How should claude-agent-sdk be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this skill.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Crawler Summary

claude-agent-sdk answer-first brief

Guide for building applications with the Claude Agent SDK (open-claude-agent-sdk or @anthropic-ai/claude-agent-sdk). Use when developing apps that spawn Claude as a subprocess, including query options, hooks, MCP servers, multi-turn conversations, streaming, permissions, structured output, and session management. --- name: claude-agent-sdk description: Guide for building applications with the Claude Agent SDK (open-claude-agent-sdk or @anthropic-ai/claude-agent-sdk). Use when developing apps that spawn Claude as a subprocess, including query options, hooks, MCP servers, multi-turn conversations, streaming, permissions, structured output, and session management. --- Claude Agent SDK Build AI agents using query() — a thin wrapp Capability contract not published. No trust telemetry is available yet. 2 GitHub stars reported by the source. Last updated 4/15/2026.

Freshness

Last checked 4/15/2026

Best For

claude-agent-sdk is best for general automation workflows where MCP compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack

Card Facts Snapshot Contract Trust

Claim this agent

Agent DossierGitHubSafety: 94/100

claude-agent-sdk

MCPself-declared

Public facts

Change events

Artifacts

Freshness

Apr 15, 2026

Verifiededitorial-contentNo verified compatibility signals2 GitHub stars

Capability contract not published. No trust telemetry is available yet. 2 GitHub stars reported by the source. Last updated 4/15/2026.

2 GitHub starsTrust evidence available

Trust score

Unknown

Compatibility

MCP

Freshness

Apr 15, 2026

Vendor

Foksa

Artifacts

Benchmarks

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. 2 GitHub stars reported by the source. Last updated 4/15/2026.

View Source

Setup snapshot

git clone https://github.com/foksa/claude-agent-sdk-skill.git

1
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content

Vendor (1)

Vendor

Foksa

profilemedium

Observed Apr 15, 2026Source link Provenance

Compatibility (1)

Protocol compatibility

MCP

contractmedium

Observed Apr 15, 2026Source link Provenance

Adoption (1)

Adoption signal

2 GitHub stars

profilemedium

Observed Apr 15, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB OPENCLEW

Extracted files

Examples

Snippets

Languages

typescript

Parameters

Executable Examples

typescript

// Official SDK
import { query } from "@anthropic-ai/claude-agent-sdk";

// Lite SDK (compatible drop-in replacement)
import { query } from "lite-claude-agent-sdk";

typescript

import { query } from "@anthropic-ai/claude-agent-sdk";

for await (const message of query({
  prompt: "Find and fix the bug in auth.py",
  options: { allowedTools: ["Read", "Edit", "Bash"] }
})) {
  if (message.type === "result" && message.subtype === "success") {
    console.log(message.result);
  }
}

typescript

const q = query({ prompt: "...", options: { ... } });

for await (const message of q) {
  switch (message.type) {
    case "system":    // Init message — session_id, tools, model
    case "assistant": // Claude's response with content blocks
    case "user":      // Echoed user messages
    case "result":    // Final result — check message.subtype
  }
}

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Full README

name: claude-agent-sdk description: Guide for building applications with the Claude Agent SDK (open-claude-agent-sdk or @anthropic-ai/claude-agent-sdk). Use when developing apps that spawn Claude as a subprocess, including query options, hooks, MCP servers, multi-turn conversations, streaming, permissions, structured output, and session management.

Claude Agent SDK

Build AI agents using query() — a thin wrapper that spawns Claude CLI as a subprocess and streams NDJSON messages back.

Import

// Official SDK
import { query } from "@anthropic-ai/claude-agent-sdk";

// Lite SDK (compatible drop-in replacement)
import { query } from "lite-claude-agent-sdk";

Quick Start

import { query } from "@anthropic-ai/claude-agent-sdk";

for await (const message of query({
  prompt: "Find and fix the bug in auth.py",
  options: { allowedTools: ["Read", "Edit", "Bash"] }
})) {
  if (message.type === "result" && message.subtype === "success") {
    console.log(message.result);
  }
}

Core Pattern

query() returns an AsyncGenerator<SDKMessage> (the Query object). Iterate to receive messages:

const q = query({ prompt: "...", options: { ... } });

for await (const message of q) {
  switch (message.type) {
    case "system":    // Init message — session_id, tools, model
    case "assistant": // Claude's response with content blocks
    case "user":      // Echoed user messages
    case "result":    // Final result — check message.subtype
  }
}

The result message signals completion. Check message.subtype:

