A developer has created a shell script called `usage-breakdown.sh` to analyze token usage in Claude Code, as the built-in `/usage` command only provides per-model cost totals. The script parses `transcript.jsonl` files, which record every operation during a session, to tally call counts for specific Skills, Agents, and MCP servers. This detailed breakdown helps users identify which specific functions are driving up their Claude Code bills, offering more granular insights than the default tooling. AI
IMPACT Enables users to gain finer-grained control and understanding of their AI tool costs.
RANK_REASON The item describes a custom script developed to provide enhanced functionality for an existing product.
Read on dev.to — Claude Code tag →
- Claude Code
- Claude (Opus 4.8)
- Claude Sonnet 4.6
- AI agent
- MCP
- Skill
- transcript.jsonl
- usage-breakdown.sh
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →