Prompt Compressor

Saves 20-40% of LLM tokens by teaching the agent to write compressed responses, compressed memory logs, and compressed pre-compaction summaries. Works via SOUL.md instructions — no hooks, no extra process, no dependencies. Also provides explicit compression when the user asks to compress a prompt. Use when the user asks about reducing token costs, optimizing API spend, compressing prompts, or making the agent more efficient.

dvcrn Updated 32 repo stars

File contents

dvcrn/openclaw-skills-marketplace/tree/main/plugins/ckpxgfnksd-max--prompt-token-saver/skills/prompt-compressor commit 0f6cd7c6e2

Frequently asked questions

npx skillmds@latest add dvcrn/prompt-compressor