claude-agent-toolkit
🥈SilverPython framework for building agents using claude-code-sdk. Provides decorator-based tools, runtime isolation, and simplified agent development. Benefits developers in operations by streamlining agent creation and integration with existing workflows.
2760Updated 2mo ago
Intermediate30min to implementautomation
Saves ~180 min per use
Quick InstallView Source
git clone https://github.com/cheolwanpark/claude-agent-toolkit.gitWorks with:
Claude
Overview
About This Skill
Claude Agent Toolkit is a Python framework that wraps claude-code-sdk to simplify AI agent development through decorator-based tool creation and Docker-based runtime isolation. It solves the complexity of manual MCP server setup and tool integration by providing a class-based tool system with the @tool decorator, enabling developers to convert Python functions into Claude-compatible tools with minimal configuration. The framework ensures production safety by running tool execution in isolated Docker containers, preventing access to unintended system tools and providing consistent behavior across environments. Built for developers building AI agents who need both ease of development and controlled, predictable runtime execution.
How to Use
1. Install the claude-agent-toolkit: `pip install claude-agent-toolkit` 2. Import required decorators: `from claude_agent_toolkit import Agent, task, runtime` 3. Define your agent's tasks using `@task` decorator with clear descriptions 4. Configure runtime isolation with `@runtime` decorator (choose between 'process', 'thread', or 'none') 5. Create the agent instance and run it using `agent.run()` Tips: - Start with simple tasks before adding complex workflows - Use isolation_level='process' for CPU-intensive tasks - Add error handling within your task functions - Test tasks individually before combining them in the agent
Use Cases
Building calculator and data processing agents with isolated tool execution
Creating multi-tool agents with parallel execution support and permission controls
Developing production AI applications requiring runtime safety and environment consistency
Replacing manual claude-code-sdk integration with simplified agent scaffolding
Tags
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/cheolwanpark/claude-agent-toolkitRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Use the claude-agent-toolkit to create a Python agent that [TASK]. The agent should use the [DECORATOR] decorator to handle [FUNCTIONALITY]. Include [RUNTIME_CONFIGURATION] for isolation. Generate the complete agent code and explain how to run it with claude-code-sdk.
Example Output
```python
from claude_agent_toolkit import Agent, task, runtime
@task(description="Process customer support tickets from Zendesk API")
def process_tickets():
import requests
response = requests.get("https://zendesk.com/api/v2/tickets.json", headers={"Authorization": "Bearer [API_KEY]"})
tickets = response.json()["tickets"]
for ticket in tickets:
if ticket["status"] == "open" and ticket["priority"] == "high":
print(f"Escalating ticket {ticket['id']} to senior support")
@runtime(isolation_level="process", timeout=30)
def run_agent():
agent = Agent(name="SupportTicketProcessor", tasks=[process_tickets])
agent.run()
if __name__ == "__main__":
run_agent()
```
To run this agent, install the dependencies:
```bash
pip install claude-agent-toolkit requests
```
Then execute with claude-code-sdk:
```bash
claude run agent.py
```
The agent will process high-priority open tickets from Zendesk and escalate them automatically. The runtime isolation ensures crashes in the ticket processing don't affect the agent's core functionality. The decorator-based approach makes it easy to add new tasks like database logging or Slack notifications without modifying the core agent logic.Apply to these tools
Browse all toolsClaude
AI assistant built for thoughtful, nuanced conversation
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
Drata
Automate security compliance and monitor real-time security posture seamlessly.
GPT for work
Automate your spreadsheet tasks with AI power
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan