Docs search: prompts / page 4 of 11 / Source Intelligence

Configure your agent Claude Code CLI · in the page agent-sdk/configuration …lve) => { startSecondTurn = resolve; }); async function* turnPrompts(): AsyncGenerator<SDKUserMessage, void> { yield userMessage("Reply with exactly: ready"); await secondTurnReady;…

Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …ive cost across multiple query() calls let totalSpend = 0; const prompts = [ "Read the files in src/ and summarize the architecture", "List all exported functions in src/auth.ts" ];…

Give Claude custom tools Claude Code CLI · in the page agent-sdk/custom-tools …e same way as the weather example. This example sends three different prompts in a loop to show the same tool handling different unit types. For each response, it inspects `AssistantMessage` objects (…

Connect to external tools with MCP Claude Code CLI · in the page agent-sdk/mcp …ons"` does auto-approve MCP tools but also disables most other safety prompts, which is broader than necessary; see [How permissions are evaluated](/docs/en/agent-sdk/permissions#how-permissions-are-e…

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 …-in-agent-sdk-sessions), [Memory](/docs/en/agent-sdk/modifying-system-prompts), [Configuration loading](/docs/en/agent-sdk/claude-code-features) | | Plugins | Package skills, agents, hooks, and MCP se…

Configure permissions Claude Code CLI · in the page agent-sdk/permissions …`dontAsk` mode both cases are denied instead, because that mode never prompts. The MCP annotation requires Claude Code v2.1.199 or later. [claude.ai connector](/docs/en/mcp#organization-controls-…

Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …ts: bool = False forward_subagent_text: bool = False verbatim_prompts: bool = False fork_session: bool = False resume_session_at: str | None = None resume_drops_turn: str | None =…

Quickstart Claude Code CLI · in the page agent-sdk/quickstart …authentication-errors) in the Error reference. </Note> ### Try other prompts Now that your agent is set up, try some different prompts: * `"Add docstrings to all functions in utils.py"` * `"Add typ…

Work with sessions Claude Code CLI · in the page agent-sdk/sessions …on's shape. Session management comes into play when you send multiple prompts that should share context. Within a single `query()` call, the agent already takes as many turns as it needs, and permissi…

Extend agents with skills Claude Code CLI · in the page agent-sdk/skills …configure [MCP servers](/docs/en/agent-sdk/mcp) can also expose [MCP prompts as commands](/docs/en/mcp#use-mcp-prompts-as-commands). ### Dispatch commands by name Send a command by including it in…

Get structured output from agents Claude Code CLI · in the page agent-sdk/structured-outputs …ation your schema requires, make those fields optional. * **Use clear prompts.** Ambiguous prompts make it harder for the agent to know what output to produce. ## Related resources * [JSON Schema do…

Subagents in the SDK Claude Code CLI · in the page agent-sdk/subagents …depends on which [system prompt](/docs/en/agent-sdk/modifying-system-prompts#how-system-prompts-work) you use: * **`claude_code` preset**: when the model is Opus 5, Claude Code adds a line to its sy…

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 …up> For the full set of system prompt options, see [Modifying system prompts](/docs/en/agent-sdk/modifying-system-prompts). ## Limits * **Maximum tools:** 10,000 tools in your catalog * **Search re…

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](/docs/en/a…

Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …d. See [Activate an output style](/docs/en/agent-sdk/modifying-system-prompts#activate-an-output-style) | | `pathToClaudeCodeExecutable` | `string` | Auto-resolved from bundled native binary | Path to…

Handle approvals and user input Claude Code CLI · in the page agent-sdk/user-input …h operation, the callback prints the tool request to the terminal and prompts for y/n approval. <CodeGroup> ```python Python theme={null} import asyncio from claude_agent_sdk import ClaudeAgen…

Orchestrate teams of Claude Code sessions Claude Code CLI · in the page agent-teams …it. The teammate's edits and commands still go through the permission prompts described in [Permissions](#permissions). Once approved, the teammate exits plan mode and begins implementation. ### Talk…

Manage multiple agents with agent view Claude Code CLI · in the page agent-view …put, [as in the main prompt](/docs/en/terminal-config#enter-multiline-prompts) | | `Ctrl+Enter` | Dispatch and attach immediately, in terminals where the `?` overlay lists `ctrl+enter to start and ope…

Claude Code on Amazon Bedrock Claude Code CLI · in the page amazon-bedrock …u-type); type it in full. </Step> <Step title="Follow the wizard prompts"> Choose how you authenticate to AWS: an AWS profile detected from your `~/.aws` directory, an Amazon Bedrock API key,…

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 …ers. When login completes, the terminal shows `Login successful` and prompts you to press `Enter` to continue. You can authenticate with any of these account types: * **Claude Pro or Max subscripti…

