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.
/plugin marketplace add OrcaQubits/agentic-commerce-skills-pluginsnpx agentmods add plugins/orcaqubits/agentic-commerce-skills-plugins/ap2-agentic-paymentsgit 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/plugins/orcaqubits/agentic-commerce-skills-plugins/ap2-agentic-payments)<a href="https://agentmods.dev/plugins/orcaqubits/agentic-commerce-skills-plugins/ap2-agentic-payments"><img src="https://agentmods.dev/badge/plugins/orcaqubits/agentic-commerce-skills-plugins/ap2-agentic-payments.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
ap2-agentic-payments 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.
What it actually says
{
"name": "ap2-agentic-payments",
"version": "1.0.0",
"description": "Expert AP2 (Agent Payments Protocol) knowledge for building agentic commerce payment modules — Verifiable Digital Credentials, mandates, cryptographic signing, transaction flows, and multi-agent payment orchestration.",
"author": {
"name": "Rohit Bajaj, Julekha Khatun",
"url": "https://orcaqubits-ai.com"
},
"repository": {
"type": "git",
"url": "https://github.com/OrcaQubits/agentic-commerce-skills-plugins",
"directory": "ap2-agentic-payments"
},
"homepage": "https://github.com/OrcaQubits/agentic-commerce-skills-plugins/tree/main/ap2-agentic-payments",
"keywords": [
"ap2",
"agent-payments",
"agentic-commerce",
"google",
"mandates",
"vdc",
"verifiable-credentials",
"payment",
"cryptographic-signing"
],
"license": "MIT"
}
What it installs
The manifest is a name and a version. 18 skills, 1 agent travel with it, and installing the plugin installs all of them — 1,042 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ap2-cryptographic-signing A 53 tokens
- Skill ap2-dev-patterns A 54 tokens
- Skill ap2-a2a-extension A 58 tokens
- Skill ap2-cart-mandate A 56 tokens
- Skill ap2-challenge-stepup A 44 tokens
- Skill ap2-human-not-present-flow A 47 tokens
- Skill ap2-human-present-flow A 59 tokens
- Skill ap2-merchant-agent A 48 tokens
- Skill ap2-payment-mandate A 47 tokens
- Skill ap2-payment-processor A 44 tokens
- Skill ap2-vdc-framework A 59 tokens
- Skill ap2-mcp-server A 38 tokens
- Skill ap2-setup A 48 tokens
- Skill ap2-intent-mandate A 50 tokens
- Skill ap2-credentials-provider A 52 tokens
- Skill ap2-dispute-accountability A 48 tokens
- Skill ap2-risk-signals A 50 tokens
- Skill ap2-shopping-agent A 45 tokens
- Agent ap2-expert A 142 tokens
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 · 28 lines scan A d43b29cf6747
ap2-agentic-payments is a plugin published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
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…
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 98 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
ecc
Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.