token-conservation

Community

Optimize token usage, extend your AI's context window.

Authorathola
Version1.0.0
Installs0

System Documentation

What problem does it solve?

High token usage can quickly exhaust AI context windows and incur unnecessary costs. This skill enforces ultra-conservative token usage by minimizing prompt exposure, delegating bulk work, and tracking quotas.

Core Features & Use Cases

  • Quota Check: Monitors session duration, weekly usage, and remaining budget.
  • Context Planning: Decides which files/snippets to expose, preferring slices over whole files.
  • Delegation Check: Evaluates if heavy lifting can be delegated to external tools (e.g., Qwen MCP).
  • Compression Review: Summarizes prior steps, removes redundant history, and collapses logs.
  • Use Case: Before a long analysis, use this skill to check your token budget, plan to expose only relevant code snippets, and consider delegating large file summaries to another AI to save Claude's context.

Quick Start

At the start of your session, check your current token quota and set a maximum token target for your task.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: token-conservation
Download link: https://github.com/athola/claudenomicon/archive/main.zip#token-conservation

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository