token-checkup
Weekly token checkup for Claude Code. Measures how big sessions get and what every session loads before the first answer, catches silent growth (app updates, new connectors, longer hooks, bigger memory), keeps memory accurate and lean (fact checks only on what changed, archive and split proposals), and can install a context-guard hook plus earlier auto-compaction. Use it when the user wants to optimize or cut token use, check context or session size, run or schedule the weekly token checkup, review or clean Claude's memory, asks why sessions are so big or slow, or says "ottimizza i token", "controllo settimanale dei token", "pulisci la memoria", "quanto contesto uso", "token checkup", even without saying "skill". Not for API billing questions or for optimizing an app's own LLM calls.
Datos de origen
- Repositorio
- Matteoikarieth96/token-checkup-skill
- Última actividad en el origen
- 16 de noviembre de 2026 a las 16:14
- Idioma detectado de SKILL.md
- inglés
- Estrellas
- 0
- Forks
- 0
Opciones de instalación
De forma predeterminada está seleccionado el prompt que primero revisa el origen. Puedes cambiar a un comando directo o descargar una copia local.
Revisa los archivos de origen
Lee SKILL.md y los archivos complementarios que muestra SkillsMP antes de decidir si quieres instalarlo.
Mostrando SKILL.md
| name | token-checkup |
|---|---|
| description | Weekly token checkup for Claude Code. Measures how big sessions get and what every session loads before the first answer, catches silent growth (app updates, new connectors, longer hooks, bigger memory), keeps memory accurate and lean (fact checks only on what changed, archive and split proposals), and can install a context-guard hook plus earlier auto-compaction. Use it when the user wants to optimize or cut token use, check context or session size, run or schedule the weekly token checkup, review or clean Claude's memory, asks why sessions are so big or slow, or says "ottimizza i token", "controllo settimanale dei token", "pulisci la memoria", "quanto contesto uso", "token checkup", even without saying "skill". Not for API billing questions or for optimizing an app's own LLM calls. |