token-efficiency-report

Measure Claude Code and carrier plane token usage and calculate orchestration overhead.

16|2|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/sbluemin/fleet-harness --skill token-efficiency-report
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: token-efficiency-report
Source: https://github.com/sbluemin/fleet-harness/tree/main/.agents/skills/token-efficiency-report
Command: npx skills add https://github.com/sbluemin/fleet-harness --skill token-efficiency-report

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill provides a detailed report on the token efficiency of a Fleet operation, comparing the use of Claude Code by the Admiral and the carrier plane's usage.

Core Features & Use Cases

  • Token Efficiency Analysis: Measures the token consumption of Claude Code and carrier planes.
  • Orchestration Overhead: Calculates the coordination overhead in tokens.
  • Counterfactual Estimate: Models the cost if the Admiral performed the work solo.
  • Deliverable Size: Measures the size of the deliverable against a base reference.
  • Use Case: Ideal for operations requiring a detailed analysis of token usage and cost savings in a Fleet environment.

Quick Start

Run the token-efficiency-report skill with the required inputs to generate a report on the current session's token efficiency.

Frequently Asked Questions about token-efficiency-report

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

FAQPage Schema
How do I measure token efficiency in a Claude Code Fleet operation?

Token efficiency is measured by analyzing session transcripts and engine logs to compare Claude Code token usage against carrier plane consumption, yielding a detailed operational efficiency report.

How do I calculate orchestration overhead in tokens for carrier plane operations?

Orchestration overhead is calculated by comparing the Admiral's coordination tokens against the carrier plane's execution tokens, using data extracted from session transcripts and engine logs.

Can I model solo execution costs to compare against Fleet operation token usage?

Yes, you can model a counterfactual solo execution cost to compare against Fleet token usage by evaluating deliverable size in a git repository against a base reference.

What inputs are required to generate a token efficiency report for Claude Code?

Generating a token efficiency report requires access to session transcripts, engine logs, and a git repository to compare deliverables and calculate orchestration overhead.

What is the best way to analyze cost savings from using a carrier plane versus solo execution?

The best way to analyze cost savings is by generating a counterfactual estimate that models solo execution costs and contrasts them with actual carrier plane token usage and deliverable size.