Mit Token-Effizienz verknüpfte gemessene Katalogeinträge.
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.
Sterne21Gemessen · 22.10.2026
Momentum59,87 Tage · Gemessen · +75% relative Änderung
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.
Sterne64Gemessen · 22.10.2026
Momentum53,97 Tage · Gemessen · +25,49% relative Änderung
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
Sterne120Gemessen · 22.10.2026
Momentum47,87 Tage · Gemessen · +12,15% relative Änderung
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Sterne2.620Gemessen · 22.10.2026
Momentum477 Tage · Gemessen · +1,91% relative Änderung
Claude Code mod that keeps the prompt cache warm and shows each refresh's cost and saving
Sterne18Gemessen · 22.10.2026
Momentum44,97 Tage · Gemessen · +28,57% relative Änderung
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.
Sterne694Gemessen · 22.10.2026
Momentum44,37 Tage · Gemessen · +3,58% relative Änderung
Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
Downloads · letzte 7 Tage35Gemessen · 22.10.2026
Momentum42,27 Tage · Gemessen · +16,67% relative Änderung
Claude Code plugin: automatic Claude model routing. Picks Haiku, Sonnet or Opus and the reasoning effort per prompt, step and subagent; effort cap, prompt-cache guard, status band, benchmarks.
Sterne15Gemessen · 22.10.2026
Momentum34,87 Tage · Gemessen · +15,38% relative Änderung
📱🐭 No we are not computer use, it's Application Use Via... a unified orchestration layer of OS automation, 0 token cost
Sterne121Gemessen · 22.10.2026
Momentum34,67 Tage · Gemessen · +5,22% relative Änderung
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.
Sterne122Gemessen · 22.10.2026
Momentum34,67 Tage · Gemessen · +5,17% relative Änderung