Back to Prompt Library
planning

Setup Claude Agents SDK and Initial Agent

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Automated Vulnerability Assessment with Claude's Extended Thinking

Format
Code-aware
Lines
8
Sections
3
Linked challenge
Automated Vulnerability Assessment with Claude's Extended Thinking

Prompt source

Original prompt text with formatting preserved for inspection.

8 lines
3 sections
No variables
1 code block
Initialize your development environment and install the Claude Agents SDK. Create a basic agent that uses Claude Opus 4.1. Configure it to respond to a simple 'hello' message, confirming basic functionality. Ensure your Anthropic API key is correctly set.

```python
from anthropic.agents import AnthropicAgent
from anthropic.agents.tool_code import ToolCode
import os

# Initialize Claude agent with Opus 4.1
# ...
```

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.