"success" — message.result has the text, message.structured_output has JSON (if outputFormat set)
"error_max_turns" / "error_during_execution" / "error_max_budget_usd" — check message.errors

Key Query Options

| Option | Type | Description | |--------|------|-------------| | prompt | string \| AsyncIterable<SDKUserMessage> | User prompt or streaming input | | model | string | Model to use (e.g., "claude-sonnet-4-5") | | maxTurns | number | Maximum conversation turns | | permissionMode | PermissionMode | "default" | "acceptEdits" | "bypassPermissions" | "plan" | | systemPrompt | string \| { type: "preset", preset: "claude_code", append?: string } | System prompt config | | hooks | Record<HookEvent, HookCallbackMatcher[]> | Hook callbacks for events | | mcpServers | Record<string, McpServerConfig> | MCP server configurations | | canUseTool | CanUseTool | Custom permission callback | | allowedTools | string[] | Allowed tool names (e.g., ["Read", "mcp__server__*"]) | | outputFormat | { type: "json_schema", schema: JSONSchema } | Structured output schema | | abortController | AbortController | Cancel the query | | includePartialMessages | boolean | Enable token streaming | | resume | string | Session ID to resume | | cwd | string | Working directory |

See references/query-options.md for the complete list of 35+ options with types and defaults.

Control Methods

Methods available on the Query object (streaming input mode only unless noted):

| Method | Description | |--------|-------------| | q.interrupt() | Interrupt current execution | | q.streamInput(msg) | Send additional messages | | q.setModel(model) | Change model mid-session | | q.setPermissionMode(mode) | Change permissions mid-session | | q.setMaxThinkingTokens(n) | Adjust thinking tokens | | q.supportedCommands() | List slash commands (works always) | | q.supportedModels() | List available models (works always) | | q.mcpServerStatus() | Check MCP server status (works always) | | q.accountInfo() | Get account info (works always) | | q.rewindFiles(uuid) | Restore files to checkpoint (requires enableFileCheckpointing) |

When to Load References

Load additional reference files based on what you need:

references/query-options.md — When you need the full list of all query options with types, defaults, and descriptions. Load when configuring advanced options like sandbox, agents, settingSources, betas, etc.
references/hooks.md — When implementing hooks to intercept agent execution. Covers all 15 hook events, matcher syntax, callback inputs/outputs, and permission decisions.
references/mcp-servers.md — When adding MCP servers (stdio, HTTP/SSE, or SDK in-process). Covers createSdkMcpServer(), tool() helper, allowedTools wildcards, and MCP control methods.
references/patterns.md — When building multi-turn conversations, streaming UIs, session management, canUseTool approval flows, structured outputs, or handling common gotchas.

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB OPENCLEW

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

missing

Auth

None

Streaming

Data region

Unspecified

Protocol support

MCP: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.

Invocation examples

curl -s "https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/snapshot"

curl -s "https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/contract"

curl -s "https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media

No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors

GITLAB_AI_CATALOGgitlab-mcp

Rank

A Model Context Protocol (MCP) server for GitLab

Traction

No public download signal

Freshness

Updated 2d ago

MCP

GITLAB_PUBLIC_PROJECTSgitlab-mcp

Rank

A Model Context Protocol (MCP) server for GitLab

Traction

No public download signal

Freshness

Updated 2d ago

MCP

GITLAB_AI_CATALOGrmcp-openapi

Rank

Expose OpenAPI definition endpoints as MCP tools using the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)

Traction

No public download signal

Freshness

Updated 2d ago

MCP

GITLAB_AI_CATALOGrmcp-actix-web

Rank

An actix_web backend for the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)

Traction

No public download signal

Freshness

Updated 2d ago

MCP

Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "MCP"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-16T23:36:28.388Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "MCP",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    }
  ],
  "flattenedTokens": "protocol:MCP|unknown|profile"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Foksa",
    "href": "https://github.com/foksa/claude-agent-sdk-skill",
    "sourceUrl": "https://github.com/foksa/claude-agent-sdk-skill",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T02:12:52.781Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "MCP",
    "href": "https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-04-15T02:12:52.781Z",
    "isPublic": true
  },
  {
    "factKey": "traction",
    "category": "adoption",
    "label": "Adoption signal",
    "value": "2 GitHub stars",
    "href": "https://github.com/foksa/claude-agent-sdk-skill",
    "sourceUrl": "https://github.com/foksa/claude-agent-sdk-skill",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T02:12:52.781Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/foksa-claude-agent-sdk-skill/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]