PulseAugur
EN
LIVE 13:12:59

Claude Code users can now track detailed skill and agent usage

A developer has created a script to analyze Claude Code's usage beyond the basic cost information provided by the platform. The script parses the `transcript.jsonl` file, which logs all interactions, to provide a detailed breakdown of how often specific skills, agents, and MCP servers are called. This granular data allows users to optimize costs and monitor the health of their Claude Code environment by identifying which components are used most frequently. AI

IMPACT Enables granular cost optimization and environment health monitoring for Claude Code users.

RANK_REASON The item describes a custom script for analyzing usage data from a specific AI product, which is a tool-related development.

Read on dev.to — Claude Code tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Claude Code users can now track detailed skill and agent usage

COVERAGE [1]

  1. dev.to — Claude Code tag TIER_1 English(EN) · Lily ·

    Parse transcript.jsonl Directly to See What's Actually Being Called

    <p>Claude Code's <code>/usage</code> tells you how much you're spending, but not what you're spending it on. In my previous post, "<a href="https://zenn.dev/bokuwalily/articles/agent-invocation-log" rel="noopener noreferrer">Logging Agent invocations to a file and piping them to …