ltm

Toggle low-token mode for single commands or entire Claude sessions.

1|Updated Mar 14, 2026

Search Tags:#session-management #prompt-control #ltm #sentinels #low-token-mode #command-toggle

Ready to run

npx skills add https://github.com/tesseract-ripple/claude-research-config --skill ltm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ltm
Source: https://github.com/tesseract-ripple/claude-research-config/tree/main/skills/ltm
Command: npx skills add https://github.com/tesseract-ripple/claude-research-config --skill ltm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

LTM helps manage token usage by toggling a low-token mode that affects prompts for the current command or the rest of the session.

Core Features & Use Cases

Check current state via sentinel files to determine if LTM is active, disabled, or overridden.
Toggle LTM with arguments such as status, once, session, on, or re-enable to control scope.
Sentinel file guidance ensures explicit user actions and persistent behavior across prompts.

Quick Start

Toggle low-token mode by running the ltm command with an argument (status, once, session, on) to adjust behavior.

Frequently Asked Questions about ltm

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

FAQPage Schema

How do I control prompt cost and manage token usage during a Claude session?▼

You can control prompt cost by toggling low-token mode, which modifies prompt behavior for a single command or an entire session using sentinel files to persistently track and enforce your token reduction settings.

What is low-token mode and how does it affect my prompts?▼

Low-token mode is a toggleable state that alters prompt behavior to reduce token consumption, affecting either the current command or all subsequent prompts in a session by relying on sentinel files to maintain explicit and predictable state changes.

How do I check if low-token mode is currently active or disabled?▼

Check the low-token mode status by running the command with the status argument, which reads the current sentinel files to determine whether the mode is active, disabled, or overridden for your session.

Can I apply low-token mode to just one command instead of the whole session?▼

Yes, you can apply low-token mode to a single command by using the once argument, which temporarily overrides the session state for that specific prompt without permanently changing the behavior for the rest of the session.

What is the best way to toggle low-token mode on for all subsequent prompts?▼

The best way to enable low-token mode for all subsequent prompts is to use the session or on argument, which updates the sentinel files to ensure persistent token reduction behavior across the rest of your active session.

How do I re-enable prompt behavior after overriding low-token mode?▼

To re-enable normal prompt behavior after overriding low-token mode, use the re-enable argument, which adjusts the sentinel files to restore the default or session-level token management settings predictably.