Compress AI agent output tokens using telegraphic prose at three levels.
npx skills add https://github.com/adihebbalae/Attacca --skill caveman-adihebbalae
Please help me install this Agent Skill. Skill: caveman Source: https://github.com/adihebbalae/Attacca/tree/main/.github/skills/caveman Command: npx skills add https://github.com/adihebbalae/Attacca --skill caveman-adihebbalae
This Skill compresses agent output, reducing token spend without losing meaning, to help manage context window size and speed up response times.
Set compression level to 'full' with the command: /set-compression full
High-intent search queries and answers about installing and using this skill.
Token compression reduces AI agent output by 65-75% using telegraphic prose, which preserves meaning while managing context window size and speeding up response times for long-running tasks.
You can set the compression level by using the command `/set-compression` followed by the desired level. The Skill offers three intensity options: 'lite', 'full', and 'ultra' for different contexts.
Telegraphic prose is a token compression mechanism that condenses agent outputs to 65-75% of their original size. It helps preserve context budget during long-running tasks without losing meaning.
Token compression reduces output size without losing meaning. By applying telegraphic prose, it condenses the text to manage context window size while maintaining the original message's integrity.
Ultra compression is suited for contexts requiring maximum context budget preservation, while lite compression applies lighter condensation. Choose the intensity level based on your long-running task requirements.
wangyouanCompress large token contexts to minimize information loss in agent sessions.
aslaiiGenerate a {phase_num}-CONTEXT.md file documenting implementation decisions for downstream agents.
Ven0m0Monitor token consumption against MECW thresholds and apply compression strategies.
Soham407Map relevant modules and callers using domain glossary vocabulary.
