agent-plan-verifier

Verify an autonomous agent plan before execution for missing preconditions, destructive steps, unsafe ordering, goal misalignment, constraint violations, and repair actions, returning a bounded GO/WARN/BLOCK result.

Price: $0.72 USDC equivalent
Endpoint: POST /v1/agent-plan-verifier
Network: Base mainnet · eip155:8453
Asset: USDC
MCP tool: agent-plan-verifier
External payability: PASS · 2026-10-08T19:55:01.298Z

When an agent should use it

verify an autonomous agent plan before execution
check AI agent plan ordering constraints and safety
agent plan preflight GO WARN BLOCK
find missing preconditions in an agent execution plan

Input schema

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000
    },
    "plan": {
      "type": "array",
      "minItems": 1,
      "maxItems": 64,
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 4000
      }
    },
    "constraints": {
      "type": "array",
      "maxItems": 32,
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 4000
      }
    }
  },
  "required": [
    "goal",
    "plan"
  ],
  "additionalProperties": false
}

Example request

{
  "goal": "Safely deploy the tested Worker change",
  "plan": [
    "Inspect repository status",
    "Run focused tests",
    "Deploy through the guarded workflow"
  ],
  "constraints": [
    "Do not deploy before validation"
  ]
}

Example output

{
  "verdict": "GO",
  "score": 1,
  "missing_preconditions": [],
  "unsafe_steps": [],
  "ordering_errors": [],
  "constraint_violations": [],
  "repairs": []
}

x402 flow

POST /v1/agent-plan-verifier
→ HTTP 402 + PAYMENT-REQUIRED
→ buyer authorizes locally
→ retry same request with PAYMENT-SIGNATURE
→ one governed execution + machine-readable JSON

Discovery: OpenAPI · x402 · llms.txt

A valid 402/payability probe is operational evidence, not proof of independent demand, future settlement, or semantic correctness.