Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.

Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills

A Claude Code skill that encodes battle-tested editorial principles, section-specific rhetorical moves, and a structured writing pipeline for research papers. Brainstorm → Draft 0 → Evaluate → Write → Compress.

C.O.N.T.EX.T is designed to compress complex, multi-domain conversations into machine-optimized "Carry-Packets." These packets achieve a crystallization point of 0.15 entity/token, ensuring that a receiving model can reconstruct the original context with near-perfect fidelity.

My personal agent skills

Pith is the hook that makes Claude Code sessions last 3x longer.

SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

The Biomimetic Context Engine & Neural Runtime for AI Coding Assistants

Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.

MCP tool lists eat 71,929 tokens at 255 tools — more than half a 128K window before you ask anything. mcptoon reads the same tools back at 581 (-99.2%, measured). 128KB CLI, zero deps. Compute your own: activeing123.github.io/mcptoon/tools/token-tax