Skip to main content
skill CX Codex

fleet-auditor — Claude Code skill: token audit and installation

This skill checks agent systems for token waste and estimates potential savings. Use it to review usage across a fleet of agents.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add alexgreensh/token-optimizer --skill fleet-auditor -a claude-code
Open on GitHub

What fleet-auditor does

The skill detects installed agent systems, gathers token-usage data from sessions, and looks for waste. It runs detection, a session scan, an audit, then prepares findings with severity, estimated monthly savings, and a suggested fix. It does not read or expose message content.

The workflow uses fleet.py with python3 and can optionally create an HTML dashboard. Model prices are needed to calculate dollar amounts. For Codex and systems outside the Claude family, the skill consults a report template that covers cost caveats; without model pricing, dollar savings cannot be calculated.

What it helps with

  • detect installed agent systems
  • collect token usage from sessions
  • find waste and estimate recurring monthly savings
  • pair each finding with a suggested fix
  • create an HTML cost dashboard

Example prompts for the agent

  • Audit my installed agent systems and identify token waste.
  • Scan session data and estimate monthly savings from the findings.
  • Create an HTML dashboard of token costs.

How to install fleet-auditor

1Skills CLI (Vercel)

npx skills add alexgreensh/token-optimizer --skill fleet-auditor -a claude-code

2Manually: put the files in place

~/.claude/skills/fleet-auditor/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/fleet-auditor/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about fleet-auditor

How do I install fleet-auditor in Claude Code?

Run npx skills add alexgreensh/token-optimizer --skill fleet-auditor -a claude-code. The skill file is available at ~/.claude/skills/fleet-auditor/SKILL.md.

What does fleet-auditor do?

It detects agent systems, gathers token usage, and identifies waste. Its report ranks findings by severity and includes monthly savings estimates and suggested fixes.

Does the audit need model prices?

Yes. Prices are needed to calculate savings in dollars. For Codex and systems outside the Claude family, the skill uses a report template with cost caveats.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set3

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor