees tool results, so injected instructions cannot influence its decisions.

52 52 

53Learn more: [Eliminate prompts with auto mode](/en/permission-modes#eliminate-prompts-with-auto-mode)53Learn more: [Eliminate prompts with auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)

54 54 

55## B55## B

56 56 

58 58 

59A startup flag, `--bare`, that skips auto-discovery of hooks, skills, plugins, MCP servers, auto memory, and CLAUDE.md. Only flags you pass explicitly take effect. Recommended for CI and scripted calls where you need identical behavior across machines regardless of local configuration.59A startup flag, `--bare`, that skips auto-discovery of hooks, skills, plugins, MCP servers, auto memory, and CLAUDE.md. Only flags you pass explicitly take effect. Recommended for CI and scripted calls where you need identical behavior across machines regardless of local configuration.

60 60 

61Learn more: [Start faster with bare mode](/en/headless#start-faster-with-bare-mode)61Learn more: [Start faster with bare mode](/docs/en/headless#start-faster-with-bare-mode)

62 62 

63### Bundled skills63### Bundled skills

64 64 

65Prompt-based playbooks included with Claude Code, such as `/batch`, `/code-review`, `/debug`, and `/loop`. Unlike built-in commands, which execute fixed logic, bundled skills give Claude a detailed prompt and let it orchestrate the work, so they can spawn agents, read files, and adapt to your codebase.65Prompt-based playbooks included with Claude Code, such as `/batch`, `/code-review`, `/debug`, and `/loop`. Unlike built-in commands, which execute fixed logic, bundled skills give Claude a detailed prompt and let it orchestrate the work, so they can spawn agents, read files, and adapt to your codebase.

66 66 

67Learn more: [Bundled skills](/en/skills#bundled-skills)67Learn more: [Bundled skills](/docs/en/skills#bundled-skills)

68 68 

69## C69## C

70 70 

72 72 

73An [MCP server](#mcp-model-context-protocol) that pushes events into your running session so Claude can react to things that happen while you're away from the terminal. Channels can be two-way: Claude reads an inbound event and replies back through the same channel. Telegram, Discord, and iMessage are included in the research preview.73An [MCP server](#mcp-model-context-protocol) that pushes events into your running session so Claude can react to things that happen while you're away from the terminal. Channels can be two-way: Claude reads an inbound event and replies back through the same channel. Telegram, Discord, and iMessage are included in the research preview.

74 74 

75Learn more: [Channels](/en/channels)75Learn more: [Channels](/docs/en/channels)

76 76 

77### Checkpoint77### Checkpoint

78 78 

79A restore point created at each prompt you send. Claude Code snapshots files before every edit so a checkpoint can revert them. Press `Esc` twice or run `/rewind` to restore code, conversation, or both to an earlier point, or to summarize part of the conversation from a selected message. Checkpoints are saved with the conversation, so a resumed session can still `/rewind` to them. They're separate from git and don't track changes made through the Bash tool.79A restore point created at each prompt you send. Claude Code snapshots files before every edit so a checkpoint can revert them. Press `Esc` twice or run `/rewind` to restore code, conversation, or both to an earlier point, or to summarize part of the conversation from a selected message. Checkpoints are saved with the conversation, so a resumed session can still `/rewind` to them. They're separate from git and don't track changes made through the Bash tool.

80 80 

81Learn more: [Checkpointing](/en/checkpointing)81Learn more: [Checkpointing](/docs/en/checkpointing)

82 82 

83### `.claude` directory83### `.claude` directory

84 84 

85The directory where Claude Code reads project-scoped configuration: settings, hooks, skills, subagents, rules, and auto memory. A project has `.claude/` at its root; your user-level defaults are at `~/.claude/`.85The directory where Claude Code reads project-scoped configuration: settings, hooks, skills, subagents, rules, and auto memory. A project has `.claude/` at its root; your user-level defaults are at `~/.claude/`.

