1,063 pages for prompt.

reduce-hallucinations Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-hallucinations …sumptions. * **Best-of-N verification:** Run Claude through the same prompt multiple times and compare the outputs. Inconsistencies across outputs could indicate hallucinations. * **Iterative refine… reduce-latency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-latency …latency by choosing a faster model such as Claude Haiku 5.5, trimming prompt and output tokens, and streaming responses. --- Latency refers to the time it takes for the model to process a prompt and… Use Claude Code with a screen reader Claude Code CLI · in the page accessibility …aude Code waits after the confirmation line before it draws the first prompt in screen reader mode. Requires Claude Code v2.1.217 or later. | | [`CLAUDE_AX_PREPARK_MS`](https://code.claude.com/docs/en… Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …cloud provider plans, Anthropic doesn't train models on your code or prompts. Your API provider determines retention and compliance posture. | Topic | What to know | Where to start | | :- | :- | :-… Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …riven rather than rule-based. You can ask for a consultation in your prompt the same way you would request any tool, for example `consult the advisor before you continue`. There is no setting to cap… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …/en/how-claude-code-works.md#the-agentic-loop): Claude evaluates your prompt, calls tools to take action, receives the results, and repeats until the task is complete. This page explains what happens… Use Claude Code features in the SDK Claude Code CLI · in the page agent-sdk/claude-code-features …t asyncio async def main(): async for message in query( prompt="Help me refactor the auth module", options=ClaudeAgentOptions( # "user" loads from ~/.claude/, "projec… Configure your agent Claude Code CLI · in the page agent-sdk/configuration …nthropic-ai/claude-agent-sdk"; for await (const message of query({ prompt: "Summarize the open TODOs in this repo", options: { model: "claude-sonnet-5", allowedTools: ["Read", "Glob", "Gr… Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …sage > Learn how to track token usage, estimate costs, and configure prompt caching with the Claude Agent SDK. The Claude Agent SDK provides detailed token usage information for each interaction wit… Give Claude custom tools Claude Code CLI · in the page agent-sdk/custom-tools …g-convention) in `allowedTools` so the tool runs without a permission prompt. That name is `mcp__{server_name}__{tool_name}`, where `{server_name}` is the key you give the server in `mcpServers`. If t… Rewind file changes with checkpointing Claude Code CLI · in the page agent-sdk/file-checkpointing …thon) when you need to restore. The examples in this section use the prompt "Refactor the authentication module". Run them in a project that contains an authentication module, or change the prompt to… Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …the operation return {}; }; for await (const message of query({ prompt: "Create a .env file with the standard local development database configuration", options: { hooks: { // Regist… Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …nthropic-ai/claude-agent-sdk"; for await (const message of query({ prompt: "Summarize the files in this directory", options: { cwd: "/work/session-a" }, })) { console.log(message); } ``` ```py… Connect to external tools with MCP Claude Code CLI · in the page agent-sdk/mcp …nthropic-ai/claude-agent-sdk"; for await (const message of query({ prompt: "Use the docs MCP server to explain what hooks are in Claude Code", options: { mcpServers: { "claude-code-docs… Migrate to Claude Agent SDK Claude Code CLI · in the page agent-sdk/migration-guide …del="claude-opus-4-7", permission_mode="acceptEdits") ``` ### System prompt no longer default **What changed:** The SDK no longer uses Claude Code's system prompt by default. **Migration:** ```typ… Observability with OpenTelemetry Claude Code CLI · in the page agent-sdk/observability …rics for token and cost counters, and emits structured log events for prompts and tool results. The SDK does not produce telemetry of its own. Instead, it passes configuration through to the CLI proce… Agent SDK overview Claude Code CLI · in the page agent-sdk/overview …, [Memory](https://code.claude.com/docs/en/agent-sdk/modifying-system-prompts.md), [Configuration