757 pages for task.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
claude-sonnet-4
Claude Developer Platform · in the page
release-notes/system-prompts/claude-sonnet-4
…tool for agentic coding. Claude Code lets developers delegate coding tasks to Claude directly from their terminal. If the person asks Claude about Claude Code, Claude should point them to check the d…
claude-sonnet-4-5
Claude Developer Platform · in the page
release-notes/system-prompts/claude-sonnet-4-5
…ool for agentic coding. **Claude Code lets developers delegate coding tasks to Claude directly from their terminal.** Claude is accessible via **beta products Claude in Chrome - a browsing agent, Clau…
claude-sonnet-4-6
Claude Developer Platform · in the page
release-notes/system-prompts/claude-sonnet-4-6
…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 spreadsheet agent), and Cla…
claude-sonnet-5
Claude Developer Platform · in the page
release-notes/system-prompts/claude-sonnet-5
…ude Code, an agentic coding tool that lets developers delegate coding tasks to Claude from the command line, desktop app, or mobile app, and through Claude Cowork, an agentic knowledge-work desktop ap…
claude-sonnet-5-5
Claude Developer Platform · in the page
release-notes/system-prompts/claude-sonnet-5-5
…ude Code, an agentic coding tool that lets developers delegate coding tasks to Claude from the command line, desktop app, or mobile app, and through Claude Cowork, an agentic knowledge-work desktop ap…
develop-tests
Claude Developer Platform · in the page
test-and-evaluate/develop-tests
…etrics and measurement methods"> **Quantitative metrics:** * Task-specific: F1 score, BLEU score, perplexity * Generic: Accuracy, precision, recall * Operational: Response time (ms),…
increase-consistency
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/increase-consistency
…ey_issues" (list), and "action_items" (list of dicts with "team" and "task"). "I've been a loyal user for 3 years, but the recent UI update is a disaster. Finding basic features is now a scavenger…
reduce-hallucinations
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/reduce-hallucinations
…``` </Accordion> * **Use direct quotes for factual grounding:** For tasks involving long documents (>20k tokens), ask Claude to extract word-for-word quotes first before performing its task. This gr…
reduce-latency
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/reduce-latency
…utput as it arrives, updating your user interface or performing other tasks in parallel. Visit [Streaming messages](https://platform.claude.com/docs/en/build-with-claude/streaming) to learn about how…
reduce-prompt-leak
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/reduce-prompt-leak
…, filtering Claude's outputs, and auditing prompts, without degrading task performance. --- Prompt leaks can expose sensitive information that you expect to be "hidden" in your prompt. Although no me…
Set up Claude Code for your organization
Claude Code CLI · in the page
admin-setup
…Cloud sessions](/docs/en/claude-code-on-the-web.md), [cloud scheduled tasks](/docs/en/routines.md), [Code Review](/docs/en/code-review.md), [Remote Control](/docs/en/remote-control.md), and the [Chrom…
Escalate hard decisions with the advisor tool
Claude Code CLI · in the page
advisor
…a stronger advisor model that Claude consults at key moments during a task. > [!NOTE] > > The advisor tool is experimental and requires the Anthropic API. It is not available on Amazon Bedrock, Claud…
How the agent loop works
Claude Code CLI · in the page
agent-sdk/agent-loop
…lls tools to take action, receives the results, and repeats until the task is complete. This page explains what happens inside that loop so you can build, debug, and optimize your agents effectively.…
Use Claude Code features in the SDK
Claude Code CLI · in the page
agent-sdk/claude-code-features
…Python, including `SessionStart`, `SessionEnd`, `TeammateIdle`, and `TaskCompleted`. See the [hooks guide](/docs/en/agent-sdk/hooks.md) for the full event compatibility table. For full details on pr…
Track cost and usage
Claude Code CLI · in the page
agent-sdk/cost-tracking
…n, Claude Code waits for them, up to the cap described in [background tasks at exit](/docs/en/headless.md#background-tasks-at-exit), before emitting the result. The result's `total_cost_usd`, `duratio…
Give Claude custom tools
Claude Code CLI · in the page
agent-sdk/custom-tools
…ed `disallowedTools` rules change permission. If you name one of the [task-tracking tools](/docs/en/agent-sdk/todo-tracking.md#model-availability) in `allowedTools`, Claude Code also opts the session…
Intercept and control agent behavior with hooks
Claude Code CLI · in the page
