1,040 pages for comm.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
mitigate-jailbreaks
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks
…iolate Anthropic’s [Terms of Service](https://www.anthropic.com/legal/commercial-terms) or [Usage Policy](https://www.anthropic.com/legal/aup). These attacks fall into two categories with different t…
Use Claude Code with a screen reader
Claude Code CLI · in the page
accessibility
…You can also pick one with [`/theme`](https://code.claude.com/docs/en/commands#all-commands). | | [`preferredNotifChannel`](https://code.claude.com/docs/en/settings-reference#preferrednotifchannel) |…
Set up Claude Code for your organization
Claude Code CLI · in the page
admin-setup
…nt (MDM) system, or a file on disk. The settings control which tools, commands, servers, and network destinations Claude can reach. This page walks through the deployment decisions in order. Each row…
Escalate hard decisions with the advisor tool
Claude Code CLI · in the page
advisor
…typically stronger model at key moments during a task, such as before committing to an approach, when stuck on a recurring error, or before declaring a task complete. The advisor receives the full con…
How the agent loop works
Claude Code CLI · in the page
agent-sdk/agent-loop
…[`AssistantMessage`](#message-types) with the tool call, executes the command, then yields a [`UserMessage`](#message-types) with the output (three failures). 2. **Turn 2:** Claude calls `Read` on `au…
Use Claude Code features in the SDK
Claude Code CLI · in the page
agent-sdk/claude-code-features
…d local settings, CLAUDE.md files, and `.claude/` skills, agents, and commands. To run without these, pass `settingSources: []`, which limits the agent to what you configure programmatically. Managed…
Configure your agent
Claude Code CLI · in the page
agent-sdk/configuration
…e passes. In either language, the option accepts a single model or a comma-separated list of backups. For the order and the chain cap, see [Fallback model chains](https://code.claude.com/docs/en/mode…
Track cost and usage
Claude Code CLI · in the page
agent-sdk/cost-tracking
…running totals start over each time your app sends one of those three commands, and inside a `query()` call nothing else resets them. Three results matter for your accounting: * **The `/clear` turn's…
Examples
Claude Code CLI · in the page
agent-sdk/examples
…t or a merchant agent with the Python SDK, start from the [Claude for commerce reference implementation](https://platform.claude.com/docs/en/about-claude/use-case-guides/commerce-agents). ## Work thr…
Rewind file changes with checkpointing
Claude Code CLI · in the page
agent-sdk/file-checkpointing
…RNING] > > `rewindFiles()` doesn't undo what `sed -i` or another Bash command did to a file, unless a tool such as Write or Edit had modified that file in the main conversation. [Subagent](https://cod…
Intercept and control agent behavior with hooks
Claude Code CLI · in the page
agent-sdk/hooks
…ck dangerous operations** before they execute, like destructive shell commands or unauthorized file access * **Log and audit** tool calls for compliance, debugging, or analytics * **Transform inputs a…
Connect to external tools with MCP
Claude Code CLI · in the page
agent-sdk/mcp
…project", options: { mcpServers: { filesystem: { command: "npx", args: ["-y", "@modelcontextprotocol/server-filesystem", "/Users/me/projects"] } }, allowedTo…
Migrate to Claude Agent SDK
Claude Code CLI · in the page
agent-sdk/migration-guide
…ngs.json`, `.claude/settings.local.json`, CLAUDE.md files, and custom commands. To run isolated from filesystem settings, pass `settingSources: []`, or `setting_sources=[]` in Python. See [Control fi…
Modifying system prompts
Claude Code CLI · in the page
agent-sdk/modifying-system-prompts
…/output-styles/` in your repository for a project-level style you can commit and share with your team. A custom output style leaves the `claude_code` preset's software engineering instructions out an…
Observability with OpenTelemetry
Claude Code CLI · in the page
agent-sdk/observability
…he SDK The Agent SDK runs the Claude Code CLI as a child process and communicates with it over a local pipe. The CLI has OpenTelemetry instrumentation built in: it records spans around each model req…
Agent SDK overview
Claude Code CLI · in the page
agent-sdk/overview
…task by planning its own steps and calling tools that read files, run commands, or edit code. The Agent SDK gives you the same tools, [agent loop](https://code.claude.com/docs/en/agent-sdk/agent-loop.…
Configure permissions
Claude Code CLI · in the page
agent-sdk/permissions
