950 pages for agent.

Interactive mode Claude Code CLI · in the page interactive-mode …-cleared-draft) | | `Ctrl+X Ctrl+K` | Stop all running [background subagents](/docs/en/sub-agents.md#run-subagents-in-foreground-or-background) in this session, and turn off [artifact auto-replies](/d… Customize keyboard shortcuts Claude Code CLI · in the page keybindings …d` | An input field or select in a mod's pane has keyboard focus | | `Agents` | [Agent view](/docs/en/agent-view.md) (`claude agents`) | | `Scroll` | Conversation scrolling and text selection in fulls… Set up Claude Code in a monorepo or large codebase Claude Code CLI · in the page large-codebases …context small in any repository, such as [running exploration in a subagent](/docs/en/best-practices.md#use-subagents-for-investigation) so file reads stay out of the main conversation, see [Best prac… Legal and compliance Claude Code CLI · in the page legal-and-compliance …irectly (1P) or accessing it through Amazon Bedrock or Google Cloud's Agent Platform (3P), your existing commercial agreement will apply to Claude Code usage, unless we've mutually agreed otherwise.… Other LLM gateways Claude Code CLI · in the page llm-gateway …n's Anthropic Console account, or your Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry account when the gateway routes there. [`ANTHROPIC_BASE_URL`](/docs/en/llm-gateway-connect#s… Connect Claude Code to an LLM gateway Claude Code CLI · in the page llm-gateway-connect …the gateway only in your shell, it doesn't reliably reach background agents hosted by the [supervisor](/docs/en/agent-view.md#how-background-sessions-are-hosted); see [how each background session sou… Claude Code gateway compatibility guide Claude Code CLI · in the page llm-gateway-protocol …riables in the Selected by column of the table below. Google Cloud's Agent Platform is Google Cloud's Claude endpoint, formerly Vertex AI; its variable names keep the `VERTEX` spelling. | Format | S… Roll out an LLM gateway for your organization Claude Code CLI · in the page llm-gateway-rollout …n Bedrock](/docs/en/amazon-bedrock.md#prerequisites), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai.md#prerequisites), or [Microsoft Foundry](/docs/en/microsoft-foundry.md#prerequisites) p… Deploy managed settings Claude Code CLI · in the page managed-settings …he VS Code and JetBrains extensions, the desktop app's Code tab, and [Agent SDK](/docs/en/agent-sdk/typescript.md) sessions read all of these sources. Agent SDK sessions load managed settings even whe… Connect Claude Code to tools via MCP Claude Code CLI · in the page mcp …e" / "ws") to this entry`. Only an SDK host application, such as an [Agent SDK](/docs/en/agent-sdk/mcp.md) application or the [desktop app](/docs/en/desktop.md), can register an in-process `"type": "… How Claude remembers your project Claude Code CLI · in the page memory …your project > Give Claude persistent instructions with CLAUDE.md or AGENTS.md files, and let Claude accumulate learnings automatically with auto memory. Each Claude Code session begins with a fresh… Claude Code on Microsoft Foundry Claude Code CLI · in the page microsoft-foundry …esource on the first prompt. Unlike Amazon Bedrock and Google Cloud's Agent Platform, Microsoft Foundry has no interactive setup wizard, so the environment variables in steps 3 and 4 are the only conf… Model configuration Claude Code CLI · in the page model-config …ofile ARN * Microsoft Foundry: a deployment name * Google Cloud's Agent Platform: a version name For guidance on which model and effort level fit different kinds of work, see [Choosing a Claude m… Monitoring Claude Code CLI · in the page monitoring-usage …elemetry](#traces-beta). > [!NOTE] > > For the Claude API or Managed Agents, see [OpenTelemetry for the Claude API](https://platform.claude.com/docs/en/manage-claude/opentelemetry). ## Quick start… Enterprise network configuration Claude Code CLI · in the page network-config …m this one in the debug log. ## Apply network settings to background agents [Background agents](/docs/en/agent-view.md) don't run inside the terminal that dispatched them. A per-user supervisor proc… Output styles Claude Code CLI · in the page output-styles …a command, use a [hook](/docs/en/hooks-guide.md). > * For skills, subagents, and the other options, see [Choose between an output style and other features](#choose-between-an-output-style-and-other-f… Overview Claude Code CLI · in the page overview # Overview > Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Available