Usage Stats Dashboard
The Usage Stats Dashboard is a full-page view of what your agents are spending. Open it from the chart icon in the title bar (beside the Agent Monitor’s activity icon) or with Ctrl+Shift+U / Cmd+Shift+U, and close it the same way. It shows cost, tokens, sessions, tool calls, line churn, and burn rate for the current project or for every project on the machine, over any time range from the trailing two hours to all time.
Added in v0.30.0, the dashboard replaces the old status-bar usage strip. The status bar now shows only the agent and task counts; every usage metric lives here.
A scope picker switches between two views:
- Current project - usage for the active project only.
- All projects - an app-wide rollup across every project registered on the machine, including a per-project comparison table so you can see which project is spending the most.
The selected scope is one global value: it persists across project switches and app restarts.
Ranges and Metrics
Section titled “Ranges and Metrics”Pick a time range: Live (the trailing 2 hours), Today, This Week, This Month, All Time, or a custom month. Click a day in a chart to drill into that single day. Like the scope, the selected range persists globally across restarts.
A metric toggle switches every chart and tile between cost and tokens, so teams that care about dollars and teams that care about context budgets both get a first-class view.
KPI Tiles and Breakdowns
Section titled “KPI Tiles and Breakdowns”Three hero tiles show Tokens, Cost, and Burn Rate (a per-hour spending rate with its own sparkline), followed by tiles for sessions, tool calls, and lines changed. Each tile carries a “vs previous period” delta so you can tell whether this week is heavier than last week at a glance.
Below the tiles, the usage series breaks down by model, by agent, and by reasoning effort, so a mixed board (some tasks on Opus at high effort, others on a lighter model) shows exactly where the spend goes.
Durable Ledgers
Section titled “Durable Ledgers”Totals are read from durable usage ledgers, not from live session records, so they survive task and session deletion. Deleting a finished task does not erase what it cost.
Pop Out
Section titled “Pop Out”The dashboard is a detachable surface: a pop-out button moves it into its own OS-level window, so you can keep it on a second monitor while you work the board. The window remembers its size, position, and monitor between openings.
For Agents and Automation
Section titled “For Agents and Automation”The same data is available to agents through the MCP server tool kangentic_get_usage_stats, which returns tokens, cost, burn rate, and by-model / by-agent usage for a project or all projects over a time range.
Two config keys back the dashboard’s persistence: usageStatsPeriod (the saved range) and usageStatsScope (the saved scope). See the Configuration Reference for details.
Next steps
Section titled “Next steps”See also:
- Notifications - the status bar and attention signals
- Session Persistence - where per-session usage records come from
- MCP Server - query usage stats from an agent
- Hotkeys - rebind the dashboard toggle
Kangentic is free and open source. A star helps other people find it.
Star on GitHub