start_context_watcher
Monitor real-time token usage for a Cerebro session. Tracks every tool call's estimated tokens and provides handover recommendations to prevent context overflow.
Instructions
Open a persistent terminal showing real-time token usage. Tracks every Cerebro tool call with estimated tokens and handover recommendation.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"sessionId": "<sessionId>"
},
"name": "start_context_watcher"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sessionId | Yes | Session ID to watch | |
| noTerminal | No | If true, tracks tokens silently without opening a terminal window. Stats available via get_context_health. Default: false. | |
| autoCloseTerminal | No | If true, terminal closes automatically when stop_context_watcher is called. Default: false (terminal stays open). |