Diagnose

This gives you a clear readout of your Claude Code session's token usage and what's eating up space. Run it when things feel sluggish or you're curious how close you are to the context limit. You get actual token counts, a visual percentage bar against the 200K or 1M window, and a breakdown of what's bloating things (progress ticks, file snapshots, thinking content, old tool results). The top 10 largest messages list is surprisingly useful for spotting that one massive paste or API response killing your session. It also estimates what you'd save with different cleanup levels, which takes the guesswork out of deciding whether to run a trim.

GitHub stars: 332
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add ruya-ai/cozempic --skill diagnose --agent claude-code

Installs into .claude/skills of the current project.

Files

Run a diagnosis on the current session:

cozempic current --diagnose

The output includes:

Weight: total session size in bytes and message count
Tokens: exact token count (from usage data) or heuristic estimate
Context bar: visual bar showing % of the detected context window (200K or 1M)
Vital signs: progress ticks, file history snapshots, system reminders, thinking content, signatures, tool results
Message type breakdown: bytes per message type
Top 10 largest messages: biggest bloat contributors
Estimated savings by prescription: what gentle/standard/aggressive would save

Always surface the token count and context % to the user. If context is above 60%, suggest running /cozempic:treat with a prescription recommendation:

Under 5MB: gentle
5-20MB: standard
Over 20MB: aggressive

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly