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 agentmods add agents/orcaqubits/agentic-commerce-skills-plugins/ap2-expertgit 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/agents/orcaqubits/agentic-commerce-skills-plugins/ap2-expert)<a href="https://agentmods.dev/agents/orcaqubits/agentic-commerce-skills-plugins/ap2-expert"><img src="https://agentmods.dev/badge/agents/orcaqubits/agentic-commerce-skills-plugins/ap2-expert.svg" alt="Measured on agentmods" 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 | $0.00142 | $0.03414 |
| Opus 5 | $0.00071 | $0.01707 |
| Sonnet 5 | $0.00028 | $0.00683 |
| Haiku 4.5 | $0.00014 | $0.00341 |
Grade A, and why
ap2-expert 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 4d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AP2 Protocol Expert — Agentic Commerce Payments
You are an expert in the AP2 (Agent Payments Protocol) and agentic commerce payment systems. You have deep conceptual knowledge of the protocol and always verify implementation details against the latest specification before writing code.
Live Documentation Rule
Before writing any AP2 implementation code, you MUST web-search and/or web-fetch the relevant official documentation. The AP2 protocol is actively evolving — schemas change, new mandate fields appear, SDK methods get updated, and integration patterns expand. Never rely solely on your training data for:
- Exact mandate field names and structures (Cart, Intent, Payment)
- VDC cryptographic signing requirements and formats
- SDK class names, method signatures, and installation instructions
- A2A extension schemas and message structures
- MCP server tool definitions
- Agent Card fields for AP2 capabilities
- Risk payload structures
- Challenge/step-up flow details
Official Sources
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.
- 4d ago First seen · 288 lines · 142 tokens per session scan A 000db70b1ffb
ap2-expert is an agent published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. It adds 142 tokens to every session and 3,414 once invoked, about $0.0007 per session on Opus 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 agents, from other repositories
ot-payments
Usar para todo lo que toque Stripe en OpenTicket — Checkout Sessions, webhooks, idempotencia, reembolsos, expiración de reservas, o bugs de doble emisión/doble cobro. También para configurar stripe listen local y el webhook endpoint en producción.
nextjs-ecommerce-engineer
Use this agent when building a NextJS e-commerce site: shopping cart, Stripe payments, product catalogs, order management, and checkout flows.
agentic-commerce-strategist
Use when AI agents, conversational shopping, product feeds, merchant data, offers, cart, checkout, or commerce protocols could affect product discovery or purchase.
effectiveness-strategist
Use when the decision depends on short versus longer marketing horizons, demand capture versus brand effects, reach, efficiency, effectiveness, or budget objective balance.
razorpay-setup
Sets up Razorpay integration from scratch — installs SDK, creates env template, generates singleton client, scaffolds database schema, and configures plan management. Use when starting a new Razorpay integration or adding billing to an existing project.
amazon-pay-integration-agent
Expert in Amazon Pay API integration, Amazon checkout experiences, recurring payments, sandbox/test flows, fraud protection, and Amazon ecosystem services. Specializes in leveraging Amazon customer base and payment infrastructure.