86 86 

87Learn more: [The `.claude` directory](/en/claude-directory)87Learn more: [The `.claude` directory](/docs/en/claude-directory)

88 88 

89### CLAUDE.md89### CLAUDE.md

90 90 

92 92 

93You can place CLAUDE.md at project scope in `./CLAUDE.md` or `./.claude/CLAUDE.md`, at user scope in `~/.claude/CLAUDE.md`, or as [managed policy](#managed-settings) for your organization. All discovered files are concatenated into context rather than overriding each other, ordered from broadest scope to most specific.93You can place CLAUDE.md at project scope in `./CLAUDE.md` or `./.claude/CLAUDE.md`, at user scope in `~/.claude/CLAUDE.md`, or as [managed policy](#managed-settings) for your organization. All discovered files are concatenated into context rather than overriding each other, ordered from broadest scope to most specific.

94 94 

95Learn more: [CLAUDE.md files](/en/memory#claude-md-files)95Learn more: [CLAUDE.md files](/docs/en/memory#claude-md-files)

96 96 

97### Command97### Command

98 98 

99A reusable instruction you invoke by typing `/name` in the prompt. Built-in commands such as `/clear`, `/model`, and `/compact` control the session. You can define your own commands as files in `.claude/commands/`, or install them from a [plugin](#plugin). [Skills](#skill) are the recommended way to package multi-step commands.99A reusable instruction you invoke by typing `/name` in the prompt. Built-in commands such as `/clear`, `/model`, and `/compact` control the session. You can define your own commands as files in `.claude/commands/`, or install them from a [plugin](#plugin). [Skills](#skill) are the recommended way to package multi-step commands.

100 100 

101Two other uses of the word are unrelated: `claude` CLI subcommands such as `claude mcp add`, listed in the [CLI reference](/en/cli-reference#cli-commands), and the `command` field of a stdio [MCP server](#mcp-server) entry, which specifies the executable Claude Code launches to start the server.101Two other uses of the word are unrelated: `claude` CLI subcommands such as `claude mcp add`, listed in the [CLI reference](/docs/en/cli-reference#cli-commands), and the `command` field of a stdio [MCP server](#mcp-server) entry, which specifies the executable Claude Code launches to start the server.

102 102 

103Learn more: [Commands](/en/commands) · [Skills](/en/skills)103Learn more: [Commands](/docs/en/commands) · [Skills](/docs/en/skills)

104 104 

105### Compaction105### Compaction

106 106 

107Automatic summarization of your conversation when the [context window](#context-window) approaches its limit. Older tool outputs are cleared first, then the conversation is summarized. Project-root CLAUDE.md and auto memory survive compaction and reload from disk; instructions given only in conversation may be lost. Run `/compact` to trigger manually, optionally with a focus like `/compact focus on the API changes`.107Automatic summarization of your conversation when the [context window](#context-window) approaches its limit. Older tool outputs are cleared first, then the conversation is summarized. Project-root CLAUDE.md and auto memory survive compaction and reload from disk; instructions given only in conversation may be lost. Run `/compact` to trigger manually, optionally with a focus like `/compact focus on the API changes`.

108 108 

109Learn more: [What survives compaction](/en/context-window#what-survives-compaction) · [When context fills up](/en/how-claude-code-works#when-context-fills-up)109Learn more: [What survives compaction](/docs/en/context-window#what-survives-compaction) · [When context fills up](/docs/en/how-claude-code-works#when-context-fills-up)

110 110 

111### Connector111### Connector

112 112 

113An [MCP server](#mcp-server) added to your claude.ai account rather than configured in Claude Code. When you sign in to Claude Code with that account, your connectors appear in `/mcp` alongside the servers you added locally. Organizations can also provision connectors and set per-tool controls on them.113An [MCP server](#mcp-server) added to your claude.ai account rather than configured in Claude Code. When you sign in to Claude Code with that account, your connectors appear in `/mcp` alongside the servers you added locally. Organizations can also provision connectors and set per-tool controls on them.

