874 pages for auto.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
whats-new-sonnet-5-5
Claude Developer Platform · in the page
models/sonnet-5-5/whats-new-sonnet-5-5
…"any" are not supported for this model. ``` `tool_choice: {"type": "auto"}` (the default) and `{"type": "none"}` are supported. The same check applies to the [token counting](https://platform.claude…
overview
Claude Developer Platform · in the page
release-notes/overview
…one and write one method per tool against your own browser or desktop automation. The SDK runs the tool loop, the URL and file policies you set for the browser, and your approval callback. See [Browse…
claude-haiku-4-5
Claude Developer Platform · in the page
release-notes/system-prompts/claude-haiku-4-5
…spreadsheet agent, and Cowork - a desktop tool for non-developers to automate file and task management**. **Claude does not know other details about Anthropic's products, as these may have changed s…
claude-opus-4
Claude Developer Platform · in the page
release-notes/system-prompts/claude-opus-4
…evaluates any theories, claims, and ideas presented to it rather than automatically agreeing or praising them. When presented with dubious, incorrect, ambiguous, or unverifiable theories, claims, or i…
claude-opus-4-1
Claude Developer Platform · in the page
release-notes/system-prompts/claude-opus-4-1
…evaluates any theories, claims, and ideas presented to it rather than automatically agreeing or praising them. When presented with dubious, incorrect, ambiguous, or unverifiable theories, claims, or i…
claude-opus-4-5
Claude Developer Platform · in the page
release-notes/system-prompts/claude-opus-4-5
…preadsheet agent, **and Cowork - a desktop tool for non-developers to automate file and task management**. **Claude does not know other details about Anthropic's products, as these may have changed s…
claude-opus-4-6
Claude Developer Platform · in the page
release-notes/system-prompts/claude-opus-4-6
…spreadsheet agent, and Cowork - a desktop tool for non-developers to automate file and task management. Claude does not know other details about Anthropic's products, as these may have changed since…
claude-opus-4-7
Claude Developer Platform · in the page
release-notes/system-prompts/claude-opus-4-7
…: Claude in Chrome - a browsing agent that can interact with websites autonomously, Claude in Excel - a spreadsheet agent, and Claude in Powerpoint - a slides agent. Claude Cowork can use all of these…
claude-sonnet-4
Claude Developer Platform · in the page
release-notes/system-prompts/claude-sonnet-4
…evaluates any theories, claims, and ideas presented to it rather than automatically agreeing or praising them. When presented with dubious, incorrect, ambiguous, or unverifiable theories, claims, or i…
claude-sonnet-4-5
Claude Developer Platform · in the page
release-notes/system-prompts/claude-sonnet-4-5
…spreadsheet agent, and Cowork - a desktop tool for non-developers to automate file and task management**. **Claude does not know other details about Anthropic's products, as these may have changed s…
claude-sonnet-4-6
Claude Developer Platform · in the page
release-notes/system-prompts/claude-sonnet-4-6
…entic coding, and Claude Cowork, a desktop tool for non-developers to automate file and task management. Claude is also accessible via Claude in Chrome (a browsing agent), Claude in Excel (a spreadshe…
develop-tests
Claude Developer Platform · in the page
test-and-evaluate/develop-tests
…ld find it hard to reach an assessment consensus </Accordion> 2. **Automate when possible:** Structure questions to allow for automated grading (for example, multiple-choice, string match, code-gra…
handle-streaming-refusals
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
…**`stop_reason`: `refusal`** checks in your error handling. * **Reset automatically:** Implement automatic context reset when refusals are detected. * **Fall back to another model:** Configure [server…
Use Claude Code with a screen reader
Claude Code CLI · in the page
accessibility
…adapted for screen reader mode: * Screen reader mode doesn't turn on automatically when a screen reader is running. * Claude Code doesn't announce a permission mode change you make with a command, su…
Set up Claude Code for your organization
Claude Code CLI · in the page
admin-setup
…start in instead of the built-in starting permission mode, or remove auto mode. [Switch permission modes](/docs/en/permission-modes.md#switch-permission-modes) lists when the VS Code extension reads…
Escalate hard decisions with the advisor tool
Claude Code CLI · in the page
advisor
…the gateway or its upstream doesn't recognize the advisor tool, see [Automatic retry and error forwarding](/docs/en/llm-gateway-protocol.md#automatic-retry-and-error-forwarding) for how Claude Code r…
How the agent loop works
Claude Code CLI · in the page
agent-sdk/agent-loop
…at power your SDK agents. The Agent SDK lets you embed Claude Code's autonomous agent loop in your own applications. The SDK is a standalone package that gives you programmatic control over tools, pe…
Use Claude Code features in the SDK
Claude Code CLI · in the page
agent-sdk/claude-code-features
…config | Always read | Relocate with `CLAUDE_CONFIG_DIR` in `env` | | Auto memory at `~/.claude/projects/<project>/memory/` | Loaded into the system prompt at session start. The agent writes new memor…
Track cost and usage
Claude Code CLI · in the page
agent-sdk/cost-tracking
…ode/ikqp3_70mqIahteV/images/agent-sdk/message-usage-flow.svg?fit=max\&auto=format\&n=ikqp3_70mqIahteV\&q=85\&s=68497aee338e01cc745323af7aea378e) **1. Each step produces assistant messages** When Cla…
Give Claude custom tools
Claude Code CLI · in the page
agent-sdk/custom-tools
…MCP servers](/docs/en/agent-sdk/mcp.md). * To control which tools run automatically versus requiring approval, see [Configure permissions](/docs/en/agent-sdk/permissions.md).
Rewind file changes with checkpointing
Claude Code CLI · in the page
agent-sdk/file-checkpointing
…le_file_checkpointing=True, permission_mode="acceptEdits", # Auto-accept file edits without prompting extra_args={ "replay-user-messages": None }, # Required to r…
Intercept and control agent behavior with hooks
Claude Code CLI · in the page
agent-sdk/hooks
…stmodelswitch) | No | Yes | The session's model changes, including an automatic fallback | Give Claude model-specific guidance for the new model | | `PermissionRequest` | Yes | Yes | A tool call needs…
Hosting the Agent SDK
Claude Code CLI · in the page
agent-sdk/hosting
…ode/ikqp3_70mqIahteV/images/agent-sdk/hosting-subprocess.svg?fit=max\&auto=format\&n=ikqp3_70mqIahteV\&q=85\&s=9dac857ca9d3b1410c3734900c386004) One agent session maps to one subprocess. Running N co…
Connect to external tools with MCP
Claude Code CLI · in the page
agent-sdk/mcp
…n/mcp.md#plugin-provided-mcp-servers) and starts with `plugin_`. ### Auto-approve with allowedTools Use `allowedTools` to auto-approve specific MCP tools so Claude can use them without a permission…
Modifying system prompts
Claude Code CLI · in the page
agent-sdk/modifying-system-prompts
…o triggered it. Chat UIs, structured-output consumers, and non-coding automation each need a prompt that matches how their output is rendered and reviewed. Unattended coding automation, like a CI job…
Observability with OpenTelemetry
Claude Code CLI · in the page
agent-sdk/observability
…or before your application starts. Every `query()` call picks them up automatically with no code change. This is the recommended approach for production deployments. * **Per-call options:** set the va…
Agent SDK overview
Claude Code CLI · in the page
agent-sdk/overview
…(/docs/en/agent-sdk/mcp.md) | | Permissions | Control which tools run automatically, which need approval | [Permissions](/docs/en/agent-sdk/permissions.md) | | Sessions | Maintain context across excha…
Configure permissions
Claude Code CLI · in the page
agent-sdk/permissions
…e uses tools. Use permission modes and rules to define what's allowed automatically, and the [`canUseTool` callback](/docs/en/agent-sdk/user-input) to handle everything else at runtime. ## How permis…
Plugins in the SDK
Claude Code CLI · in the page
agent-sdk/plugins
…ons. A plugin can include: * **Skills**: capabilities Claude invokes autonomously when relevant. You can also invoke a plugin skill directly with `/plugin-name:skill-name`. * **Agents**: specialized…
Agent SDK reference - Python
Claude Code CLI · in the page
agent-sdk/python
…nge | Multiple exchanges in same context | | **Connection** | Managed automatically | Manual control | | **Streaming Input** | ✅ Supported | ✅ Supported | | **Interrupts** | ❌ Not supported | ✅ Suppor…
Quickstart
Claude Code CLI · in the page
agent-sdk/quickstart
…with the Python or TypeScript Agent SDK to build AI agents that work autonomously Use the Agent SDK to build an AI agent that reads your code, finds bugs, and fixes them, all without manual interven…
Securely deploying AI agents
Claude Code CLI · in the page
agent-sdk/secure-deployment
…uest kernel doesn't directly compromise the host. However, VMs aren't automatically "more secure" than alternatives like gVisor. VM security depends heavily on the hypervisor and device emulation code…
Persist sessions to external storage
Claude Code CLI · in the page
agent-sdk/session-storage
…a session store: * **Multi-host deployments.** Serverless functions, autoscaled workers, and CI runners don't share a filesystem. A shared store lets replicas resume each other's sessions. * **Durabi…
Work with sessions
Claude Code CLI · in the page
agent-sdk/sessions
…ade, every tool result, and every response. The SDK writes it to disk automatically so you can return to it later. Returning to a session means the agent has full context from before: files it alread…
Extend agents with skills
Claude Code CLI · in the page
agent-sdk/skills
…ed by `settingSources` (TypeScript) or `setting_sources` (Python) * **Automatically discovered**: once filesystem settings load, the SDK discovers skill metadata at startup from user and project direc…
Get structured output from agents
Claude Code CLI · in the page
agent-sdk/structured-outputs
…e into a fully-typed object you can use throughout your codebase with autocomplete and type checking. The example below defines a schema for a feature implementation plan with a summary, list of step…
Subagents in the SDK
Claude Code CLI · in the page
agent-sdk/subagents
…r security issues", options=ClaudeAgentOptions( # Auto-approve these tools allowed_tools=["Read", "Grep", "Glob", "Agent"], agents={ "code-r…
Track todos
Claude Code CLI · in the page
agent-sdk/todo-tracking
…ptEdits"` (TypeScript) or `permission_mode="acceptEdits"` (Python) to auto-approve the file edits that work produces. See [Permission modes](/docs/en/agent-sdk/permissions.md#permission-modes) for the…
Scale to many tools with tool search
Claude Code CLI · in the page
agent-sdk/tool-search
…search behind such a gateway unless `ENABLE_TOOL_SEARCH` was `true`, `auto`, or `auto:N`. You control whether and when tool definitions are deferred with the `ENABLE_TOOL_SEARCH` environment variable…
Agent SDK reference - TypeScript
Claude Code CLI · in the page
agent-sdk/typescript
…ummary` | `string` | Display title: custom title, most recent prompt, auto-generated summary, or first prompt | | `lastModified` | `number` | Last modified time in milliseconds since epoch | | `fileSi…
TypeScript SDK V2 session API (removed)
Claude Code CLI · in the page
agent-sdk/typescript-v2-preview
…g-declarations-and-explicit-resource-management) (TypeScript 5.2+) to automatically close the session when the block exits. You can also call `session.close()` manually. ```typescript theme={null} im…
Handle approvals and user input
Claude Code CLI · in the page
agent-sdk/user-input
…s: 1. **Tool needs approval**: Claude wants to use a tool that isn't auto-approved by a [permission rule](/docs/en/agent-sdk/permissions.md) or permission mode. Check `tool_name` for the tool (e.g.,…
Orchestrate teams of Claude Code sessions
Claude Code CLI · in the page
agent-teams
…e/nsvRFSDNfpSU5nT7/images/subagents-vs-agent-teams-light.png?fit=max\&auto=format\&n=nsvRFSDNfpSU5nT7\&q=85\&s=2f8db9b4f3705dd3ab931fbe2d96e42a) Subagents report results back to the main agent. In ag…
Manage multiple agents with agent view
Claude Code CLI · in the page
agent-view
…com/claude-code/HDAmBwgbrZVk0pOt/images/agent-view-light.png?fit=max\&auto=format\&n=HDAmBwgbrZVk0pOt\&q=85\&s=d6905012bee31f3e6b3920b09c05dd02) Use agent view when you have several independent tasks…
Claude Code on Amazon Bedrock
Claude Code CLI · in the page
amazon-bedrock
…aseForModelAccess` IAM permission. Approval extends to child accounts automatically. ### 2. Configure AWS credentials Claude Code uses the default AWS SDK credential chain. If the machine already su…
Track team usage with analytics
Claude Code CLI · in the page
analytics
…red for attribution matching. #### Excluded files Certain files are automatically excluded from analysis because they are auto-generated: * Lock files: package-lock.json, yarn.lock, Cargo.lock, and…
Share session output as artifacts
Claude Code CLI · in the page
artifacts
…com/claude-code/kaHIYYMIYMYPxQg9/images/artifacts-viewer.png?fit=max\&auto=format\&n=kaHIYYMIYMYPxQg9\&q=85\&s=dbfd671cdb0d15f49f808b9e89778fe1) ## When to use an artifact Use an artifact when termi…
Authentication
Claude Code CLI · in the page
authentication
…still-appears-after-an-earlier-sign-in). If the browser doesn't open automatically, press `c` to copy the login URL to your clipboard, then paste it into your browser. If your browser shows a login…
Best practices for Claude Code
Claude Code CLI · in the page
best-practices
…its, Claude Code can read your files, run commands, make changes, and autonomously work through problems while you watch, redirect, or step away entirely. This changes how you work. Instead of writin…
Champion kit
Claude Code CLI · in the page
champion-kit
…t should be avoided. | [Memory](/docs/en/memory.md) | | "Is this just autocomplete?" | Offer a brief demonstration in which Claude explains an unfamiliar file, traces a bug across services, or drafts…