claude-agent-sdk
Best for coding agentsWorks with GitHub
⌘source
- author
@LeoYeAI- language
- Python
★2kstars
306forks
May 6, 2026
✦overview.md
Key Features
- ·JSON schema validation with Zod or JSON Schema
- ·outputFormat parameter for structured responses
- ·Plugin system and hooks for event-driven workflows
- ·Prevents 14 documented errors
- ·TypeScript type inference with Zod schemas
Use Cases
- →Building coding agents that require guaranteed structured outputs
- →Creating SRE systems with event-driven workflows
- →Developing security auditors with validated output schemas
- →Troubleshooting structured output validation and session forking errors
Best for
- ✓coding agents
- ✓SRE systems
- ✓security auditors
Not ideal for
- !one-off scripts
- !simple automations without structured outputs
FAQs
name
claude-agent-sdk
description
Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with plugins system and hooks for event-driven workflows. Prevents 14 documented errors.
Use when: building coding agents, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors, MCP config issues, subagent cleanup.
user-invocable:true
Claude Agent SDK - Structured Outputs & Error Prevention Guide
Package: @anthropic-ai/claude-agent-sdk@0.2.12 Breaking Changes: v0.1.45 - Structured outputs (Nov 2025), v0.1.0 - No default system prompt, settingSources required
What's New in v0.1.45+ (Nov 2025)
Major Features:
1. Structured Outputs (v0.1.45, Nov 14, 2025)
- JSON schema validation - Guarantees responses match exact schemas
outputFormatparameter - Define output structure with JSON schema or Zod- Access validated results - Via
message.structured_output - Beta header required:
structured-outputs-2025-11-13 - Type safety - Full TypeScript inference with Zod schemas
Example:
import { query } from "@anthropic-ai/claude-agent-sdk";
import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";
const schema = z.object({
summary: z.string(),
sentiment: z.enum(['positive', 'neutral', 'negative']),
confidence: z.number().min(0).max(1)
});
const response = query({
prompt: "Analyze this code review feedback",
options: {
model: "claude-sonnet-4-5",
outputFormat: {
type: "json_schema",
json_schema: {
$install
1-click copynpx skills add LeoYeAI/openclaw-master-skills --skill claude-agent-sdkSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.