Token efficiency

Mods for Claude Code. effortless picks the reasoning effort for every prompt and shows the cache countdown. textless shows art, quotes and chess instead of the wall of text while Claude works.

Source

GitHub

Language

HTML

Domains

Agents, skills and MCP

Uses

Agent skills, Token efficiency, Code assistants

Keep Claude Code’s prompt cache warm during breaks and show the estimated cost before a cold send.

Source

GitHub

Language

TypeScript

Domains

Agents, skills and MCP

Uses

Agent skills, Token efficiency, Code assistants

A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent cards and swimlanes.

Source

GitHub

Language

TypeScript

Domains

Agents, skills and MCP

Uses

Agent skills, Token efficiency, Observability, Code assistants

Claude Code mod: hands off to a fresh conversation when context fills up, keeps the cache warm while you're away, and turns what you teach Claude into project notes

Source

GitHub

Language

TypeScript

Domains

Agents, skills and MCP

Uses

Agent skills, Token efficiency, Code assistants

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Source

GitHub

Language

Rust

Domains

Rust

Uses

Token efficiency, Code assistants

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Source

GitHub

Language

Python

Domains

Agents, skills and MCP, Web / JavaScript

Uses

Token efficiency, Retrieval-augmented generation (RAG), Code assistants

📱🐭 No we are not computer use, it's Application Use Via... a unified orchestration layer of OS automation, 0 token cost

Source

GitHub

Language

Rust

Domains

Agents, skills and MCP

Uses

Agent skills, Token efficiency

Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.

Source

GitHub

Language

JavaScript

Domains

Agents, skills and MCP

Uses

Agent skills, Token efficiency, Code assistants

Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.

Source

GitHub

Language

Go

Domains

Agents, skills and MCP

Uses

Agent skills, Token efficiency, Code assistants

Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

Source

GitHub

Language

Python

Domains

Agents, skills and MCP

Uses

Token efficiency, Code assistants