Same answer, fewer tokens — KO-first LLM output-compression skill for Claude Code & Codex. A Korean-native caveman alternative, measured on real session output_tokens.
Cut the tokens your IDE-to-LLM coding session is billed for. Stops re-sending files the model already has, places provider cache breakpoints where they cover the request, and compresses what needs sending — measured against real tokenizers, not character counts. CLI, VS Code, MCP server, proxy.
Ork z kopalni. Mówi mało. Wie dużo. Pomaga.
KISS MCP proxy for Codex: compress text and turn image payloads into compact graph/diagram primitives.
DeepSeek Harness bundle: mount mcptoon as an MCP server in one command. Tool discovery 71,929 -> 581 tokens across 255 tools (-99.2%, measured); encoding is lossless.
PhoLine — client-side PhO channel codec for LLM chats. Information filter, not IPA. By Christian Heinrich Hohlfeld, ORCID 0009-0003-6634-9045.
Client-side semantic token reduction and local response rehydration for LLM web chats. By Christian Heinrich Hohlfeld, ORCID 0009-0003-6634-9045.
To associate your repository with the token-compression topic, visit your repo's landing page and select "manage topics."