claude-agent-sdk-python

claude-agent-sdk-python is a skill for Claude Code, Codex from kivo360/OmoiOS. It costs 65 tokens per session (1,733 once invoked), scanned A, original, Apache-2.0.

A Python toolkit for building applications with the Claude Agent SDK. It supports requests, interactive conversations, custom tools, permission checks, and lifecycle hooks.

In plain words
What is it for?
Use it to create one-shot or multi-turn agent apps, stream conversations, add in-process tools, restrict tool use, and intercept lifecycle events.
Why use it?
It provides the SDK patterns needed to connect a Python program to Claude and control what the agent can do.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/kivo360/omoios/claude-agent-sdk-python
Any agent
npx skills add kivo360/OmoiOS --skill claude-agent-sdk-python
Clone the repo
git clone --depth 1 https://github.com/kivo360/OmoiOS

Made for: Claude Code, Codex.

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-python

README.md
[![agentmods](https://agentmods.dev/badge/skills/kivo360/omoios/claude-agent-sdk-python.svg)](https://agentmods.dev/skills/kivo360/omoios/claude-agent-sdk-python)
Your own site
<a href="https://agentmods.dev/skills/kivo360/omoios/claude-agent-sdk-python"><img src="https://agentmods.dev/badge/skills/kivo360/omoios/claude-agent-sdk-python.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,733 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00065 $0.01733
Opus 5 $0.00032 $0.00866
Sonnet 5 $0.00013 $0.00347
Haiku 4.5 $0.00006 $0.00173

Measured 3d ago against content hash 4bd46050fe02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-agent-sdk-python 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/create_agent_project.py, scripts/run_agent_app.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/claude-agent-sdk-python/SKILL.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Agent SDK Python

Build production-ready agent applications with the Claude Agent SDK for Python.

Quick Reference

Installation

pip install claude-agent-sdk

Requires Python 3.10+ and bundled Claude CLI v2.0.60+.

Core APIs

API Use Case
query() One-shot or simple multi-turn queries
ClaudeSDKClient Interactive streaming, bidirectional control
@tool + create_sdk_mcp_server() Custom in-process tools
can_use_tool callback Fine-grained permission control
hooks Lifecycle event interception

Basic Patterns

One-Shot Query

import anyio
from claude_agent_sdk import query, AssistantMessage, TextBlock, ResultMessage

async def main():
    async for msg in query(prompt="Explain Python decorators"):
        if isinstance(msg, AssistantMessage):
            for block in msg.content:
                if isinstance(block, TextBlock):
                    print(block.text)
        elif isinstance(msg, ResultMessage):
            print(f"Cost: ${msg.total_cost_usd:.4f}")

anyio.run(main)

Interactive Client

import anyio
from claude_agent_sdk import (
    ClaudeSDKClient,
    ClaudeAgentOptions,
    AssistantMessage,
    TextBlock,
    ResultMessage,
)

async def main():
    options = ClaudeAgentOptions(
        system_prompt="You are a helpful assistant",
        allowed_tools=["Read", "Write", "Bash"],
        permission_mode="acceptEdits",
        max_turns=10,
    )

    async with ClaudeSDKClient(options=options) as client:
        await client.query("Analyze main.py")

        async for msg in client.receive_response():
            if isinstance(msg, AssistantMessage):
                for block in msg.content:
                    if isinstance(block, TextBlock):
                        print(block.text)
            elif isinstance(msg, ResultMessage):
                print(f"Done. Cost: ${msg.total_cost_usd:.4f}")

anyio.run(main)

Custom Tools

Read the full file on GitHub · 256 lines

Files

What ships with it

6 files beside SKILL.md 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. 3d ago First seen · 256 lines · 65 tokens per session scan A 4bd46050fe02

Subscribe to this mod's changes

claude-agent-sdk-python is a skill published in the GitHub repository kivo360/OmoiOS (76 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,733 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-30.