114 114 

115Learn more: [Use MCP servers from claude.ai](/en/mcp#use-mcp-servers-from-claude-ai)115Learn more: [Use MCP servers from claude.ai](/docs/en/mcp#use-mcp-servers-from-claude-ai)

116 116 

117### Context window117### Context window

118 118 

119The working memory for a session, holding conversation history, file contents, command outputs, CLAUDE.md, auto memory, loaded skills, and system instructions. As you work, context fills up until [compaction](#compaction) summarizes it. Run `/context` to see what's using space. For the underlying model concept, see the [platform glossary](https://platform.claude.com/docs/en/about-claude/glossary#context-window).119The working memory for a session, holding conversation history, file contents, command outputs, CLAUDE.md, auto memory, loaded skills, and system instructions. As you work, context fills up until [compaction](#compaction) summarizes it. Run `/context` to see what's using space. For the underlying model concept, see the [platform glossary](https://platform.claude.com/docs/en/about-claude/glossary#context-window).

120 120 

121Learn more: [Explore the context window](/en/context-window)121Learn more: [Explore the context window](/docs/en/context-window)

122 122 

123## D123## D

124 124 

126 126 

127A phone-initiated task router that spawns a Claude Code session in the Desktop app when you send a coding task from the Claude mobile app. Your prompt routes to the right tool automatically. Available on Pro and Max plans.127A phone-initiated task router that spawns a Claude Code session in the Desktop app when you send a coding task from the Claude mobile app. Your prompt routes to the right tool automatically. Available on Pro and Max plans.

128 128 

129Learn more: [Sessions from Dispatch](/en/desktop#sessions-from-dispatch)129Learn more: [Sessions from Dispatch](/docs/en/desktop#sessions-from-dispatch)

130 130 

131## E131## E

132 132 

134 134 

135A setting that controls how much of the adaptive-reasoning thinking budget Claude uses on each turn. Higher effort means more thinking tokens and deeper reasoning; lower effort is faster and cheaper. Effort is supported on Fable 5, on Opus 4.6 and later, and on Sonnet 4.6 and later.135A setting that controls how much of the adaptive-reasoning thinking budget Claude uses on each turn. Higher effort means more thinking tokens and deeper reasoning; lower effort is faster and cheaper. Effort is supported on Fable 5, on Opus 4.6 and later, and on Sonnet 4.6 and later.

136 136 

137Learn more: [Adjust effort level](/en/model-config#adjust-effort-level)137Learn more: [Adjust effort level](/docs/en/model-config#adjust-effort-level)

138 138 

139### Extended thinking139### Extended thinking

140 140 

141Visible step-by-step reasoning the model performs before responding. You can adjust it with the [effort level](#effort-level), or cap thinking tokens with `MAX_THINKING_TOKENS` on models with a fixed thinking budget. Thinking appears in gray italic text in the terminal.141Visible step-by-step reasoning the model performs before responding. You can adjust it with the [effort level](#effort-level), or cap thinking tokens with `MAX_THINKING_TOKENS` on models with a fixed thinking budget. Thinking appears in gray italic text in the terminal.

142 142 

143Learn more: [Use extended thinking](/en/model-config#extended-thinking)143Learn more: [Use extended thinking](/docs/en/model-config#extended-thinking)

144 144 

145## H145## H

146 146 

154* **Matcher**: filters which events fire it154* **Matcher**: filters which events fire it

155* **Hook handler**: what runs155* **Hook handler**: what runs

156 156 

157Learn more: [Get started with hooks](/en/hooks-guide) · [Hooks reference](/en/hooks)157Learn more: [Get started with hooks](/docs/en/hooks-guide) · [Hooks reference](/docs/en/hooks)

