token-harness

Community

Transparent token tracking and observability for AI CLIs.

AuthorAesopScott
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill offers comprehensive visibility into AI CLI model calls, providing accurate token usage tracking, prompt/input auditing, and usage metadata for token accountability and analysis.

Core Features & Use Cases

  • Token Usage Observation: Track and log model calls, input/output payloads, and stdout/stderr from AI providers.
  • Usage Metadata Analysis: Report detailed information on token consumption by providers and local estimations.
  • Use Case: For an organization seeking to audit their token usage across various AI services, this skill can be integrated to provide a granular breakdown of each CLI interaction's token expenditure.

Quick Start

Utilize the token-harness Skill to monitor and report the token usage for the latest Codex message interaction.

Dependency Matrix

Required Modules

pythontiktokenlangsmithphoenix

Components

scriptsreferences

💻 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-harness
Download link: https://github.com/AesopScott/central/archive/main.zip#token-harness

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 620,000+ vetted skills library on demand.