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 skills/orcaqubits/agentic-commerce-skills-plugins/ap2-setupnpx skills add OrcaQubits/agentic-commerce-skills-plugins --skill ap2-setupgit 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-setup)<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-setup"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/ap2-setup.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 | $0.00048 | $0.00944 |
| Opus 5 | $0.00024 | $0.00472 |
| Sonnet 5 | $0.00010 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
ap2-setup 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AP2 Project Setup
Before writing code
Fetch live docs:
- Fetch
https://ap2-protocol.org/for the latest protocol overview - Fetch
https://github.com/google-agentic-commerce/AP2for the current README and installation instructions - Web-search
site:github.com google-agentic-commerce AP2 samples pythonfor the sample project structure - Fetch
https://github.com/google-agentic-commerce/AP2/tree/main/samples/pythonfor Python sample layout
Conceptual Architecture
What Setup Involves
An AP2 project creates a multi-agent payment system with distinct roles:
- Install the AP2 Python package from GitHub
- Create agent role directories — Shopping Agent, Merchant, Credentials Provider, Payment Processor
- Configure authentication — Google API key or Vertex AI credentials
- Define Agent Cards — each agent advertises its AP2 capabilities
- Set up the agent framework — Google ADK (Agent Development Kit) is the reference framework
Installation
# Requires Python 3.10+ and uv
uv pip install git+https://github.com/google-agentic-commerce/AP2.git@main
Project Structure (Reference from Official Samples)
my-ap2-project/
├── roles/
│ ├── shopping_agent/ # Shopping Agent — orchestrates purchases
│ │ ├── __init__.py
│ │ └── agent.py
│ ├── merchant_agent/ # Merchant — product catalog, cart creation
│ │ ├── __init__.py
│ │ └── agent.py
│ ├── credentials_provider_agent/ # CP — payment methods, tokenization
│ │ ├── __init__.py
│ │ └── agent.py
│ └── merchant_payment_processor_agent/ # MPP — payment processing
│ ├── __init__.py
│ └── agent.py
├── .env # GOOGLE_API_KEY or Vertex AI config
├── pyproject.toml
├── run.sh # Launches all agents
└── tests/
└── test_flow.py
Environment Configuration
Two authentication options:
- Google API Key (development): Set
GOOGLE_API_KEYin.env - Vertex AI (production): Set
GOOGLE_CLOUD_PROJECTandGOOGLE_CLOUD_LOCATION
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 · 98 lines · 48 tokens per session scan A c4f52be27a7a
ap2-setup is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 944 once invoked, about $0.0002 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 skills, from other repositories
design-taste-frontend
Use for visual design direction on greenfield, user-facing surfaces — marketing and landing pages, generated apps, portfolio-style or standalone pages. NOT for routine Archestra platform UI work (dashboards, data tables, settings, forms, existing components) — use archestra-dev-frontend for that. Upstream intent…
internet-court
Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with another agent or a paid service, or a user mentions agent payments, paid APIs (HTTP 402/x402), wallet custody or trust concerns, spending mandates, delegated permissions (ERC-7710/7715), escrow…
x402-erc7710
Design and implement demos combining x402 HTTP payments with ERC-7710 smart contract delegations and ERC-7715 wallet permission requests for subscriptions, bounded agent budgets, recurring spend, pay-per-use APIs, and agentic commerce.
magicblock
Design, implement, and debug MagicBlock applications on Solana. Covers Ephemeral Rollups with delegated state; ER/PER architecture and settlement; private payments and token flows; oracles and randomness; scheduling and temporary authority; security and local validation. Use for MagicBlock product selection…
web3-data
Two services in one skill: (1) Web3 on-chain data via Chainbase CLI — use when the user asks about blockchain data, token holders, wallet addresses, token prices, ENS domains, transactions, DeFi portfolios, or any on-chain analytics. Triggers: "top holders of", "who holds", "wallet address", "token price", "token…
dflow-phantom-connect
Build Solana wallet-connected apps with Phantom Connect SDKs and DFlow spot trading. Use when user asks to connect a Phantom wallet, integrate Phantom in React, React Native, or vanilla JS, sign messages or transactions, build token-gated pages, mint NFTs, accept crypto payments, or swap/stream tokens with DFlow.…