uvs-lite

Name: uvs-lite
Availability: InStock
Author: utsav

Toggle lite mode across UVS sessions via on/off/status commands.

2|Updated Apr 11, 2026

Search Tags:#verbosity #token-efficiency #prompt-injection #state-file #lite #uvs

Ready to run

npx skills add https://github.com/utsavanand/uv-suite --skill uvs-lite

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: uvs-lite
Source: https://github.com/utsavanand/uv-suite/tree/main/skills/uvs-lite
Command: npx skills add https://github.com/utsavanand/uv-suite --skill uvs-lite

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Toggle lite mode to enforce terse AI responses across UVS sessions, saving tokens and keeping conversations focused.

Core Features & Use Cases

Persistent lite-state across turns
On/off/status control via simple commands
Reduces noise in long-running sessions and dashboards

Quick Start

Enable lite mode by issuing '/uvs-lite on' and return to normal once you say '/uvs-lite off'.

Frequently Asked Questions about uvs-lite

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I make AI responses terse and save tokens during long chats?▼

To make AI responses terse and save tokens, you can enable a persistent lite mode that enforces concise outputs across sessions. This reduces noise and keeps interactions focused by injecting terse prompts via a UserPromptSubmit hook.

How do I toggle lite mode on and off to control AI verbosity?▼

You can toggle lite mode on and off to control AI verbosity by issuing simple commands. Use '/uvs-lite on' to enable terse responses and return to normal output by saying '/uvs-lite off'.

Does AI verbosity reduction persist across multiple chat turns?▼

Yes, AI verbosity reduction persists across multiple chat turns. The setting is maintained in a state file located at .uv-suite-state/lite-mode.txt, ensuring the terse output mode remains active throughout long-running sessions.

What is the best way to check the current token-efficiency status of my session?▼

The best way to check the token-efficiency status of your session is to use the status command. By issuing '/uvs-lite status', you can query the current state file to see if terse response injection is active.

When should I use a lite mode approach for prompt injection?▼

You should use a lite mode approach for prompt injection during token-limited interactions, long-running chats, or when concise responses are required. It is specifically designed to reduce noise in dashboards and focus conversations.