llm-agent-token-audit

Community

Slim down agent prompts to save token costs.

Authordragonkid
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps teams reduce fixed per-call token overhead by auditing LLM agent prompts and workspace files to eliminate bloated prompts, unused assets, and unnecessary components.

Core Features & Use Cases

  • Systematic prompt overhead audit: quantify token usage and identify waste such as dead files, placeholder templates, and redundant content.
  • Framework-ready recommendations: prioritize deletions and config changes to minimize prompt size while preserving essential behavior.
  • Use Case: When adding new skills/tools in an agent, run the audit to strip excess workspace files and optimize prompts to improve latency and cost.

Quick Start

Run the audit workflow on your current project to prune prompt components while preserving essential behavior.

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: llm-agent-token-audit
Download link: https://github.com/dragonkid/dotfiles/archive/main.zip#llm-agent-token-audit

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

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.