OpenChainGraph Suite · Verify-Only Chain

Agentic Payment Mandate Lint

Note (dated 2026-08-04): a chain composes independent computations performed in an analytical order. No step's output is carried into the next step by the execution model; each step computes from its own declared inputs. This is true of every chain on this site, including chains whose per-step copy below reads as a data handoff.

A2A agent card validation > x402 extension mandate validation > AP2 mandate credential build. A verify-then-build lint chain for agentic payment mandates supplied by the caller: checks the calling agent's card, checks its x402 payment-extension mandate, then builds the AP2 verifiable-credential representation. Read-only linting only: no payment execution, no wallet or custody action, no live network call.

OpenChainGraph · 3 Steps compliance mandate Hash-Anchored §4 chain_depth:3 Client-Side · Zero PII Verify/Lint Only · No Execution
Chain Topology: A2A Agent Card Validator → A2A X402-Extension Mandate Validator → Google AP2 Mandate Builder
§4 Execution Hash · Chain Definition Anchor
execution_hash:computing…
Market Rationale
Buyer: Agentic Commerce / A2A Payments Platform Team
Forcing function: A2A agent-card and x402 payment-extension checks, plus a Google AP2 mandate credential, are the shape both rails require before an agent-initiated payment mandate is trusted. This chain lints all three in sequence.
Chain Stages · 3 Steps
1 ROOT node
A2A Agent Card Validator & Extension Checker art-25-a2a-agent-card-validator
verdict, score, and has_ap2_extension establish whether the calling agent's card is well-formed and AP2-capable before its payment mandate is checked.
↓
2 D2 node
A2A x402-Extension Mandate Validator art-31-a2a-x402-extension-mandate-validator
verdict, pass_count, and fail_count record whether the caller-supplied x402 payment-extension mandate checks out before the AP2 credential is built from it.
↓
3 TERMINAL · D3 node
Google AP2 Mandate Builder art-16-google-ap2-mandate-builder
vdc and vdc_stage are the chain output, the AP2 W3C verifiable-credential mandate built from the caller's own inputs, gated behind the two prior lint passes.
Export Artifacts
Download the §4 chain definition artifact (hash-anchored composite JSON) or the §13.11 W3C Verifiable Credentials view. Both derive from the chain definition; no new hash is minted. Available after hash computation.

Ask your agent

Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this whole workflow on the server and check one field that answers a real question.

Question: Does the agent card authorise the amount this x402 payload asks us to settle?
Run the AINumbers MCP tool `run_chain` with {"chain":"agentic-payment-mandate-lint"} and read `art-31-a2a-x402-extension-mandate-validator.verdict`.
Re-run with `inputs` for `art-31-a2a-x402-extension-mandate-validator`, reusing the values that result echoed, with `payment_payload` changed so maxAmountRequired is 5000, above the mandate cap. Compare the same field.
Verify: call `verify_execution_hash` (https://mcp.ainumbers.co/mcp) with `claimed_hash` set to `composite_execution_hash` and the full `composite_artifact`.
Ledger, for a human re-check: https://ledger.ainumbers.co/
PII rule: send synthetic or anonymised inputs only. The MCP server runs these kernels and logs no payloads.
Chain page: https://ainumbers.co/chaingraph/chains/agentic-payment-mandate-lint.html