loading](https://code.claude.com/docs/en/agent-sdk/claude-code-features.md) | | Plugins | Package skil… Configure permissions Claude Code CLI · in the page agent-sdk/permissions …Ask` mode both cases are denied instead, because that mode turns each prompt into a denial. The MCP annotation requires Claude Code v2.1.199 or later. [claude.ai connector](https://code.claude.com/do… Plugins in the SDK Claude Code CLI · in the page agent-sdk/plugins …nthropic-ai/claude-agent-sdk"; for await (const message of query({ prompt: "Hello", options: { plugins: [ { type: "local", path: "./my-plugin" }, { type: "local", path: "/absolute… Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …sdk/sessions.md). ```python theme={null} async def query( *, prompt: str | AsyncIterable[dict[str, Any]], options: ClaudeAgentOptions | None = None, transport: Transport | None = None… Quickstart Claude Code CLI · in the page agent-sdk/quickstart …eams messages as Claude works async for message in query( prompt="Review utils.py for bugs that would cause crashes. Fix any issues you find.", options=ClaudeAgentOptions(… Securely deploying AI agents Claude Code CLI · in the page agent-sdk/secure-deployment …hey process: files, webpages, or user input. This is sometimes called prompt injection. For example, if a repository's README contains unusual instructions, Claude Code might incorporate those into it… Persist sessions to external storage Claude Code CLI · in the page agent-sdk/session-storage …: string | undefined; try { for await (const message of query({ prompt: "List the TypeScript files under src/", options: { sessionStore: store }, })) { if (message.type === "result") {… Work with sessions Claude Code CLI · in the page agent-sdk/sessions …history the SDK accumulates while your agent works. It contains your prompt, every tool call the agent made, every tool result, and every response. The SDK writes it to disk automatically so you can… Extend agents with skills Claude Code CLI · in the page agent-sdk/skills …er-invoked**: you dispatch a skill directly by sending `/<name>` in a prompt. See [Commands in Agent SDK sessions](#commands-in-agent-sdk-sessions) * **Scoped via the `skills` option**: discovered ski… Stream responses in real-time Claude Code CLI · in the page agent-sdk/streaming-output …allowed_tools=["Bash", "Read"], ) async for message in query(prompt="List the files in my project", options=options): if isinstance(message, StreamEvent): event = message.… Streaming Input Claude Code CLI · in the page agent-sdk/streaming-vs-single-mode …// Process streaming responses for await (const message of query({ prompt: generateMessages(), options: { maxTurns: 10, allowedTools: ["Read", "Grep"] } })) { if (message.type === "re… Get structured output from agents Claude Code CLI · in the page agent-sdk/structured-outputs …e structure you need, and the SDK validates the output against it, re-prompting on mismatch. If validation does not succeed within the retry limit, the result is an error instead of structured data; s… Subagents in the SDK Claude Code CLI · in the page agent-sdk/subagents …and apply specialized instructions without adding to the main agent's prompt. ## Overview You can create subagents in three ways: * **Programmatically**: use the `agents` parameter in your `query()… Track todos Claude Code CLI · in the page agent-sdk/todo-tracking …rmission setup and exit behavior: * **Permission mode**: the example prompts ask Claude to do real work on a project, so each example sets `permissionMode: "acceptEdits"` (TypeScript) or `permission_… Scale to many tools with tool search Claude Code CLI · in the page agent-sdk/tool-search …i/claude-agent-sdk"; try { for await (const message of query({ prompt: "Find and run the appropriate database query", options: { mcpServers: { "enterprise-tools": {… Troubleshoot the Agent SDK Claude Code CLI · in the page agent-sdk/troubleshooting …t applied, session hooks not available in Python, subagent permission prompts multiplying, recursive hook loops with subagents, `systemMessage` not appearing in output | [Fix common issues](https://co… Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …h = extractFromBunfs(binPath); for await (const message of query({ prompt: "Hello", options: { pathToClaudeCodeExecutable: cliPath }, })) { console.log(message); } ``` `extractFromBunfs()` cop… TypeScript SDK V2 session API (removed) Claude Code CLI · in the page agent-sdk/typescript-v2-preview …unstable_v2_createSession`, `unstable_v2_resumeSession`, `unstable_v2_prompt`, and