Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Intercept and authorize outgoing machine-to-machine payments (x402 or similar) using @valiron/sdk trust decisions on the counterparty agent before payment ex...
Intercept and authorize outgoing machine-to-machine payments (x402 or similar) using @valiron/sdk trust decisions on the counterparty agent before payment ex...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Add a trust gate in front of outgoing agent payments.
Declare and validate runtime prerequisites before enabling the interceptor: Node.js runtime compatible with your app and @valiron/sdk. Installed dependencies: @valiron/sdk Your payment rail package(s) (x402 or equivalent) used by the host app. Configuration/credentials (via secret manager or env vars): VALIRON_API_KEY (optional today; reserved for authenticated deployments) VALIRON_BASE_URL (if using non-default endpoint) VALIRON_TIMEOUT_MS (optional, with safe default) Policy/config inputs: Decision policy JSON (route-to-action matrix) Spend limit defaults and per-route overrides 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.
Extract counterparty identity from the payment request. Prefer counterpartyAgentId. Support wallet fallback with getWalletProfile(wallet). Evaluate trust with Valiron. Fast path: checkAgent(agentId). Full path: getAgentProfile(agentId) when you need reasons/signals, pricing, or audit details. Apply deterministic decision policy from references/decision-policy.md. Enforce spend controls from references/spend-controls.md. If allowed, continue to payment initiation (x402 challenge creation or equivalent flow). If blocked/restricted, return explicit denial/degrade reason. Log outcome using 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: Trust-check counterparty identity. Evaluate route + spend policy. If denied, abort before creating payment commitment. If allowed, generate/send x402 payment payload. Record authorization decision + amount + result.
Use endpoint-class fallback from references/fallback-modes.md: High-risk payment actions: fail-closed. Low-risk/test actions: optional fail-open-guarded with strict caps. Keep fallback mode explicit and versioned.
Runtime + credential checklist: references/runtime-requirements.md Decision matrix: references/decision-policy.md Spend/risk controls: references/spend-controls.md Fallback guidance: references/fallback-modes.md Audit schema: references/audit-events.md Error handling: references/error-handling.md Interceptor template: assets/payment-interceptor.ts Policy validator: scripts/validate-payment-policy.mjs
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.