158 158 

159## M159## M

160 160 

161### Managed settings161### Managed settings

162 162 

163Settings enforced org-wide by IT or DevOps, delivered from Anthropic's servers through the admin console or deployed to devices at an OS-level path outside `~/.claude`. User and project settings cannot override managed settings. Server-managed delivery applies on [eligible configurations](/en/server-managed-settings#platform-availability); see [Security considerations](/en/server-managed-settings#security-considerations). Use this for security policies, compliance requirements, or standardized tooling across a fleet.163Settings enforced org-wide by IT or DevOps, delivered from Anthropic's servers through the admin console or deployed to devices at an OS-level path outside `~/.claude`. User and project settings cannot override managed settings. Server-managed delivery applies on [eligible configurations](/docs/en/server-managed-settings#platform-availability); see [Security considerations](/docs/en/server-managed-settings#security-considerations). Use this for security policies, compliance requirements, or standardized tooling across a fleet.

164 164 

165Learn more: [Server-managed settings](/en/server-managed-settings) · [Settings files](/en/settings#settings-files)165Learn more: [Server-managed settings](/docs/en/server-managed-settings) · [Settings files](/docs/en/settings#settings-files)

166 166 

167### MCP (Model Context Protocol)167### MCP (Model Context Protocol)

168 168 

169An open standard for connecting AI tools to external data sources and services. MCP servers give Claude new tools for Slack, Jira, databases, browsers, and hundreds of other integrations. You connect servers via `/mcp` or by adding them to `.mcp.json`. For the protocol itself, see the [platform glossary](https://platform.claude.com/docs/en/about-claude/glossary#mcp-model-context-protocol).169An open standard for connecting AI tools to external data sources and services. MCP servers give Claude new tools for Slack, Jira, databases, browsers, and hundreds of other integrations. You connect servers via `/mcp` or by adding them to `.mcp.json`. For the protocol itself, see the [platform glossary](https://platform.claude.com/docs/en/about-claude/glossary#mcp-model-context-protocol).

170 170 

171Learn more: [Model Context Protocol](/en/mcp)171Learn more: [Model Context Protocol](/docs/en/mcp)

172 172 

173### MCP server173### MCP server

174 174 

175A program that gives Claude tools, prompts, or resources over [MCP](#mcp-model-context-protocol). You add servers with `claude mcp add`, in `.mcp.json`, through a [plugin](#plugin), or as a claude.ai [connector](#connector). A local stdio server runs as a process Claude Code starts from the `command` and `args` fields of its configuration, which have nothing to do with the [commands](#command) you type at the prompt.175A program that gives Claude tools, prompts, or resources over [MCP](#mcp-model-context-protocol). You add servers with `claude mcp add`, in `.mcp.json`, through a [plugin](#plugin), or as a claude.ai [connector](#connector). A local stdio server runs as a process Claude Code starts from the `command` and `args` fields of its configuration, which have nothing to do with the [commands](#command) you type at the prompt.

176 176 

177Learn more: [Model Context Protocol](/en/mcp)177Learn more: [Model Context Protocol](/docs/en/mcp)

178 178 

179### MCP Tool Search179### MCP Tool Search

180 180 

181A context-saving mechanism that defers MCP tool schemas until needed. Only tool names load at startup; Claude fetches the full schema on demand when it decides to use a specific tool. This keeps idle MCP servers from consuming much context.181A context-saving mechanism that defers MCP tool schemas until needed. Only tool names load at startup; Claude fetches the full schema on demand when it decides to use a specific tool. This keeps idle MCP servers from consuming much context.