the `SDKSession` and `SDKSessionOptions` types. > > To migrate, use the [`query()` API](https://code.claude.com/docs/… Handle approvals and user input Claude Code CLI · in the page agent-sdk/user-input …async def handle_tool_request(tool_name, input_data, context): # Prompt user and return allow or deny ... options = ClaudeAgentOptions(can_use_tool=handle_tool_request) ``` ```typescript T… Orchestrate teams of Claude Code sessions Claude Code CLI · in the page agent-teams …tural language. Claude spawns them and coordinates work based on your prompt. This example works well because the three roles are independent and can explore the problem without waiting on each other… Manage multiple agents with agent view Claude Code CLI · in the page agent-view …the next time you open agent view. **2. Dispatch a session** Type a prompt describing a task and press `Enter`. A new background session starts on that task and appears as a row showing whether it's… Claude Code on Amazon Bedrock Claude Code CLI · in the page amazon-bedrock …t Claude Code and choose Amazon Bedrock** Run `claude`. At the login prompt, select **3rd-party platform**, then **Amazon Bedrock**. If you're already signed in and see the chat prompt instead, run `… Track team usage with analytics Claude Code CLI · in the page analytics …ou find team members with high Claude Code adoption who can: * Share prompting techniques and workflows with the team * Provide feedback on what's working well * Help onboard new users #### Access d… Share session output as artifacts Claude Code CLI · in the page artifacts …e someone opens it See [What you can build](#what-you-can-build) for prompts that match these, and [Pull live data with MCP connectors](#pull-live-data-with-mcp-connectors) for the connector-backed b… Authentication Claude Code CLI · in the page authentication …st launch, except in cases such as these, where it can skip the login prompt: * **API key**: you've set the `ANTHROPIC_API_KEY` environment variable and you approve the key when Claude Code asks whet… Auto mode classifier request charges Claude Code CLI · in the page auto-mode-classifier-billing …o mode](https://code.claude.com/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode), a classifier checks actions such as shell commands and network requests before they run. Wherever [server… Configure auto mode Claude Code CLI · in the page auto-mode-config …o mode](https://code.claude.com/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode) lets Claude Code run without routine permission prompts by routing tool calls through a classifier that bl… Best practices for Claude Code Claude Code CLI · in the page best-practices …Claude Code is built in a way that, in most cases, your first plain prompt in a fresh session already does the right thing, without any setup on your part. For example: * To let commands run safel… Champion kit Claude Code CLI · in the page champion-kit …| Why it matters | | - | - | - | | Share what you discover | Post the prompts, screenshots, and small wins from your own work in the places your team already reads, such as an engineering channel, a s… Claude Code changelog Claude Code CLI · in the page changelog …ll command to the background after 3 minutes on all providers, so the prompt cache doesn't expire while it runs * Changed subagent progress summaries on Bedrock, Vertex, Foundry, or with telemetry off… Push events into a running session with channels Claude Code CLI · in the page channels …ude Code by running `claude` in your terminal, then enter this at its prompt: > > ``` > /plugin install telegram@claude-plugins-official > ``` > > If the install fails, match the message Claude Code r… Channels reference Claude Code CLI · in the page channels-reference …annel with a trusted sender path can also opt in to [relay permission prompts](#relay-permission-prompts) so you can approve or deny tool use remotely. This page covers: * [Overview](#overview): how… Checkpointing Claude Code CLI · in the page checkpointing …eckpointing automatically captures the state of your code before each prompt you send that starts a turn. ### Automatic tracking Claude Code tracks all changes made by its file editing tools: * Eve… Use Claude Code with Chrome Claude Code CLI · in the page chrome …laude uses. When a browser action starts before you've chosen, Claude prompts you to pick one. To switch browsers later, run `/chrome` and select **Select browser…**. Claude keeps using your choice ev…