Back to Prompt Library
implementation
Claude Agents SDK Setup with Extended Thinking
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Build a Claude Agents SDK Reproductive Psychiatry Legal & Risk Inspector
Format
Text-first
Lines
1
Sections
1
Linked challenge
Build a Claude Agents SDK Reproductive Psychiatry Legal & Risk Inspector
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Initialize a Claude Agents SDK agent using `claude-3-7-sonnet` with extended thinking budget enabled (`thinking={'type': 'enabled', 'budget_tokens': 2048}`).Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Hold the task contract and output shape stable so generated implementations remain comparable.
Tune next
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Verify after
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.