cost-aware-llm-pipeline

SKILL.md

Patterns for controlling LLM API costs while maintaining quality. Combines model routing, budget tracking, retry logic, and prompt caching into a composable pipeline.

Automatically select cheaper models for simple tasks, reserving expensive models for complex ones.

Track cumulative spend with frozen dataclasses. Each API call returns a new tracker — never mutates state.

LLM API 사용을 위한 비용 최적화 패턴 — 작업 복잡성에 따른 모델 라우팅, 예산 추적, 재시도 논리 및 프롬프트 캐싱. 출처: affaan-m/everything-claude-code.

원본 보기