Configure auto mode Claude Code CLI · in the page auto-mode-config …ode CLI subcommands. [Auto mode](/docs/en/permission-modes#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 …, skip the plan. </Callout> *** ## Provide specific context in your prompts <Tip> The more precise your instructions, the fewer corrections you'll need. </Tip> Claude can infer intent, but it ca…

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 …ow states the limit and what frees space * Improved Bash permission prompts to give a shorter reason when part of a command can't be checked before it runs * Self-hosted runner: Improved the built…

Push events into a running session with channels Claude Code CLI · in the page channels ….db` is protected by macOS. The first time the server reads it, macOS prompts for access: click **Allow**. The prompt names whichever app launched Bun, such as Terminal, iTerm, or your IDE. I…

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…

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…

Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry Claude Code CLI · in the page claude-apps-gateway …s` expiry. When a refresh fails after IdP deprovisioning, Claude Code prompts the developer to log in again. ### Set the gateway URL Three keys go in the per-OS [managed settings file](/docs/en/mana…

Claude apps gateway configuration Claude Code CLI · in the page claude-apps-gateway-config …oesn't support guardrail input tags. It adds no guard content tags to prompts, so a guardrail filter that Amazon Bedrock applies only to tagged input doesn't run on traffic through the gateway. For wh…

Use Claude Code in the cloud Claude Code CLI · in the page claude-code-on-the-web …e | Your working directory must have no uncommitted changes. Teleport prompts you to stash changes if needed. | | Correct repository | You must run `--teleport` from a checkout of the same repository,…

Explore the .claude directory Claude Code CLI · in the page claude-directory …: 'folder', color: '#D4A843', oneLiner: 'Reusable prompts you or Claude invoke by name', when: <>Invoked with <C>/skill-name</C> or when Claude matches the task to a skil…

Let Claude coordinate ongoing work with Projects Claude Code CLI · in the page claude-projects …roval Threads run in [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) when the thread's model supports it, so most tool calls run without asking you. When a thread needs your a…

claude-tag Claude Code CLI · in the page claude-tag …center; } .dark .dropdown-icon { background-color: #ffffff80; } #prompts-container { grid-template-columns: repeat(1, minmax(0, 1fr)); gap: 2rem; } .dropdown-item { padding: 0.25rem 0.5rem…

CLI reference Claude Code CLI · in the page cli-reference …| Print the built-in [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) classifier rules as JSON. Use `claude auto-mode config` to see your effective config with settings applied…

Code Review Claude Code CLI · in the page code-review …/Step> <Step title="Install the Claude GitHub App"> Follow the prompts to install the Claude GitHub App: pick the GitHub organization that owns the repositories you want reviewed, choose which…

Commands Claude Code CLI · in the page commands …`prompt-audit` to flag instructions written for older models in your prompts, skills, and tool descriptions and propose fixes as a diff. Run `cost-optimize` to profile where your project's Claude API…

Common workflows Claude Code CLI · in the page common-workflows …inue` restore unexpired fixed-interval loops. | <Tip> When writing prompts for scheduled tasks, be explicit about what success looks like and what to do with results. The task runs autonomously, so…

Communications kit Claude Code CLI · in the page communications-kit …our Team or Enterprise plan, Anthropic does not use your code or prompts to train its models. Details: https://code.claude.com/docs/en/data-usage https://code.claude.com/docs/en/…

Let Claude use your computer from the CLI Claude Code CLI · in the page computer-use …m screenshots**: Claude never sees your terminal window, so on-screen prompts in your session can't feed back into the model. * **Global escape**: the `Esc` key aborts computer use from anywhere, and…

Explore the context window Claude Code CLI · in the page context-window …e sees.', tip: 'File reads dominate context usage. Be specific in prompts ("fix the bug in auth.ts") so Claude reads fewer files. For research-heavy tasks, use a subagent.', link: null }, {…

Manage costs effectively Claude Code CLI · in the page costs …s (412 total)`. When [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) is available to the session and your recent sessions mostly ran without it, the report can also include an…

Message your other Claude Code sessions Claude Code CLI · in the page cross-session-messaging …stead. On the receiving side, the [receiving session's own permission prompts and rules still apply](#how-a-session-treats-an-incoming-message) to anything the message asks for. ### Get a notice when…

Data usage Claude Code CLI · in the page data-usage …ng policies: Anthropic does not train generative models using code or prompts sent to Claude Code under commercial terms, unless the customer has chosen to provide their data to us for model improveme…

Debug your configuration Claude Code CLI · in the page debug-your-config …ixes | | `/debug [issue]` | Enables debug logging for the session and prompts Claude to diagnose using the log output and settings paths | | `/status` | Active settings sources, including whether mana…

Launch sessions from links Claude Code CLI · in the page deep-links …ernal link` and stays visible until you send or clear the prompt. For prompts over 1,000 characters, the warning includes the character count and tells you to scroll and review the full text before pr…