Cost Aware Llm Pipeline

This is a practical blueprint for keeping LLM API costs under control without tanking quality. It shows you how to route simple tasks to cheap models like Haiku and complex ones to Sonnet, track spend with immutable dataclasses, retry only transient errors, and cache long system prompts. The code examples are concrete and composable. Most useful if you're processing batches where costs add up fast or need hard budget limits before you burn through your API quota. The model selection thresholds are opinionated but tunable, which is the right approach.

Install to Claude Code

npx -y skills add affaan-m/ecc --skill cost-aware-llm-pipeline --agent claude-code