An additive toolkit that wraps Claude Code (Fable) with hooks, skills, and routing patterns to minimize token costs by exploiting prompt caching economics and offloading mechanical work to cheaper lanes.
107
No data
4
0
MIT
2026-07-04
It directly addresses the high token cost of reasoning-focused models like Claude Code by providing a practical, evidence-based orchestration layer that keeps expensive models on judgment tasks while routing routine work to cheaper alternatives, all grounded in official Anthropic pricing and caching documentation.
🧚 Fable-first Claude orchestration kit for token-saving lane routing, dense turns, and cache-preserving wait discipline.
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.