Mit Token-Effizienz verknüpfte gemessene Katalogeinträge.
Say more with less. Claude Code skill/plugin that cuts ~60-70% of output tokens while keeping natural, readable English.
Sterne19Gemessen · 22.10.2026
Momentum32,77 Tage · Gemessen · +11,76% relative Änderung
The context layer for production AI agents: local-first context planning, compression and runtime for LLM apps.
Sterne19Gemessen · 22.10.2026
Momentum32,77 Tage · Gemessen · +11,76% relative Änderung
A tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying full price.
Sterne75Gemessen · 22.10.2026
Momentum31,97 Tage · Gemessen · +5,63% relative Änderung
Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.
Sterne217Gemessen · 22.10.2026
Momentum30,57 Tage · Gemessen · +2,84% relative Änderung
"Work appears completed or recorded. Run /compact to save tokens."
Sterne223Gemessen · 22.10.2026
Momentum30,37 Tage · Gemessen · +2,76% relative Änderung
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.
Sterne2.462Gemessen · 22.10.2026
Momentum30,17 Tage · Gemessen · +0,57% relative Änderung
Your AI coding agent follows these files blindly, before it reads a line of your code.
Sterne10Gemessen · 22.10.2026
Momentum28,37 Tage · Gemessen · +11,11% relative Änderung
Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.
Sterne158Gemessen · 22.10.2026
Momentum26,67 Tage · Gemessen · +2,6% relative Änderung
Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.
Sterne484Gemessen · 22.10.2026
Momentum25,87 Tage · Gemessen · +1,26% relative Änderung
Claude Opus 5.5 with the effort level re-decided every step by the TypeSafe Jev reflex — without breaking the prompt cache. CLI + Claude Code plugin.
Sterne15Gemessen · 22.10.2026
Momentum24,97 Tage · Gemessen · +7,14% relative Änderung