agent_preflight
InactiveTool of io.github.digitalweb33333-creator/x402-endpoints
Safety preflight before an agent runs a DESTRUCTIVE, costly or IRREVERSIBLE action (delete, deploy, transfer funds, publish, overwrite): risk assessment + reversibility check + timing + CLEAR/LIMIT/REVIEW/BLOCK verdict + a cryptographically SIGNED ClearancePacket (decision, approved amount, policy version, evidence hash, expiry, rationale) the agent keeps as proof of authorization. Should I run this action, or stop and ask a human? Stops a mistake far costlier than the call price. Agent action guardrail / clearance / human-in-the-loop gate. Price: $0.25 per call (x402 payment, USDC on Base mainnet).
Parameters schema
{
"type": "object",
"required": [
"action"
],
"properties": {
"action": {
"type": "string",
"description": "Action about to run, e.g. 'delete the production users table'"
},
"target": {
"type": "string",
"description": "Optional target (table, address, repo, recipient)"
},
"context": {
"type": "string",
"description": "Optional extra context (environment, prior approval)"
},
"amount_usd": {
"type": "number",
"description": "Monetary stake in USD if applicable, e.g. 250"
},
"reversible": {
"type": "boolean",
"description": "Optional caller hint: is the action reversible?"
},
"action_type": {
"type": "string",
"description": "Optional: delete|deploy|send|spend|transfer|publish|email|overwrite|approve|rotate|shutdown|other"
}
}
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
io.github.digitalweb33333-creator/x402-endpoints
https://github.com/digitalweb33333-creator/x402-endpoints
1/7 registries