Measured catalogue entries associated with Token efficiency.
🤿 The cheapest multi-agent workforce that is actually user-friendly: 7.7x more productive and 50x cheaper compared to your ultracode mode, an intelligent multi-agent swarm of Claude Code agents on DeepSeek or other providers, integrated with your own Claude Code or Codex.
Stars11Measured · Oct 21, 2026
Momentum62.27 days · Measured · +450% relative change
Claude Code mod: context in tokens, 5-hour and weekly limits vs. the clock, prompt cache countdown, session cost and running agents, in one band above the prompt.
Stars21Measured · Oct 21, 2026
Momentum59.87 days · Measured · +75% relative change
Use GPT, DeepSeek, GLM, Gemini, Kimi and 400+ models in Claude Desktop's own model picker and in Claude Code, while staying signed in to your Claude subscription (1P, no gateway mode). Auto reasoning effort per prompt, subagents routed by difficulty, cache and limit warnings. Claude inside Codex too.
Stars64Measured · Oct 21, 2026
Momentum587 days · Measured · +33.33% relative change
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Stars2,609Measured · Oct 21, 2026
Momentum45.77 days · Measured · +1.76% relative change
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.
Stars690Measured · Oct 21, 2026
Momentum45.67 days · Measured · +3.92% relative change
Claude Code mod that keeps the prompt cache warm and shows each refresh's cost and saving
Stars18Measured · Oct 21, 2026
Momentum44.97 days · Measured · +28.57% relative change
Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
Downloads · last 7 days35Measured · Oct 21, 2026
Momentum42.27 days · Measured · +16.67% relative change
Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware suggestions — all local, zero config.
Stars120Measured · Oct 21, 2026
Momentum34.77 days · Measured · +5.26% relative change
Say more with less. Claude Code skill/plugin that cuts ~60-70% of output tokens while keeping natural, readable English.
Stars19Measured · Oct 21, 2026
Momentum32.77 days · Measured · +11.76% relative change
📱🐭 No we are not computer use, it's Application Use Via... a unified orchestration layer of OS automation, 0 token cost
Stars120Measured · Oct 21, 2026
Momentum31.87 days · Measured · +4.35% relative change