Token-Effizienz

Claude Code mod: picks the reasoning effort for every prompt, shows the prompt cache and context, and hands off or compacts in one click

Quelle

GitHub

Sprache

HTML

Domänen

Agenten, Skills und MCP

Einsatzzwecke

Agenten-Skills, Token-Effizienz, Code-Assistenten

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

Quelle

GitHub

Sprache

TypeScript

Domänen

Agenten, Skills und MCP

Einsatzzwecke

Agenten-Skills, Token-Effizienz, Code-Assistenten

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.

Quelle

GitHub

Sprache

TypeScript

Domänen

Agenten, Skills und MCP

Einsatzzwecke

Agenten-Skills, Token-Effizienz, Beobachtbarkeit, Code-Assistenten

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

Quelle

GitHub

Sprache

Rust

Domänen

Rust

Einsatzzwecke

Token-Effizienz, Code-Assistenten

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.

Quelle

GitHub

Sprache

Python

Domänen

Agenten, Skills und MCP, Web / JavaScript

Einsatzzwecke

Token-Effizienz, Retrieval-Augmented Generation (RAG), Code-Assistenten

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

Quelle

GitHub

Sprache

Rust

Domänen

Agenten, Skills und MCP

Einsatzzwecke

Agenten-Skills, Token-Effizienz

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

Quelle

GitHub

Sprache

TypeScript

Domänen

Agenten, Skills und MCP

Einsatzzwecke

Agenten-Skills, Token-Effizienz, Code-Assistenten

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

Quelle

GitHub

Sprache

Go

Domänen

Agenten, Skills und MCP

Einsatzzwecke

Agenten-Skills, Token-Effizienz, Code-Assistenten

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.

Quelle

GitHub

Sprache

JavaScript

Domänen

Agenten, Skills und MCP

Einsatzzwecke

Agenten-Skills, Token-Effizienz, Code-Assistenten

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

Quelle

GitHub

Sprache

Python

Domänen

Agenten, Skills und MCP

Einsatzzwecke

Token-Effizienz, Code-Assistenten