Model Context Budgeting
AvanzadaopsContexto mínimo: 16K
Optimizes prompts and agent workflows for finite context windows by prioritizing evidence, compressing history, managing retrieval budgets, and measuring token-cost trade-offs.
Casos de uso
- Long-running agents
- Prompt cost optimization
- RAG context tuning
Prompt de ejemplo
Optimize this agent context strategy. Allocate a token budget across instructions, history, retrieval, and tool output, then propose truncation and summarization rules.
Modelos recomendados
Herramientas compatibles
claude-codecursorkiroany
Modalidades
Entrada: text, code, file
→Salida: text, code
Skills relacionadas
Autor
OpenModels Community