cozempic-doctor
SkillAI & modelsRun health checks on Claude Code configuration and sessions. Use when troubleshooting Claude Code issues. (cozempic — does not shadow Claude Code's built-in /doctor)
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the cozempic-doctor skill
What this skill tells your AI
The instructions your AI receives, as published by ruya-ai/cozempic in plugin/skills/cozempic-doctor/SKILL.md and read by ahel’s review.
Run cozempic health checks:
cozempic doctor
Checks for:
- Trust dialog hang — Windows resume bug where
.claude.jsontrust entry causes hangs - Hooks trust flag — missing
hasTrustDialogHooksAcceptedcausing hooks to silently fail (v2.1.51+ bug) - Agent model mismatch — spawned subagents not inheriting team lead's model causing 403 errors
- Claude.json corruption — truncated or invalid
.claude.jsonfrom concurrent write races - Corrupted tool_use — tool blocks with names >200 chars causing 400 API errors
- Orphaned tool_results — tool_result blocks missing matching tool_use causing 400 API errors
- Zombie teams — stale agent team directories accumulating on disk
- Oversized sessions — sessions that may trigger compaction issues
- Stale backups — old
.bakfiles consuming disk space - Disk usage — total Claude Code storage footprint
To auto-fix detected issues:
cozempic doctor --fix
Signals
- GitHub stars
- 412
- Forks
- 38
- Last commit
- Jul 2026
Advanced
- Catalog kind
- skill
- Gateway key
cozempic-doctor- Source
- github.com/ruya-ai/cozempic