Plugin Claude Code
Spend tokens where they matter: one benchmark-picked tool per token layer.
10 1mo ago A
tokens not measured
original MIT
Agent skill that routes each coding task to the most token-efficient tool per layer: serena for code reads, rtk for command output, caveman for prose, Ponytail for generated code — −70% tokens measured in a 9-tool benchmark. Installable as a Claude Code plugin or Codex skill.
Plugin Claude Code
Spend tokens where they matter: one benchmark-picked tool per token layer.
Plugin Claude Code
Route every coding task to the most token-efficient tool per layer: serena (code reads), rtk (command output), caveman (prose output), Ponytail (code output) — backed by a 9-tool benchmark.