pi-infected

Tokenade — AI skill for Claude Code

AI community

Cut your AI coding agent's token bill, locally: Claude Code, Codex, Cursor, Copilot.

How to install Tokenade

This entry records only its repository, not the path inside it, so there is no exact command to give. Open pi-infected/tokenade and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Tokenade does

Cut your AI coding agent's token bill, locally: Claude Code, Codex, Cursor, Copilot. #1 on THOL, 39% cheaper on long sessions.

Alternatives in AI

  • Codeburn — Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Code 9.7k ★
  • Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★
  • Token Monitor — Local-first desktop widget for tracking token usage, costs, and limits across 32+ AI coding tools—including Cl 1.8k ★

README

Tokenade — a marble hand squeezes a lemon and every drop is a coding agent (Claude Code, Codex, Cursor, Copilot, OpenCode…). Squeeze your agent's token bill: open source, 100% local. #1 on THOL — 39% cheaper on long sessions.

Tokenade

Cut your AI coding agent's token bill — locally, automatically, on every prompt.

Demo: npm install -g @tokenade/cli, tokenade install, then a Claude Code session runs pytest -v and Tokenade folds the 342 passing-test lines; the dashboard shows the tokens saved.

license npm #1 on THOL

Install · What it does · Benchmark · Website

Tokenade is a single Rust binary that sits between your coding agent (Claude Code, Codex, Cursor, Copilot CLI, OpenCode, Kilo Code, Qwen Code…) and the model. It strips what the model never needed to see — 2,000-line build logs, whole files when one function mattered, verbose MCP payloads, re-reads of content already in context — before it is billed, and keeps every byte it folds recoverable on demand.

#1 on THOL

Tokenade ranks **#1 on THOL**, the Token-Harness Optimizer Leaderboard — real end-to-end agent runs, every optimizer measured the same way: **39% cheaper on long sessions**. Method and fu