in your terminal, IDE, desktop app, and… Choose a permission mode Claude Code CLI · in the page permission-modes …`disableAutoMode` to `"disable"` | `default` | | `claude -p` or the [Agent SDK](/docs/en/agent-sdk/permissions.md#permission-modes) | `default` | | Your organization has the [HIPAA configuration](#hi… Configure permissions Claude Code CLI · in the page permissions …rts fine-grained permissions so that you can specify exactly what the agent is allowed to do and what it can't. You can check permission settings into version control to share them with every develope… Platforms and integrations Claude Code CLI · in the page platforms …| Terminal workflows, scripting, remote servers | Full feature set, [Agent SDK](/docs/en/headless.md), [computer use](/docs/en/computer-use.md) on macOS (Pro and Max), third-party providers | | [Desk… Test plugins with evals Claude Code CLI · in the page plugin-evals …those calls. If you run Claude Code on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, run the suite from a shell that exports the same provider variables as your normal sessions,… Recommend your plugin from your CLI Claude Code CLI · in the page plugins/cli-hints …ars only in interactive terminal sessions. In `claude -p` runs, in subagent runs, and in hook command output, the tag is stripped and no prompt is shown. All of these checks must also pass: * **Offic… Plugin commands reference Claude Code CLI · in the page plugins/cli-reference …`--with <components...>` | Also scaffold starter files for `skills`, `agents`, `hooks`, `mcp`, `lsp`, `output-style`, or `channel` | | `-f, --force` | Overwrite an existing `.claude-plugin/` at the ta… Add components to a plugin Claude Code CLI · in the page plugins/components …each. A Claude Code plugin is built from components, such as skills, agents, hooks, and MCP servers. Each component has a default folder in the plugin, an optional manifest key in `.claude-plugin/plu… Create a Claude Code plugin Claude Code CLI · in the page plugins/create …nvert an existing .claude/ setup. A plugin is a directory of skills, agents, hooks, and MCP servers, plus a `plugin.json` file, called the manifest, that names the plugin. Claude Code loads the direc… Host and maintain a marketplace Claude Code CLI · in the page plugins/host-marketplace …without a passphrase prompt, for example because it's loaded in `ssh-agent`. The host must already be in `known_hosts`. * **HTTPS**: Claude Code leaves the user's git credential helper enabled but fo… Install and manage plugins Claude Code CLI · in the page plugins/install …nd update or remove them later. Installing a plugin adds its skills, agents, hooks, and MCP servers to Claude Code on your machine. This page is for anyone using plugins on their own machine or acco… Plugin loading reference Claude Code CLI · in the page plugins/loading …, set [`CLAUDE_CODE_PLUGIN_DIRS`](/docs/en/env-vars#variables), or an Agent SDK app passed the `plugins` option. It loads for that session only | On for the session unless the manifest sets `defaultEn… Plugin manifest reference Claude Code CLI · in the page plugins/manifest-reference …"version": "1.2.0", "description": "Deployment commands, a review agent, and a status monitor", "author": { "name": "Example Team", "email": "[email protected]", "url": "https://exampl… Marketplace reference Claude Code CLI · in the page plugins/marketplace-reference …ude-plugins-official`, `anthropic-marketplace`, `anthropic-plugins`, `agent-skills`, `anthropic-agent-skills`, `life-sciences`, `knowledge-work-plugins`, `claude-for-legal`, `claude-for-financial-serv… Measure plugin cost and usage Claude Code CLI · in the page plugins/measure …plugin is enabled includes the names and descriptions of its skills, agents, and commands in Claude's context, and those tokens count against the user's usage whether or not the plugin gets used. Thi… Manage mods for your organization Claude Code CLI · in the page plugins/mods/admin …through MDM, it works the same way on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. For delivery from the claude.ai admin console, see [Platform availability](/docs/en/server-… Use the mods API Claude Code CLI · in the page plugins/mods/api …ser's Claude Code settings, not from the call. For one hour, set [`subagentPromptCacheTtl`](/docs/en/prompt-caching#choose-the-ttl-yourself) to `1h`. * **Breakpoints per request**: the API accepts [up… React to events with a mod Claude Code CLI · in the page plugins/mods/events …` fires when Claude