cortex_confirm_destructive
Blocks destructive actions until human confirmation, using a red modal in the dashboard or a terminal prompt.
Instructions
Block dangerous actions until human confirms. Shows red modal in dashboard. Falls back to terminal if no dashboard.
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": {
"action": "<action>"
},
"name": "cortex_confirm_destructive"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Description of the destructive action (e.g., "delete file src/auth.py") | |
| target | No | What will be affected (e.g., file path, DB table, feature name) |