…lUse` hook that returns `allow` also can't approve an `rm` or `rmdir` command whose target Claude Code recognizes as a [critical path](https://code.claude.com/docs/en/permission-modes.md#critical-path…
Plugins in the SDK
Claude Code CLI · in the page
agent-sdk/plugins
…ath: "/absolute/path/to/another-plugin" } ] } })) { // Plugin commands, agents, and other features are now available } ``` ```python Python theme={null} import asyncio from claude_agent_sdk i…
Agent SDK reference - Python
Claude Code CLI · in the page
agent-sdk/python
…| | `transport` | `Transport \| None` | Optional custom transport for communicating with the CLI process | #### Returns Returns an `AsyncIterator[Message]` that yields messages from the conversation…
Quickstart
Claude Code CLI · in the page
agent-sdk/quickstart
…://tsx.hirok.io) runs TypeScript files directly. If your project uses CommonJS, name your agent script `agent.mts` instead of `agent.ts`. The `.mts` extension makes tsx treat the file as an ES module,…
Securely deploying AI agents
Claude Code CLI · in the page
agent-sdk/secure-deployment
…features Claude Code includes several security features that address common concerns. See the [security documentation](https://code.claude.com/docs/en/security.md) for full details. * **Permissions…
Persist sessions to external storage
Claude Code CLI · in the page
agent-sdk/session-storage
…e resumed on another host running from a matching working directory. Common reasons to use a session store: * **Multi-host deployments.** Serverless functions, autoscaled workers, and CI runners don…
Work with sessions
Claude Code CLI · in the page
agent-sdk/sessions
…agent picks up with full context from wherever the session left off. Common reasons to resume: * **Follow up on a completed task.** The agent already analyzed something; now you want it to act on th…
Extend agents with skills
Claude Code CLI · in the page
agent-sdk/skills
…which skills Claude can invoke in Claude Agent SDK sessions, dispatch commands by name, and author skills your sessions discover Agent Skills extend Claude with specialized capabilities that Claude i…
Stream responses in real-time
Claude Code CLI · in the page
agent-sdk/streaming-output
…platform.claude.com/docs/en/build-with-claude/streaming#event-types). Common event types include: | Event Type | Description | | :- | :- | | `message_start` | Start of a new message | | `content_bloc…
Streaming Input
Claude Code CLI · in the page
agent-sdk/streaming-vs-single-mode
…eries that use session state and resuming ## Streaming Input Mode (Recommended) Streaming input mode is the **preferred** way to use the Claude Agent SDK. It provides full access to the agent's capa…
Get structured output from agents
Claude Code CLI · in the page
agent-sdk/structured-outputs
…d outputs work with multi-step tool use. The agent needs to find TODO comments in the codebase, then look up git blame information for each one. It autonomously decides which tools to use (Grep to sea…
Subagents in the SDK
Claude Code CLI · in the page
agent-sdk/subagents
…anything This guide focuses on the programmatic approach, which is recommended for SDK applications. ## Benefits of using subagents Because subagents are separate agent instances, delegating work t…
Track todos
Claude Code CLI · in the page
agent-sdk/todo-tracking
…ge) (Python) among them, report background tasks such as backgrounded commands and subagents. In the message stream, you see todo activity as `tool_use` blocks in the assistant messages. ### Monitor…
Troubleshoot the Agent SDK
Claude Code CLI · in the page
agent-sdk/troubleshooting
…loops with subagents, `systemMessage` not appearing in output | [Fix common issues](https://code.claude.com/docs/en/agent-sdk/hooks.md#fix-common-issues) on the hooks page | | An agent that works on…
Agent SDK reference - TypeScript
Claude Code CLI · in the page
agent-sdk/typescript
…oject` setting source Claude Code also [loads the directory's skills, commands, and subagents](https://code.claude.com/docs/en/permissions.md#additional-directories-grant-file-access-not-configuration…
Handle approvals and user input
Claude Code CLI · in the page
agent-sdk/user-input
…it needs **permission to use a tool** (like deleting files or running commands), and when it has **clarifying questions** (via the `AskUserQuestion` tool). Both trigger your `canUseTool` callback, whi…
Orchestrate teams of Claude Code sessions
Claude Code CLI · in the page
agent-teams
…ts. Teammates work independently, each in its own context window, and communicate directly with each other. You can also talk to any teammate directly without going through the lead. Before you set u…
Manage multiple agents with agent view
Claude Code CLI · in the page
agent-view
…nted with the color set by [`/color`](https://code.claude.com/docs/en/commands) in that session, including when you [background a session](#from-inside-a-session) with `←` or `/background`. By defaul…
Run agents in parallel
Claude Code CLI · in the page
agents
…atus between themselves. * [`/batch`](https://code.claude.com/docs/en/commands) is a [skill](https://code.claude.com/docs/en/skills.md) that has Claude split one large change into 5 to 30 worktree-iso…
Claude Code on Amazon Bedrock
Claude Code CLI · in the page
amazon-bedrock
…ard. Until `CLAUDE_CODE_USE_BEDROCK=1` is set, Claude Code [hides the command from the command menu](https://code.claude.com/docs/en/commands.md#how-the-command-menu-matches-what-you-type); type it in…
Share session output as artifacts
Claude Code CLI · in the page
artifacts
…once per conversation before changing it, and before each reply to a comment on it | | Claude publishes in a turn that a [session-scoped scheduled task](https://code.claude.com/docs/en/scheduled-task…
Authentication
Claude Code CLI · in the page
authentication
…claude auth login`](https://code.claude.com/docs/en/cli-reference#cli-commands) in your shell before your first session, or you rebuilt a dev container that keeps your credentials in a [volume](https:…
Auto mode classifier request charges
Claude Code CLI · in the page
auto-mode-classifier-billing
…te-prompts-with-auto-mode), a classifier checks actions such as shell commands and network requests before they run. Wherever [server-side checks are on](https://code.claude.com/docs/en/permission-mod…
Configure auto mode
Claude Code CLI · in the page
auto-mode-config
…ow rules, and inspect your effective config with the auto-mode CLI subcommands. [Auto mode](https://code.claude.com/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode) lets Claude Code run…
Best practices for Claude Code
Claude Code CLI · in the page
best-practices
…right thing, without any setup on your part. For example: * To let commands run safely without you approving each one, new terminal and VS Code sessions start in [auto mode](https://code.claude.com…
Champion kit
Claude Code CLI · in the page
champion-kit
…r the questions you will get, a thirty-day playbook, and responses to common concerns. Adoption of a developer tool rarely happens because of a rollout announcement. It happens because someone on the…
Claude Code changelog
Claude Code CLI · in the page
changelog
…t asking in auto and bypass modes, even with managed `allowUnsandboxedCommands: false` or `allowManagedDomainsOnly`, and not to load in `dontAsk` mode * Changed mods' own tool calls (`$.tool.call`, `$…
Push events into a running session with channels
Claude Code CLI · in the page
channels
…ugins/cli-reference.md#reload-plugins) to make the plugin's configure command available. > > **3. Configure your token** > > Run the configure command with the token from BotFather: > > ``` > /telegra…
Channels reference
Claude Code CLI · in the page
channels-reference
…ame machine as Claude Code. Claude Code spawns it as a subprocess and communicates over stdio. Your channel server is the bridge between external systems and the Claude Code session: * **Chat platfor…
Checkpointing
Claude Code CLI · in the page
checkpointing
…#branch-a-session) or `claude --continue --fork-session` instead. ## Common use cases Checkpoints are particularly useful when: * **Exploring alternatives**: try different implementation approaches…
Use Claude Code with Chrome
Claude Code CLI · in the page
chrome
…survives the clear is still running * When you switch sessions with a command like `/resume`, exit Claude Code, or run a `/clear` while work that survives it is still running, Claude Code closes the g…
Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry
Claude Code CLI · in the page
claude-apps-gateway
…security guard, because a trusted gateway can push settings that run commands on developer machines. Put the gateway behind an internal load balancer or VPN and give it a hostname that resolves to pr…
Claude apps gateway configuration
Claude Code CLI · in the page
claude-apps-gateway-config
…start with any key that doesn't meet these conditions. This `openssl` command creates such a key with a self-signed certificate that is valid for one year: ```bash theme={null} openssl req -x509 -new…
Claude apps gateway deployment and operations
Claude Code CLI · in the page
claude-apps-gateway-deploy
…can push settings to users' machines, including hooks that run shell commands. The check helps keep users from accidentally signing in to a malicious gateway on the public internet. Keep your own gat…