General skillAI and agent development
token-diet
Reduce LLM token use by pruning context, caching prompts, and routing models.
- Stars
- 3
- Forks
- 0
- Updated
- Updated May 19, 2026
MIT
Reduce LLM token use by pruning context, caching prompts, and routing models.
Token-Diet lays out an ordered optimization workflow for LLM applications: prune retrieved context first, reuse cached material, route work by complexity, keep structured state, and compress prose only at the final step. It also defines metrics and guardrails for token use, latency, cost, and quality, while excluding code, schemas, legal text, URLs, and identifiers from linguistic compression.
Resource types
Use cases
Platforms
Capabilities
Turn detailed business processes into reusable, tested AI skills.
Define portable task-specific sub-agents in Markdown for several coding assistants.
Public GitHub facts last synced Jul 10, 2026.
Find, create, run, and improve agent skills from real execution feedback.
Surface unknowns and assumptions before an AI agent starts building.