auto-insights
Show or configure auto-generated insights from the claudectl brain — friction patterns, suggested rules, and workflow improvements
Show status of all active Claude Code sessions (cost, health, context usage)
$ npx -y skills add mercurialsolo/claudectl --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/sessionsContext preview
What this command does when you run it.
Show status of all active Claude Code sessions (cost, health, context usage)
name: sessions description: Show status of all active Claude Code sessions (cost, health, context usage)
Run `claudectl --list` to get the current status of all active Claude Code sessions. If no sessions are found, let the user know.
If the user wants more detail, you can also run `claudectl --json` for machine-readable output with full session data including token counts, cost, burn rate, and context window usage.
For session health issues (loops, stalls, cost spikes, context saturation), run `claudectl --json` and look at the `decay_score`, `has_file_conflict`, and `last_tool_error` fields.
Present the results in a concise table showing: project name, status, cost, context %, and any health warnings.
Swarm orchestration for claude code agents with a local brain that steers based on your preferences
Show or configure auto-generated insights from the claudectl brain — friction patterns, suggested rules, and workflow improvements
Show claudectl brain learning metrics — accuracy, correction rate, and effectiveness
Set this Claude session's agent-bus role so other sessions can address it (e.g. /role frontend, /role backend, /role tester)
Show Claude Code spend summary — total cost, per-session breakdown, and burn rate