agent-sdk/hooks
…SubagentStart` | Yes | Yes | Subagent initialization | Track parallel task spawning | | `SubagentStop` | Yes | Yes | Subagent completion | Aggregate results from parallel tasks | | `PreCompact` | Yes…
Hosting the Agent SDK
Claude Code CLI · in the page
agent-sdk/hosting
…e cookbook. ### Ephemeral sessions Create a container for each user task and destroy it when the task completes. Best for one-off tasks. The user may still interact with the AI while the task is com…
Connect to external tools with MCP
Claude Code CLI · in the page
agent-sdk/mcp
…configure it on a prompt-submission, tool-use, permission, subagent, task, elicitation, or worktree event. Before v2.1.284, naming a server had no effect on the first-turn wait. ### Set the first-tu…
Migrate to Claude Agent SDK
Claude Code CLI · in the page
agent-sdk/migration-guide
…s the SDK's broader capabilities for building AI agents beyond coding tasks. Migrating from the OpenAI Agents SDK instead? The [OpenAI Agents SDK migration recipe](https://platform.claude.com/cookboo…
Modifying system prompts
Claude Code CLI · in the page
agent-sdk/modifying-system-prompts
…a human is in the loop with access to a full toolset. * **Non-coding tasks**: most of Claude Code's prompt is coding guidance. For research, content, or operations agents, that guidance competes with…
Observability with OpenTelemetry
Claude Code CLI · in the page
agent-sdk/observability
…ionary and passes them through `options.env`. The agent runs a single task, and the CLI exports spans, metrics, and events to the collector at `collector.example.com` while the loop consumes the respo…
Agent SDK overview
Claude Code CLI · in the page
agent-sdk/overview
…Claude Code as a library An agent is an application that completes a task by planning its own steps and calling tools that read files, run commands, or edit code. The Agent SDK gives you the same too…
Configure permissions
Claude Code CLI · in the page
agent-sdk/permissions
…fall through to the callback, even when an allow rule matches. In `dontAsk` mode both cases are denied instead, because that mode never prompts. The MCP annotation requires Claude Code v2.1.199 or lat…
Plugins in the SDK
Claude Code CLI · in the page
agent-sdk/plugins
…in-name:skill-name`. * **Agents**: specialized subagents for specific tasks * **Hooks**: event handlers that respond to tool use and other events * **MCP servers**: external tool integrations via Mode…
Agent SDK reference - Python
Claude Code CLI · in the page
agent-sdk/python
…ue_conversation` or `resume` | ✅ Automatic | | **Use Case** | One-off tasks | Continuous conversations | Use `ClaudeSDKClient` for interactive applications such as chat interfaces, or when the next a…
Quickstart
Claude Code CLI · in the page
agent-sdk/quickstart
…want Claude to do. Claude figures out which tools to use based on the task. 3. **`options`**: configuration for the agent. This example uses `allowedTools` to pre-approve `Read`, `Edit`, and `Glob`,…
Securely deploying AI agents
Claude Code CLI · in the page
agent-sdk/secure-deployment
…restrict the agent to only the capabilities required for its specific task: | Resource | Restriction options | | - | - | | Filesystem | Mount only needed directories, prefer read-only | | Network | R…
Work with sessions
Claude Code CLI · in the page
agent-sdk/sessions
…call). | What you're building | What to use | | :- | :- | | One-shot task: single prompt, no follow-up | Nothing extra. One `query()` call handles it. | | Multi-turn chat in one process | [`ClaudeSDK…
Stream responses in real-time
Claude Code CLI · in the page
agent-sdk/streaming-output
…or chat interfaces that need to show progress during multi-step agent tasks. ```python Python theme={null} from claude_agent_sdk import query, ClaudeAgentOptions, ResultMessage from claude_agent_sdk.…
Get structured output from agents
Claude Code CLI · in the page
agent-sdk/structured-outputs
…k from an agent. The agent can use any tools it needs to complete the task, and you still get validated JSON matching your schema at the end. Define a [JSON Schema](https://json-schema.org/understandi…
Subagents in the SDK
Claude Code CLI · in the page
agent-sdk/subagents
…nts in the SDK > Define and invoke subagents to isolate context, run tasks in parallel, and apply specialized instructions in your Claude Agent SDK applications. Subagents are separate agent instanc…
Track todos
Claude Code CLI · in the page
agent-sdk/todo-tracking
…our application from structured tool calls Claude Code provides the [task-tracking tools](/docs/en/tools-reference.md#task-tool-availability) by default only on the models listed under [Model availab…
Scale to many tools with tool search
