claude-agent-sdk

claude-agent-sdk is a plugin for Claude Code from latestaiagents/agent-skills. Its manifest loads nothing; the 5 skills it bundles cost 497 tokens per session together, scanned A, original, MIT.

A guide to building software agents with the Claude Agent SDK, including managed agents, sessions, delegated sub-agents, and streamed responses.

In plain words
What is it for?
Use it to create Claude-powered agents, manage their sessions, delegate work to sub-agents, and stream results to users.
Why use it?
It gives you the patterns needed to manage an agent's work over time and split tasks between cooperating agents.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions subagents.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add latestaiagents/agent-skills
agentmods
npx agentmods add plugins/latestaiagents/agent-skills/claude-agent-sdk
Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-agent-sdk

README.md
[![agentmods](https://agentmods.dev/badge/plugins/latestaiagents/agent-skills/claude-agent-sdk.svg)](https://agentmods.dev/plugins/latestaiagents/agent-skills/claude-agent-sdk)
Your own site
<a href="https://agentmods.dev/plugins/latestaiagents/agent-skills/claude-agent-sdk"><img src="https://agentmods.dev/badge/plugins/latestaiagents/agent-skills/claude-agent-sdk.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 5 skills cost 497 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claude-agent-sdk scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json#claude-agent-sdk · 21 lines

What it actually says

{
  "name": "claude-agent-sdk",
  "source": "./skills/claude-agent-sdk",
  "description": "Build agents with the Claude Agent SDK. Quickstart, Managed Agents API, session lifecycle, sub-agent delegation, streaming. 5 skills for production agent development.",
  "version": "1.0.0",
  "author": {
    "name": "latestaiagents"
  },
  "homepage": "https://github.com/latestaiagents/agent-skills",
  "repository": "https://github.com/latestaiagents/agent-skills",
  "license": "MIT",
  "keywords": [
    "claude-agent-sdk",
    "managed-agents",
    "sub-agents",
    "sessions",
    "streaming",
    "agent-framework"
  ],
  "category": "AI Architecture"
}
Contents

What it installs

The manifest is a name and a version. 5 skills travel with it, and installing the plugin installs all of them — 497 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

2 files beside marketplace.json#claude-agent-sdk in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 21 lines scan A 4ae28dd73a67

Subscribe to this mod's changes

claude-agent-sdk is a plugin published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.