182 182 

183Learn more: [Scale with MCP Tool Search](/en/mcp#scale-with-mcp-tool-search)183Learn more: [Scale with MCP Tool Search](/docs/en/mcp#scale-with-mcp-tool-search)

184 184 

185## N185## N

186 186 

187### Non-interactive mode187### Non-interactive mode

188 188 

189A mode that executes a single prompt and exits without an interactive prompt, invoked with `-p` or `--print`. Used for CI, scripts, and piping. The run is still saved as a resumable session unless you pass `--no-session-persistence`. The [Agent SDK](/en/agent-sdk/overview) is the Python and TypeScript equivalent. Formerly called headless mode.189A mode that executes a single prompt and exits without an interactive prompt, invoked with `-p` or `--print`. Used for CI, scripts, and piping. The run is still saved as a resumable session unless you pass `--no-session-persistence`. The [Agent SDK](/docs/en/agent-sdk/overview) is the Python and TypeScript equivalent. Formerly called headless mode.

190 190 

191Learn more: [Run Claude Code programmatically](/en/headless)191Learn more: [Run Claude Code programmatically](/docs/en/headless)

192 192 

193## O193## O

194 194 

196 196 

197A configuration that modifies Claude's system prompt to change response behavior, tone, or format. Output styles turn off the software-engineering-specific parts of the default system prompt, unlike [CLAUDE.md](#claude-md) which is delivered as a user message following the system prompt. Built-in styles include Default, Proactive, Explanatory, and Learning.197A configuration that modifies Claude's system prompt to change response behavior, tone, or format. Output styles turn off the software-engineering-specific parts of the default system prompt, unlike [CLAUDE.md](#claude-md) which is delivered as a user message following the system prompt. Built-in styles include Default, Proactive, Explanatory, and Learning.

198 198 

199Learn more: [Output styles](/en/output-styles)199Learn more: [Output styles](/docs/en/output-styles)

200 200 

201## P201## P

202 202 

206 206 

207The `default` mode is labeled Manual in the CLI, in the VS Code and JetBrains extensions, and in the desktop app, and Claude Code accepts `manual` as an alias for the value.207The `default` mode is labeled Manual in the CLI, in the VS Code and JetBrains extensions, and in the desktop app, and Claude Code accepts `manual` as an alias for the value.

208 208 

209Learn more: [Choose a permission mode](/en/permission-modes)209Learn more: [Choose a permission mode](/docs/en/permission-modes)

210 210 

211### Permission rule211### Permission rule

212 212 

213A settings entry that allows, asks about, or denies a tool invocation based on the tool name and argument pattern. Rules are evaluated deny→ask→allow, first match wins. Permission rules are fine-grained controls layered on top of the broader [permission mode](#permission-mode).213A settings entry that allows, asks about, or denies a tool invocation based on the tool name and argument pattern. Rules are evaluated deny→ask→allow, first match wins. Permission rules are fine-grained controls layered on top of the broader [permission mode](#permission-mode).

214 214 

215Learn more: [Configure permissions](/en/permissions)215Learn more: [Configure permissions](/docs/en/permissions)

216 216 

217### Plan mode217### Plan mode

218 218 

219A [permission mode](#permission-mode) where Claude researches and proposes changes without editing your source files. It can read, search, and run exploration commands, then presents a plan for approval before touching anything. Enter plan mode with `/plan` or by pressing `Shift+Tab`.219A [permission mode](#permission-mode) where Claude researches and proposes changes without editing your source files. It can read, search, and run exploration commands, then presents a plan for approval before touching anything. Enter plan mode with `/plan` or by pressing `Shift+Tab`.

220 220 

221Learn more: [Analyze before you edit with plan mode](/en/permission-modes#analyze-before-you-edit-with-plan-mode)221Learn more: [Analyze before you edit with plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode)

222 222 

223### Plugin223### Plugin

224 224 

225A bundle of skills, hooks, subagents, and MCP servers packaged as a single installable unit. Plugin skills are namespaced as `plugin-name:skill-name` so multiple plugins coexist. Distribute plugins across teams via a [marketplace](/en/plugin-marketplaces).225A bundle of skills, hooks, subagents, and MCP servers packaged as a single installable unit. Plugin skills are namespaced as `plugin-name:skill-name` so multiple plugins coexist. Distribute plugins across teams via a [marketplace](/docs/en/plugin-marketplaces).