Claude Code CLI · in the page
agent-sdk/tool-search
…a summary of available tools and searches for relevant ones when the task requires a capability not already loaded. Up to five of the most relevant tools are loaded into context by default, where the…
Agent SDK reference - TypeScript
Claude Code CLI · in the page
agent-sdk/typescript
…erate one-line progress summaries for subagents and forward them on [`task_progress`](#sdktaskprogressmessage) events via the `summary` field. Applies to foreground and background subagents | | `allow…
Handle approvals and user input
Claude Code CLI · in the page
agent-sdk/user-input
…to users, then return their decisions to the SDK. While working on a task, Claude sometimes needs to check in with users. It might need permission before deleting files, or need to ask which database…
Orchestrate teams of Claude Code sessions
Claude Code CLI · in the page
agent-teams
…ultiple Claude Code instances working together as a team, with shared tasks, inter-agent messaging, and centralized management. > [!WARNING] > > Agent teams are experimental and disabled by default.…
Manage multiple agents with agent view
Claude Code CLI · in the page
agent-view
…question, and a time. At the bottom are an input for describing a new task and a row of keyboard hints.](https://mintcdn.com/claude-code/HDAmBwgbrZVk0pOt/images/agent-view-light.png?fit=max\&auto=form…
Run agents in parallel
Claude Code CLI · in the page
agents
…ents in parallel > Compare the ways Claude Code can take on multiple tasks at once: subagents, agent view, agent teams, dynamic workflows, and projects. Claude Code has five ways to work on several…
Claude Code on Amazon Bedrock
Claude Code CLI · in the page
amazon-bedrock
…s to that chain, such as an Amazon EC2 instance profile or Amazon ECS task credentials, skip to [step 3](#3-configure-claude-code). AWS [warns against using an IAM user's access keys](https://docs.aw…
Share session output as artifacts
Claude Code CLI · in the page
artifacts
…e by side * Keep an investigation timeline that fills in while a long task runs * Send a teammate a link instead of pasting output into Slack * Publish a status board that [pulls fresh data through MC…
Configure auto mode
Claude Code CLI · in the page
auto-mode-config
…hould be reachable, and which cloud project, cluster, or registry the task uses and under what identity. Until this entry names that identity, the classifier [blocks](/docs/en/permission-modes.md#what…
Best practices for Claude Code
Claude Code CLI · in the page
best-practices
…Each step trades setup for attention. The prompt version works on any task today. The `/goal` and Stop hook versions are what let an unattended run finish correctly without you. Have Claude show evid…
Champion kit
Claude Code CLI · in the page
champion-kit
…the actual prompt you used so they can apply it directly to their own task. | A concrete, runnable example removes the gap between curiosity and a first successful use, which is where most adoption ef…
Claude Code changelog
Claude Code CLI · in the page
changelog
…s starting without an SDK MCP server's latest tools when a background task was running * Fixed some "Autocompact is thrashing" errors in turns that read many PDF pages, images or other large tool resu…
Push events into a running session with channels
Claude Code CLI · in the page
channels
…- | - | | [Cloud sessions](/docs/en/claude-code-on-the-web.md) | Run tasks in a fresh cloud sandbox, cloned from GitHub | Delegating self-contained async work you check on later | | [Claude in Slack]…
Use Claude Code with Chrome
Claude Code CLI · in the page
chrome
…e CLI or the [VS Code extension](/docs/en/vs-code.md#automate-browser-tasks-with-chrome). Build your code, then test and debug in the browser without switching contexts. Claude opens new tabs for bro…
Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry
Claude Code CLI · in the page
claude-apps-gateway
…ial chain # (IRSA, EC2/ECS task role, env vars, ~/.aws) # Models are translated per upstream automatically. The built-in catalog # maps claude-opus-4-8 to u…
Claude apps gateway configuration
Claude Code CLI · in the page
claude-apps-gateway-config
…S SDK's default credential chain: env vars, `~/.aws/credentials`, ECS task role, EC2 instance metadata, or IRSA on EKS. In production, give the gateway pod an IAM role instead of embedding static keys…
Claude apps gateway deployment and operations
Claude Code CLI · in the page
claude-apps-gateway-deploy
…te. The change applies to every container on the instance. Prefer ECS task roles where available, which read credentials from the ECS container-credentials endpoint and avoid the change entirely, or a…