home/categories/framework-internals/shengxinjing-burn-token-skill-skill-md
framework-internalsdevelopment

burn-token

Use when user wants to burn tokens aggressively - infinite loop of analysis, summarization, or heavy math computation. Maximizes token consumption by defeating KV cache, randomizing prompts, and dispatching verbose subagents. Supports time limits, round limits, or unlimited burn until interrupted.

shengxinjing
maintainer
shengxinjing
Updated 4/5/2026
Stars
21
Forks
0
quick start

Installation and usage

Use when user wants to burn tokens aggressively - infinite loop of analysis, summarization, or heavy math computation. Maximizes token consumption by defeating KV cache, randomizing prompts, and dispatching verbose subagents. Supports time limits, round limits, or unlimited burn until interrupted.

Installation
$ install --globalskills.sh
Usage

Once installed, you can use this skill by running the following command in your terminal:

skills use burn-token