Install
openclaw skills install valiron-trust-layerIntercept and authorize outgoing machine-to-machine payments (x402 or similar) using @valiron/sdk trust decisions on the counterparty agent before payment ex...
openclaw skills install valiron-trust-layerAdd a trust gate in front of outgoing agent payments.
Declare and validate runtime prerequisites before enabling the interceptor:
@valiron/sdk.@valiron/sdkVALIRON_API_KEY (optional today; reserved for authenticated deployments)VALIRON_BASE_URL (if using non-default endpoint)VALIRON_TIMEOUT_MS (optional, with safe default)Fail startup (or fail closed for payment endpoints) when required policy/config inputs are missing. If your deployment enforces SDK auth, treat VALIRON_API_KEY as required.
counterpartyAgentId.getWalletProfile(wallet).checkAgent(agentId).getAgentProfile(agentId) when you need reasons/signals, pricing, or audit details.references/decision-policy.md.references/spend-controls.md.references/audit-events.md.Map route decisions to payment actions:
prod: allow payment under normal limits.prod_throttled: allow with reduced caps/rate limits.sandbox: allow only test/sandbox payment rail (or deny prod transfer).sandbox_only: deny outgoing payment.Never authorize payment using free-form model output alone.
For x402-protected purchases or settlement-like flows:
Use endpoint-class fallback from references/fallback-modes.md:
fail-closed.fail-open-guarded with strict caps.Keep fallback mode explicit and versioned.
references/runtime-requirements.mdreferences/decision-policy.mdreferences/spend-controls.mdreferences/fallback-modes.mdreferences/audit-events.mdreferences/error-handling.mdassets/payment-interceptor.tsscripts/validate-payment-policy.mjs