Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OrcaQubits/agentic-commerce-skills-plugins --skill ap2-dev-patternsgit clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dev-patterns)<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dev-patterns"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dev-patterns/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dev-patterns"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-dev-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.01409 |
| Opus 5.5 | $0.00022 | $0.00564 |
| Sonnet 5.5 | $0.00011 | $0.00282 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
ap2-dev-patterns scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AP2 Development Patterns
Before writing code
Fetch live docs:
- Fetch
https://ap2-protocol.org/ap2/specification/for the latest protocol details - Fetch
https://ap2-protocol.org/overview/for UCP integration patterns - Fetch
https://ap2-protocol.org/overview/for x402 crypto integration - Web-search
site:github.com google-agentic-commerce AP2 samplesfor reference architectures
Conceptual Architecture
Multi-Agent Payment Architecture
The standard AP2 architecture involves four agents communicating via A2A:
┌──────────────────────────────────────────────────┐
│ User │
│ (trusted device surface) │
└──────────┬───────────────────────────────────────┘
│ intent + signatures
┌──────────▼───────────────────────────────────────┐
│ Shopping Agent (SA) │
│ Orchestrator — coordinates the full flow │
└──┬──────────────┬────────────────────────────────┘
│ │
│ A2A │ A2A
│ │
┌──▼──────┐ ┌───▼──────────┐
│ Merchant │ │ Credentials │
│ Agent │ │ Provider │
│ │ │ │
│ catalog │ │ payment │
│ cart │ │ methods │
│ signing │ │ tokenization │
└────┬─────┘ └──────────────┘
│
│ (Merchant → MPP)
│
┌────▼─────────────┐
│ Merchant Payment │
│ Processor (MPP) │
│ │
│ authorization │
│ settlement │
│ Payment Mandate │
│ challenges │
└────────┬──────────┘
│
┌────▼──────────┐
│ Network/Issuer │
│ (Visa, MC, │
│ banks) │
└────────────────┘
Important: The SA communicates with the Merchant and the CP via A2A. The Merchant communicates with the MPP. The SA does not directly communicate with the MPP.
UCP Integration Pattern
UCP (Universal Commerce Protocol) operationalizes AP2:
- UCP's Checkout object maps to a commerce-level checkout flow
- UCP's
checkout_mandateis distinct from (but related to) AP2's Checkout Mandate —checkout_mandateis a UCP-specific concept that wraps the commerce checkout authorization, while AP2's Checkout Mandate is the cryptographically signed VDC binding user consent to specific transaction terms - UCP's
/complete_checkoutAPI = AP2's payment authorization step - PaymentMandate (constructed by the MPP) proves payment authorization for the network/issuer
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed 2bb310aac12a
- 1mo ago First seen · 154 lines · 54 tokens per session scan A 7bbff95267e3
ap2-dev-patterns is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,409 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
metengine-data-agent
Real-time smart money analytics API for Polymarket prediction markets, Hyperliquid perpetual futures, and Meteora Solana LP/AMM pools. 63 endpoints. Pay-per-request via x402 on Solana Mainnet USDC. No API keys.
okx-agent-payments-protocol
Use when an agent hits HTTP 402 / payment-required, or the user mentions x402, x402Version, X-PAYMENT, PAYMENT-REQUIRED, PAYMENT-SIGNATURE, WWW-Authenticate: Payment, permit2, upto, metered billing, a payment channel / voucher / session, channelId / channelid, opening / closing / topping up / settling / refunding a…
write-contract
Write production-quality GenLayer intelligent contracts. Always pins concrete GenVM runner version hashes and never uses local-only test/latest runner aliases. Covers equivalence principles, storage rules, LLM resilience, and cross-contract interaction.
jupiter-lend
Interact with Jupiter Lend Protocol. Read-only SDK (@jup-ag/lend-read) for querying liquidity pools, lending markets (jlTokens), and vaults. Write SDK (@jup-ag/lend) for lending (deposit/withdraw) and vault operations (deposit collateral, borrow, repay, manage positions).
okx-dapp-discovery
Plugin router for 20 third-party DeFi protocols (Polymarket, Aave, Hyperliquid, PancakeSwap, Morpho, Raydium, Curve, Compound, Pendle, Lido, ether.fi, GMX, Kamino, Orca, Meteora, Clanker, pump.fun, Uniswap) and their protocol-native tokens (HYPE, HLP, eETH, weETH, stETH, wstETH, LDO, GHO, CAKE, CRV, COMP, RAY, ETHFI…
agent-wallet
Give the AI agent its own EVM wallet with admin-controlled policies the agent CANNOT bypass even under prompt injection. Encrypted keystore (AES-256-GCM, scrypt KDF), policy file the agent has no tool to write, deterministic policy gate on every signing operation, optional local HTTP dashboard. Triggers: agent wallet…