/spend
Show Claude Code spend summary — total cost, per-session breakdown, and burn rate
$ npx -y skills add mercurialsolo/claudectl --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/spend
Context preview
What this command does when you run it.
Show Claude Code spend summary — total cost, per-session breakdown, and burn rate
Command definition
spend.mdname: spend description: Show Claude Code spend summary — total cost, per-session breakdown, and burn rate args: "[time-window]"
Show the user's Claude Code spending. The optional argument is a time window (e.g., "8h", "24h", "7d"). Default is "24h".
Run these commands to gather spend data:
1. `claudectl --stats --since {{time_window}}` for aggregated statistics (total cost, token counts, per-project and per-model breakdown) 2. `claudectl --list` for current active session costs and burn rates
Present the results showing:
- Total spend in the time window
- Active session costs and burn rates
- Per-project breakdown if available
- Today's spend vs weekly average if the window is large enough
Orchestrate a swarm of Claude Code agents with a local brain that learns from you.
Other commands on claudectl.
- /auto-insights
Show or configure auto-generated insights from the claudectl brain — friction patterns, suggested rules, and workflow improvements
Open command - /brain-stats
Show claudectl brain learning metrics — accuracy, correction rate, and effectiveness
Open command - /brain
Toggle the claudectl brain gate on/off/auto for this session
Open command - /inbox
Drain pending agent-bus messages addressed to this session's role
Open command - /role
Set this Claude session's agent-bus role so other sessions can address it (e.g. /role frontend, /role backend, /role tester)
Open command - /sessions
Show status of all active Claude Code sessions (cost, health, context usage)
Open command