226 226 

227Learn more: [Plugins](/en/plugins)227Learn more: [Plugins](/docs/en/plugins)

228 228 

229### Project trust229### Project trust

230 230 

231A dialog accepting a directory before Claude Code loads its configuration. Acceptance is saved per project directory, except your home directory, where trust is held for the current session only and the prompt reappears on each launch. Trust gates auto-installation of marketplace plugins and execution of project-defined hooks. Trusting a directory means its `.claude/settings.json`, `.mcp.json`, and other config files take effect.231A dialog accepting a directory before Claude Code loads its configuration. Acceptance is saved per project directory, except your home directory, where trust is held for the current session only and the prompt reappears on each launch. Trust gates auto-installation of marketplace plugins and execution of project-defined hooks. Trusting a directory means its `.claude/settings.json`, `.mcp.json`, and other config files take effect.

232 232 

233Learn more: [The `.claude` directory](/en/claude-directory)233Learn more: [The `.claude` directory](/docs/en/claude-directory)

234 234 

235### Prompt injection235### Prompt injection

236 236 

237Hostile instructions embedded in a file, web page, or tool result that attempt to redirect Claude toward actions you never asked for. Claude Code's defenses include the permission system, command injection detection, and trust verification. [Auto mode](#auto-mode) adds a server-side probe that scans tool results for suspicious content and a classifier that never sees tool results, so injected text cannot influence its approval decisions.237Hostile instructions embedded in a file, web page, or tool result that attempt to redirect Claude toward actions you never asked for. Claude Code's defenses include the permission system, command injection detection, and trust verification. [Auto mode](#auto-mode) adds a server-side probe that scans tool results for suspicious content and a classifier that never sees tool results, so injected text cannot influence its approval decisions.

238 238 

239Learn more: [Protect against prompt injection](/en/security#protect-against-prompt-injection)239Learn more: [Protect against prompt injection](/docs/en/security#protect-against-prompt-injection)

240 240 

241## R241## R

242 242 

244 244 

245A way to continue a local Claude Code session from your phone or browser via claude.ai. Your code execution and files stay on your machine; the interface is remote. Different from Claude Code on the web, which runs in a cloud sandbox.245A way to continue a local Claude Code session from your phone or browser via claude.ai. Your code execution and files stay on your machine; the interface is remote. Different from Claude Code on the web, which runs in a cloud sandbox.

246 246 

247Learn more: [Remote Control](/en/remote-control)247Learn more: [Remote Control](/docs/en/remote-control)

248 248 

249### Rules249### Rules

250 250 

251Modular instruction files in `.claude/rules/` that load alongside CLAUDE.md. A rule can be path-scoped with YAML `paths:` frontmatter so it only loads when Claude reads a matching file, keeping context lean until it's relevant.251Modular instruction files in `.claude/rules/` that load alongside CLAUDE.md. A rule can be path-scoped with YAML `paths:` frontmatter so it only loads when Claude reads a matching file, keeping context lean until it's relevant.

252 252 

253Learn more: [Organize rules with `.claude/rules/`](/en/memory#organize-rules-with-claude/rules/)253Learn more: [Organize rules with `.claude/rules/`](/docs/en/memory#organize-rules-with-claude/rules/)

254 254 

255## S255## S

256 256 

258 258 

259OS-level filesystem and network isolation for the Bash tool. Commands run inside a boundary you define upfront, so Claude can work freely within it without per-command approval prompts. Sandboxing is a separate layer from [permission rules](#permission-rule).259OS-level filesystem and network isolation for the Bash tool. Commands run inside a boundary you define upfront, so Claude can work freely within it without per-command approval prompts. Sandboxing is a separate layer from [permission rules](#permission-rule).

260 260 

261Learn more: [Sandboxing](/en/sandboxing)261Learn more: [Sandboxing](/docs/en/sandboxing)

262 262 

263### Session263### Session

264 264 

265A conversation tied to your current directory, with its own independent [context window](#context-window). Sessions can be resumed with `claude -c`, forked with `--fork-session` to preserve history under a new session ID, or run in parallel across terminals. Running `/clear` starts a new session; the previous one stays stored and is available via `/resume`. Each session's transcript is stored under `~/.claude/projects/`.265A conversation tied to your current directory, with its own independent [context window](#context-window). Sessions can be resumed with `claude -c`, forked with `--fork-session` to preserve history under a new session ID, or run in parallel across terminals. Running `/clear` starts a new session; the previous one stays stored and is available via `/resume`. Each session's transcript is stored under `~/.claude/projects/`.

266 266 

267Learn more: [Work with sessions](/en/how-claude-code-works#work-with-sessions)267Learn more: [Work with sessions](/docs/en/how-claude-code-works#work-with-sessions)

268 268 

269### Settings layers269### Settings layers

270 270 

271The hierarchy Claude Code reads configuration from, in precedence order from highest to lowest: [managed policy](#managed-settings), command-line arguments, local settings at `.claude/settings.local.json`, project settings at `.claude/settings.json`, then user settings at `~/.claude/settings.json`. Arrays merge across layers; scalars at a higher layer override lower ones.271The hierarchy Claude Code reads configuration from, in precedence order from highest to lowest: [managed policy](#managed-settings), command-line arguments, local settings at `.claude/settings.local.json`, project settings at `.claude/settings.json`, then user settings at `~/.claude/settings.json`. Arrays merge across layers; scalars at a higher layer override lower ones.

272 272 

273Learn more: [Settings files](/en/settings#settings-files)273Learn more: [Settings files](/docs/en/settings#settings-files)

274 274 

275### Skill275### Skill

276 276 

278 278 

279Skills are the recommended successor to custom commands. A file at `.claude/commands/deploy.md` and one at `.claude/skills/deploy/SKILL.md` both create `/deploy` and work the same way; existing command files continue to work.279Skills are the recommended successor to custom commands. A file at `.claude/commands/deploy.md` and one at `.claude/skills/deploy/SKILL.md` both create `/deploy` and work the same way; existing command files continue to work.

280 280 

281Learn more: [Extend Claude with skills](/en/skills)281Learn more: [Extend Claude with skills](/docs/en/skills)

282 282 

283### Subagent283### Subagent

284 284 

286 286 

287Built-in subagents include Explore, Plan, and general-purpose.287Built-in subagents include Explore, Plan, and general-purpose.

288 288 

289Learn more: [Create custom subagents](/en/sub-agents)289Learn more: [Create custom subagents](/docs/en/sub-agents)

290 290 

291### Surface291### Surface

292 292 

293Any place you access Claude Code: the CLI, VS Code, JetBrains, Desktop, or claude.ai. All surfaces share the same engine. Sessions on your machine read your local CLAUDE.md, settings, and skills; [cloud sessions](/en/claude-code-on-the-web#what’s-available-in-cloud-sessions) start from a fresh clone of your repository and don't read `~/.claude/` on your machine. Slack and the Chrome extension are integrations that connect to a surface rather than surfaces themselves.293Any place you access Claude Code: the CLI, VS Code, JetBrains, Desktop, or claude.ai. All surfaces share the same engine. Sessions on your machine read your local CLAUDE.md, settings, and skills; [cloud sessions](/docs/en/cloud-environments#what-carries-over-from-your-setup) start from a fresh clone of your repository and don't read `~/.claude/` on your machine. Slack and the Chrome extension are integrations that connect to a surface rather than surfaces themselves.

294 294 

295Learn more: [Platforms and integrations](/en/platforms)295Learn more: [Platforms and integrations](/docs/en/platforms)

296 296 

297## T297## T

298 298 

300 300 

301A command, `/teleport`, that pulls a cloud Claude Code session into your local terminal. Claude fetches the branch, loads the conversation history, and resumes from the web session's last state. The reverse direction is `--cloud`, which sends a local task to run on the web.301A command, `/teleport`, that pulls a cloud Claude Code session into your local terminal. Claude fetches the branch, loads the conversation history, and resumes from the web session's last state. The reverse direction is `--cloud`, which sends a local task to run on the web.

