Excessive Token Usage: Cursor auto-loads too many "Skills" from ~/.claude/skills at conversation start

Hey, thanks for the detailed report and the screenshot. Confirmed: the recursive skills scanner doesn’t filter hidden directories inside ~/.claude/skills/, so anything in .hermes/, .opencode/, .gstack/, and similar subfolders from other agent CLIs gets pulled into context. I’ve reported this internally.

On dedup: normalization works for ~/.claude/skills vs ~/.cursor/skills, but GStack stores skills in ~/.agent/skills (no s at the end), and we only detect ~/.agents/skills. That’s why duplicates don’t collapse in your case. Flagged this too.

No fix yet. Workaround: turn off Include third-party Plugins, Skills, and other configs in Settings → Rules, Skills, Subagents. This will stop loading from the .claude/, .codex/, .agents/ roots entirely, including skills you might want, so if you need them you can temporarily copy specific folders into ~/.cursor/skills/.

There’s also a related thread Toggle (or allowlist) for Agent Skills roots — stop loading ~/.claude/skills and ~/.codex/skills when I only want .cursor / .agents about more granular control over skill roots. If you’re interested, please upvote it, it helps with prioritization. No ETA yet, we’ll post an update here when we have one.