Official Technical Resources: Anthropic (page 17)
Official Technical Resources · Anthropic: 269 entries in total; this page lists entries 241–255.
Plugins reference
Complete technical reference for Claude Code plugin system, including schemas, CLI commands, and component specifications.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Tool Calling · AI Agent
Link last checked: 2026-09-24
Channels reference
Build an MCP server that pushes webhooks, alerts, and chat messages into a Claude Code session. Reference for the channel contract: capability declaration, notification events, reply tools, sender gating, and permission relay.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · Privacy and Data Compliance
Link last checked: 2026-09-24
Agent SDK overview
Build production AI agents with Claude Code as a library
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Agent Memory
Link last checked: 2026-09-24
Migrate to Claude Agent SDK
Guide for migrating the Claude Code TypeScript and Python SDKs to the Claude Agent SDK
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Agent Memory
Link last checked: 2026-09-24
Troubleshoot the Agent SDK
Fix Agent SDK errors by the exact message you see, with the cause and fix for each error in the TypeScript and Python SDKs.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Agent Memory
Link last checked: 2026-09-24
Configure your agent
Configure Agent SDK sessions: compose the options object, set the model, environment, and limits, and find each feature option's page.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Selection and Cost · Prompt Engineering
Link last checked: 2026-09-24
How the agent loop works
Understand the message lifecycle, tool execution, context window, and architecture that power your SDK agents.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Tool Calling · AI Agent
Link last checked: 2026-09-24
Use Claude Code features in the SDK
Load project instructions, skills, hooks, and other Claude Code features into your SDK agents.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Tool Calling · AI Agent
Link last checked: 2026-09-24
Work with sessions
How sessions persist agent conversation history, and when to use continue, resume, and fork to return to a prior run.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Agent Memory
Link last checked: 2026-09-24
Persist sessions to external storage
Mirror Agent SDK session transcripts to your own object store, key-value store, or database so other hosts can resume your sessions.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Agent Memory
Link last checked: 2026-09-24
Streaming Input
Understanding the two input modes for Claude Agent SDK and when to use each
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Structured Outputs · AI Agent
Link last checked: 2026-09-24
Handle approvals and user input
Surface Claude's approval requests and clarifying questions to users, then return their decisions to the SDK.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Agent Memory
Link last checked: 2026-09-24
Stream responses in real-time
Get real-time responses from the Agent SDK as text and tool calls stream in
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Selection and Cost · Prompt Engineering
Link last checked: 2026-09-24
Get structured output from agents
Return validated JSON from agent workflows using JSON Schema, Zod, or Pydantic. Get type-safe, structured data after multi-turn tool use.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Structured Outputs · AI Agent
Link last checked: 2026-09-24
Give Claude custom tools
Define custom tools with the Claude Agent SDK's in-process MCP server so Claude can call your functions, hit your APIs, and perform domain-specific operations.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Tool Calling · AI Agent
Link last checked: 2026-09-24