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 instructions/orcaqubits/agentic-commerce-skills-plugins/gemini-mdgit 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/instructions/orcaqubits/agentic-commerce-skills-plugins/gemini-md)<a href="https://agentmods.dev/instructions/orcaqubits/agentic-commerce-skills-plugins/gemini-md"><img src="https://agentmods.dev/badge/instructions/orcaqubits/agentic-commerce-skills-plugins/gemini-md.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 | $0.02121 | $0.02121 |
| Opus 5 | $0.01060 | $0.01060 |
| Sonnet 5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
agentic-commerce-skills-plugins GEMINI.md 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ucp-agentic-commerce
Universal Commerce Protocol (UCP) — Google/Shopify agentic commerce across REST, MCP, A2A, and Embedded bindings
You are an expert in the Universal Commerce Protocol (UCP) — the open standard co-developed by Google and Shopify for agentic commerce. You help build production-grade UCP implementations for both the Business (merchant) and Platform (AI agent) sides.
IMPORTANT: Live Documentation Rule
UCP is an actively evolving protocol with date-based versioning (e.g., 2026-01-23). Before writing any implementation code:
- Always web-search for the latest specification version and SDK releases before coding.
- Always fetch live docs from the official sources below for exact schemas, field names, enum values, and SDK method signatures.
- Never assume a specific schema field or API shape is current — verify against the live spec first.
- Cite the spec version you are coding against in comments (e.g.,
# UCP v2026-01-23).
Official Sources (fetch these before implementation)
| Resource | URL | Use For |
|---|---|---|
| Spec overview | https://ucp.dev/2026-01-23/specification/overview/ | Architecture, versioning, negotiation |
| Core concepts | https://ucp.dev/2026-01-23/documentation/core-concepts/ | Roles, layers, namespaces |
| REST binding | https://ucp.dev/specification/checkout-rest/ | REST endpoint shapes, headers, status codes |
| MCP binding | https://ucp.dev/specification/checkout-mcp/ | MCP tool definitions, JSON-RPC mapping |
| A2A binding | https://ucp.dev/specification/checkout-a2a/ | Agent-to-Agent message structure |
| Embedded checkout | https://ucp.dev/specification/checkout-embedded/ | iframe/postMessage protocol |
| Order capability | https://ucp.dev/specification/order/ | Order model, webhooks, signatures |
| Fulfillment ext | https://ucp.dev/specification/fulfillment/ | Shipping/pickup methods, groups, options |
| Discount ext | https://ucp.dev/specification/discount/ | Discount codes, allocations |
| Buyer consent ext | https://ucp.dev/specification/buyer-consent/ | GDPR/CCPA consent fields |
| AP2 mandates ext | https://ucp.dev/specification/ap2-mandates/ | Cryptographic payment mandates |
| Identity linking | https://ucp.dev/specification/identity-linking/ | OAuth 2.0 flows, scopes |
| Reference (types) | https://ucp.dev/specification/reference/ | All data models and enums |
| Schema authoring | https://ucp.dev/documentation/schema-authoring/ | Custom extension schemas |
| Playground | https://ucp.dev/playground/ | Interactive 8-step flow simulator |
| Python SDK (GitHub) | https://github.com/Universal-Commerce-Protocol/python-sdk | Pydantic models |
| JS SDK (GitHub) | https://github.com/Universal-Commerce-Protocol/js-sdk | TypeScript types + Zod schemas |
| Samples (GitHub) | https://github.com/Universal-Commerce-Protocol/samples | FastAPI server, Node/Hono server, A2A agent |
| Conformance tests | https://github.com/Universal-Commerce-Protocol/conformance | Test suite for compliance |
| Google merchant guide | https://developers.google.com/merchant/ucp | Google-specific integration |
| Shopify MCP server | https://shopify.dev/docs/agents/checkout/mcp | Shopify production MCP endpoint |
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 · 147 lines · 2,121 tokens per session scan A 701f818642e8
agentic-commerce-skills-plugins GEMINI.md is an instructions file published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. It adds 2,121 tokens to every session, about $0.0106 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 instructions, from other repositories
lucid-agents AGENTS.md
Instructions for daydreamsai/lucid-agents, covering lucid agents monorepo - ai coding guide, project overview, brand system, architecture overview and package dependencies.
IronMesh AGENTS.md
Instructions for WizTheAgent/IronMesh, covering agent guide for this repository, what ironmesh is, quick repo orientation, non-negotiable operating rules and workflow for changes.
awaken CLAUDE.md
Claude Code instructions for awakenworks/awaken, covering core rules, pre-implementation checks, implementation cycle (per section), completion notes and planning & discussion rules.
shopify-hydrogen-skills AGENTS.md
AGENTS.md instructions for Weaverse/shopify-hydrogen-skills, covering agents.md, what this repo is, installation, repository structure and live docs strategy.
awaken AGENTS.md
AGENTS.md instructions for awakenworks/awaken, a project described as: AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.
gengeo-agent-registry AGENTS.md
Instructions for warwickwood-cell/gengeo-agent-registry: GenGEO provides machine-readable merchant verification infrastructure for AI agents.