302 302 

303Learn more: [From web to terminal](/en/claude-code-on-the-web#from-web-to-terminal)303Learn more: [From web to terminal](/docs/en/claude-code-on-the-web#from-web-to-terminal)

304 304 

305### Tool305### Tool

306 306 

307An action Claude can take: read a file, edit code, run a shell command, search the web, spawn a subagent. Tools are what make Claude Code agentic. Without them, Claude can only respond with text. Each tool use returns a result that informs Claude's next decision in the [agentic loop](#agentic-loop).307An action Claude can take: read a file, edit code, run a shell command, search the web, spawn a subagent. Tools are what make Claude Code agentic. Without them, Claude can only respond with text. Each tool use returns a result that informs Claude's next decision in the [agentic loop](#agentic-loop).

308 308 

309Learn more: [Tools available to Claude](/en/tools-reference)309Learn more: [Tools available to Claude](/docs/en/tools-reference)

310 310 

311### Turn311### Turn

312 312 

313One complete response from Claude within a [session](#session). A turn begins when you send a message and ends when Claude finishes responding, with any number of [tool](#tool) calls in between. [Stop hooks](#hook) fire at the end of each turn. A session consists of many turns, and the [agentic loop](#agentic-loop) describes what happens inside one.313One complete response from Claude within a [session](#session). A turn begins when you send a message and ends when Claude finishes responding, with any number of [tool](#tool) calls in between. [Stop hooks](#hook) fire at the end of each turn. A session consists of many turns, and the [agentic loop](#agentic-loop) describes what happens inside one.

314 314 

315Learn more: [How Claude Code works](/en/how-claude-code-works#the-agentic-loop)315Learn more: [How Claude Code works](/docs/en/how-claude-code-works#the-agentic-loop)

316 316 

317## V317## V

318 318 

319### Verification loop319### Verification loop

320 320 

321How a session knows the work is actually done rather than just plausible. You give Claude a check it can run, such as a test suite, a build, or a screenshot comparison, and Claude iterates until the check passes instead of stopping after one attempt. A verification loop is the prerequisite for [`/goal`](/en/goal), unattended runs, and [dynamic workflows](/en/workflows): without one, the only thing deciding the agent is finished is the agent itself.321How a session knows the work is actually done rather than just plausible. You give Claude a check it can run, such as a test suite, a build, or a screenshot comparison, and Claude iterates until the check passes instead of stopping after one attempt. A verification loop is the prerequisite for [`/goal`](/docs/en/goal), unattended runs, and [dynamic workflows](/docs/en/workflows): without one, the only thing deciding the agent is finished is the agent itself.

322 322 

323Learn more: [Give Claude a way to verify its work](/en/best-practices#give-claude-a-way-to-verify-its-work)323Learn more: [Give Claude a way to verify its work](/docs/en/best-practices#give-claude-a-way-to-verify-its-work)

324 324 

325## W325## W

326 326 

328 328 

329An isolation mode that runs Claude in a separate git worktree under `.claude/worktrees/`, enabled with the `-w` flag or `isolation: worktree` in subagent config. Changes stay on a separate branch in a separate directory, so parallel agents don't overwrite each other's files.329An isolation mode that runs Claude in a separate git worktree under `.claude/worktrees/`, enabled with the `-w` flag or `isolation: worktree` in subagent config. Changes stay on a separate branch in a separate directory, so parallel agents don't overwrite each other's files.

330 330 

331Learn more: [Run parallel sessions with git worktrees](/en/worktrees)331Learn more: [Run parallel sessions with git worktrees](/docs/en/worktrees)

332 332 

333***333***

334 334