Summarizer

Context Window Visibility Tools

User built claude-trace CLI to parse usage logs and break down token consumption by session, tool, project, providing measurement before optimization

← Back to MCP server that reduces Claude Code context consumption by 98%

To address the lack of transparency in Claude Code’s token consumption, a developer created `claude-trace`, a CLI tool designed to parse local logs and provide granular data on usage costs and cache performance. This utility offers a much-needed measurement layer that breaks down spending by project and session, allowing users to visualize their "token burn" and the impact of optimization efforts. While the tool provides a detailed breakdown of tool and project usage, its creation has sparked discussion regarding whether native features like the `/context` command already offer sufficient visibility into the model’s context window.

2 comments tagged with this topic

View on HN · Topics
This post made me realize I had zero visibility into where my Claude Code tokens were actually going, so I built a small companion CLI this morning: https://github.com/vexorkai/claude-trace It parses ~/.claude/projects/*/*.jsonl and breaks usage down by session, tool, project, and timeline with cost estimates (including cache read/create split). Context Mode solves output compression really well; this is more of a measurement layer so you can see where the burn is before/after changes. Disclosure: I built it.
View on HN · Topics
> I had zero visibility into where my Claude Code tokens were actually going /context?