1,595 pages for form.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
overview
Claude Developer Platform · in the page
resources/overview
--- title: Model cards url: https://platform.claude.com/docs/en/resources/overview description: Model cards with detailed documentation for Claude models. --- <CardGroup cols={3}> <Card title="Clau…
develop-tests
Claude Developer Platform · in the page
test-and-evaluate/develop-tests
…title: Define success criteria and build evaluations url: https://platform.claude.com/docs/en/test-and-evaluate/develop-tests description: Define measurable success criteria for your LLM application a…
handle-streaming-refusals
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
--- title: Handle streaming refusals url: https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/handle-streaming-refusals description: Detect and handle refusal stop reasons in s…
increase-consistency
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/increase-consistency
--- title: Increase output consistency url: https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/increase-consistency description: Make Claude's outputs more consistent by speci…
mitigate-jailbreaks
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks
--- title: Mitigate jailbreaks and prompt injections url: https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks description: Defend your application against j…
reduce-hallucinations
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/reduce-hallucinations
--- title: Reduce hallucinations url: https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/reduce-hallucinations description: Minimize hallucinations in Claude's outputs by allo…
reduce-latency
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/reduce-latency
--- title: Reducing latency url: https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/reduce-latency description: Reduce Claude's response latency by choosing a faster model suc…
reduce-prompt-leak
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/reduce-prompt-leak
--- title: Reduce prompt leak url: https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/reduce-prompt-leak description: Reduce the risk of prompt leaks by separating context fro…
Set up Claude Code for your organization
Claude Code CLI · in the page
admin-setup
…code.claude.com/docs/en/amazon-bedrock.md), [Google Cloud's Agent Platform](https://code.claude.com/docs/en/google-vertex-ai.md), [Microsoft Foundry](https://code.claude.com/docs/en/microsoft-foundry.…
Escalate hard decisions with the advisor tool
Claude Code CLI · in the page
advisor
…the Anthropic API. It is not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry. Behavior, pricing, and availability may change. The advisor too…
How the agent loop works
Claude Code CLI · in the page
agent-sdk/agent-loop
…ude-code/ikqp3_70mqIahteV/images/agent-loop-diagram.svg?fit=max\&auto=format\&n=ikqp3_70mqIahteV\&q=85\&s=1c6e8f28d80dba14a7287419656f1237) 1. **Receive prompt.** Claude receives your prompt, along w…
Use Claude Code features in the SDK
Claude Code CLI · in the page
agent-sdk/claude-code-features
…~/.claude.json` config are read regardless of this option. For more information, see [What settingSources does not control](#what-settingsources-does-not-control). ## Control filesystem settings with…
Configure your agent
Claude Code CLI · in the page
agent-sdk/configuration
…d tool, the permission mode decides whether the call runs. For more information, see [Allow and deny rules](https://code.claude.com/docs/en/agent-sdk/permissions.md#allow-and-deny-rules). ## Load set…
Track cost and usage
Claude Code CLI · in the page
agent-sdk/cost-tracking
…aude Agent SDK. The Claude Agent SDK provides detailed token usage information for each interaction with Claude. This guide explains how to properly track usage and understand cost reporting, especia…
Give Claude custom tools
Claude Code CLI · in the page
agent-sdk/custom-tools
…s MCP server so Claude can call your functions, hit your APIs, and perform domain-specific operations. Custom tools extend the Agent SDK by letting you define your own functions that Claude can call…
Examples
Claude Code CLI · in the page
agent-sdk/examples
…s) repo, and Python recipes live in the [Claude Cookbook](https://platform.claude.com/cookbook). ## Run a minimal agent first If you haven't built anything with the SDK yet, start with one of these…
Rewind file changes with checkpointing
Claude Code CLI · in the page
agent-sdk/file-checkpointing
…`, which approves the agent's file edits without a prompt. For more information, see [Permission modes](https://code.claude.com/docs/en/agent-sdk/permissions.md#permission-modes). **2. Capture checkp…
Intercept and control agent behavior with hooks
Claude Code CLI · in the page
agent-sdk/hooks
…d audit** tool calls for compliance, debugging, or analytics * **Transform inputs and outputs** to sanitize data, inject credentials, or redirect file paths * **Require human approval** for sensitive…
Hosting the Agent SDK
Claude Code CLI · in the page
agent-sdk/hosting
…elf on your own infrastructure, consider [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) instead. Anthropic hosts the agent loop, and your application sends events and re…
Connect to external tools with MCP
Claude Code CLI · in the page
agent-sdk/mcp
…) ``` The agent connects to the documentation server, searches for information about hooks, and returns the results. ## Add an MCP server You can configure MCP servers in code when calling `query()…
Migrate to Claude Agent SDK
Claude Code CLI · in the page
agent-sdk/migration-guide
…nts SDK instead? The [OpenAI Agents SDK migration recipe](https://platform.claude.com/cookbook/claude-agent-sdk-04-migrating-from-openai-agents-sdk) maps each primitive onto the Claude Agent SDK throu…
Modifying system prompts
Claude Code CLI · in the page
agent-sdk/modifying-system-prompts
…nd of tool, plus product-specific rules like coding standards, output format, or domain context | `claude_code` preset with `append` | Everything above, with your instructions added after the preset.…
Observability with OpenTelemetry
Claude Code CLI · in the page
agent-sdk/observability
…the OpenTelemetry Protocol (OTLP), whether a hosted observability platform or a self-hosted collector. This guide explains how the SDK emits telemetry, how to configure the export, and how to tag and…
Agent SDK overview
Claude Code CLI · in the page
agent-sdk/overview
…Claude API directly from your own code | [**Client SDK**](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) | Direct access to the Claude API from any of the client SDK languages. You w…
Configure permissions
Claude Code CLI · in the page
agent-sdk/permissions
…/jYgs7qigNjO1Badj/images/agent-sdk/permissions-flow.svg?fit=max\&auto=format\&n=jYgs7qigNjO1Badj\&q=85\&s=c771ad9085b1277d3708027a49c744bc) If you pass a `canUseTool` callback in a configuration wher…
Plugins in the SDK
Claude Code CLI · in the page
agent-sdk/plugins
…external tool integrations via Model Context Protocol For complete information on plugin structure and how to create plugins, see [Plugins](https://code.claude.com/docs/en/plugins/overview.md). ## L…
Agent SDK reference - Python
Claude Code CLI · in the page
agent-sdk/python
…{"text": str, "count": int, "enabled": bool} ``` 2. **JSON Schema format** (for complex validation): ```python theme={null} { "type": "object", "properties": { "text…
Quickstart
Claude Code CLI · in the page
agent-sdk/quickstart
…nthropic account**. If you don't have one, [sign up here](https://platform.claude.com/). ## Setup **1. Create a project folder** Create a new directory for this quickstart: ```bash theme={null} mk…
Securely deploying AI agents
Claude Code CLI · in the page
agent-sdk/secure-deployment
…els are designed to resist this; see the [model overview](https://platform.claude.com/docs/en/about-claude/models/overview) and the system card for the model you deploy for evaluation details. Defens…
Persist sessions to external storage
Claude Code CLI · in the page
agent-sdk/session-storage
…})) { // ... } ``` ### Validate your adapter Both SDKs ship a conformance suite that asserts the behavioral contract `append`, `load`, and the optional methods must satisfy. Tests for optional me…
Work with sessions
Claude Code CLI · in the page
agent-sdk/sessions
…ll context from before: files it already read, analysis it already performed, decisions it already made. You can ask a follow-up question, recover from an interruption, or branch off to try a differen…
Extend agents with skills
Claude Code CLI · in the page
agent-sdk/skills
…in Agent SDK sessions](#commands-in-agent-sdk-sessions). For more information about skills, including benefits, architecture, and authoring guidelines, see the [Agent Skills overview](https://platfo…
Stream responses in real-time
Claude Code CLI · in the page
agent-sdk/streaming-output
…ld contains the raw streaming event from the [Claude API](https://platform.claude.com/docs/en/build-with-claude/streaming#event-types). Common event types include: | Event Type | Description | | :- |…
Get structured output from agents
Claude Code CLI · in the page
agent-sdk/structured-outputs
…y typed objects back. ## Why structured outputs? Agents return free-form text by default, which works for chat but not when you need to use the output programmatically. Structured outputs give you t…
Subagents in the SDK
Claude Code CLI · in the page
agent-sdk/subagents
…pt="""You are a code review specialist with expertise in security, performance, and best practices. When reviewing code: - Identify security vulnerabilities - Check for performance issues - Verify ad…
Track todos
Claude Code CLI · in the page
agent-sdk/todo-tracking
…s before execution, mapping `id` or `task_id` to `taskId` and `active_form` to `activeForm`, but that repair is not reflected in the stream. Read `TaskUpdate` input fields defensively, as both example…
Scale to many tools with tool search
Claude Code CLI · in the page
agent-sdk/tool-search
…he underlying API mechanism, see [Tool search in the API](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool). > [!NOTE] > > Tool search isn't supported on Microsoft Found…
Troubleshoot the Agent SDK
Claude Code CLI · in the page
agent-sdk/troubleshooting
…locations, and the message includes install instructions for your platform. To fix it: * Install Claude Code if it isn't installed. See [Install Claude Code](https://code.claude.com/docs/en/setup.md…
Agent SDK reference - TypeScript
Claude Code CLI · in the page
agent-sdk/typescript
…[!NOTE] > > The SDK bundles a native Claude Code binary for your platform as an optional dependency such as `@anthropic-ai/claude-agent-sdk-darwin-arm64`. Most installs need no separate Claude Code i…
TypeScript SDK V2 session API (removed)
Claude Code CLI · in the page
agent-sdk/typescript-v2-preview
…[!NOTE] > > The SDK bundles a native Claude Code binary for your platform as an optional dependency, so most installs need no separate Claude Code install. See the [quickstart's install note](https:/…
Handle approvals and user input
Claude Code CLI · in the page
agent-sdk/user-input
…en/agent-sdk/typescript.md#tool-input-types). You can display this information to the user so they can decide whether to allow or reject the action, then return the appropriate response. The followi…
Orchestrate teams of Claude Code sessions
Claude Code CLI · in the page
agent-teams
…RFSDNfpSU5nT7/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 agent t…
Manage multiple agents with agent view
Claude Code CLI · in the page
agent-view
…laude-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 Clau…
Claude Code on Amazon Bedrock
Claude Code CLI · in the page
amazon-bedrock
…the Model catalog, select an Anthropic model, and submit the use case form. Access is granted immediately after submission. See [Submit use case details](#1-submit-use-case-details) for AWS Organizati…
Track team usage with analytics
Claude Code CLI · in the page
analytics
…ss-analytics-for-team-and-enterprise) | | API (Claude Console) | [platform.claude.com/claude-code](https://platform.claude.com/claude-code) | Usage metrics, spend tracking, team insights | [Details](#…
Share session output as artifacts
Claude Code CLI · in the page
artifacts
…laude-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 terminal t…
Authentication
Claude Code CLI · in the page
authentication
…le, or a cloud provider like Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. ## Log in to Claude Code After [installing Claude Code](https://code.claude.com/docs/en/setup.md#ins…
Auto mode classifier request charges
Claude Code CLI · in the page
auto-mode-classifier-billing
…/en/permission-modes.md#server-side-classifier-review), the server performs those checks as part of the session's own model requests, at no charge. This notice means the server's checks aren't reachin…
Configure auto mode
Claude Code CLI · in the page
auto-mode-config
…all users on every provider, including the Anthropic API, [Claude Platform on AWS](https://code.claude.com/docs/en/claude-platform-on-aws.md), Amazon Bedrock, Google Cloud's Agent Platform, Microsoft…
Best practices for Claude Code
Claude Code CLI · in the page
best-practices
…ediscover the same fact at the start of every session. It's missing information it can't get from reading the repo. See [Tell Claude what it can't see](#tell-claude-what-it-cant-see). * Claude said it…