headroom
Unclaimed, from headroomlabs-ai
Use when a Python or TypeScript app sends large tool outputs, logs, JSON, search results or long chat history to an LLM and the task is to cut input tokens, reduce token cost, fit a context window, or trim tool results without losing errors. Adds the headroom-ai compress() call; in-process, no API…
Launcher coming soon
Without the launcher
git clone https://github.com/headroomlabs-ai/headroom.git cd headroom git checkout 3c66c91eea3ad8cf77d7d66abe484cee876271eb
Then copy headroom/plugins/headroom-skill/skills/headroom into your app's skills folder, for example .claude/skills/headroom.
No images in this version.