Skills and MCP tagged “compression”

omni-compression cheaper-inference skill Skill automatically compresses tokens by choosing between RTK for command logs, Caveman for prose, or stacking both. Cuts API spend and speeds up agent responses. Claude Code CX Codex Cursor +1 998installs omni-context-rtk cheaper-inference skill Configures RTK filters, context rules, and relay settings, then tests compression on real prompts. Use it when context transformation needs inspection. Claude Code CX Codex Cursor +1 971installs context-compression sickn33 skill A skill for managing context compression when agent sessions exceed token limits. Instead of naive truncation, it maintains structured summaries with file inventory, decisions, and state. Claude Code CX Codex Cursor +1 1,400installs steno-mode official github skill Compresses agent replies into disciplined shorthand, cutting roughly 40% of response tokens while code, commands, paths and API names stay exact. GitHub Copilot 32installs