Code is about to run a tool, including calls a subagent makes and calls to MCP tools. `e.tool` is the tool's name and the tool's arguments are fields of `e`, such as `e.command` fo… Interface gallery for mods Claude Code CLI · in the page plugins/mods/gallery …minal. * **Background sessions**: every [background session](/docs/en/agent-view.md), whatever terminal it's attached from. * **iTerm2 outside fullscreen rendering**: in iTerm2 the picture draws only… Mods overview Claude Code CLI · in the page plugins/mods/overview …lugin in place: the plugin stays installed, and its skills, commands, agents, and MCP servers load. Other settings and flags reach further. [`disableAllHooks`](/docs/en/settings-reference#disableallho… Mods reference Claude Code CLI · in the page plugins/mods/reference …retooluse) hook changed the mods API call the event came from, or an `agent.spawn` hook changed an agent started by that call. `lent` when a method another mod adds to the mods API fired that event, u… Test a mod Claude Code CLI · in the page plugins/mods/test …'assistant', text: '...', toolUses: [] }] })` | | `$.session.id`, `$.agent.list` | `() => ({ value: 'abc123' })`, `() => ({ value: [] })` | | `session.send` | `() => ({ isDelivered: true })`. `e.to`… Troubleshoot a mod Claude Code CLI · in the page plugins/mods/troubleshoot …the mod's name and names a `$.prompt.submit`, `$.command.run`, or `$.agent.spawn` call, as in `first-mod: its session.start ran again in a fresh copy; the $.prompt.submit call it had already made was… Manage Claude Code plugins for your organization Claude Code CLI · in the page plugins/org …| `disableSideloadFlags` | Rejects `--plugin-dir`, `--plugin-url`, `--agents`, the Agent SDK `plugins` option, and non-SDK `--mcp-config` at startup, and rejects folders named in the [`CLAUDE_CODE_PLU… Plugins overview Claude Code CLI · in the page plugins/overview …nstall or create one. A Claude Code plugin is a directory of skills, agents, hooks, MCP servers, or other components that Claude Code installs and loads as one unit. Most plugins come from a marketpl… Plugin security and trust Claude Code CLI · in the page plugins/security …boxing.md), and not when it runs inside it. * **Skills, commands, and agents**: these enter Claude's context as instructions, so they influence what Claude does with the tools it already has. * **Upda… Troubleshoot plugins Claude Code CLI · in the page plugins/troubleshooting …n: [non-interactive mode](/docs/en/headless.md) with `claude -p`, the Agent SDK, the Claude desktop app's Code tab, the VS Code extension panel, and the browser at claude.ai/code. In the VS Code exte… How Claude Code uses prompt caching Claude Code CLI · in the page prompt-caching …ttps://platform.claude.com/docs) * **Amazon Bedrock or Google Cloud's Agent Platform**: the cache lives in your cloud provider's serving infrastructure * **Microsoft Foundry**: depends on the deployme… Prompt library Claude Code CLI · in the page prompt-library …d', cat: 'Review', roles: ['security'], prompt: 'use a subagent to review {path} for security issues and report what it finds', slots: { path: 'src/api/' }, nextHref: '/e… Quickstart Claude Code CLI · in the page quickstart …sole for centralized cost tracking. * [Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry](/docs/en/third-party-integrations.md) (enterprise cloud providers) * A self-hosted [Claude a… Continue local sessions from any device with Remote Control Claude Code CLI · in the page remote-control …rom both surfaces at once**: the conversation and the progress of [subagents](/docs/en/sub-agents.md) and [dynamic workflows](/docs/en/workflows.md) stay in sync across all connected devices, so you c… Automate work with scheduled tasks Claude Code CLI · in the page routines …dentials), or a cloud provider such as Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. `/schedule` requires a claude.ai subscription login. With a Console API key or a profile, an… Choose a sandbox environment Claude Code CLI · in the page sandbox-environments …the broader security model, see [Security](/docs/en/security.md). For Agent SDK deployments, see [Secure deployment](/docs/en/agent-sdk/secure-deployment.md). ## Compare sandboxing approaches The fi… Configure the sandboxed Bash tool Claude Code CLI · in the page sandboxing …ess the session is one of these: * **A [background session](/docs/en/agent-view.md)**: strict sandbox mode covers shell-mode commands too * **A Linux session with [`CLAUDE_CODE_SUBPROCESS_ENV_SCRUB`]…