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/spree/agent-skills/spree-expertgit clone --depth 1 https://github.com/spree/agent-skillsWrote 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/spree/agent-skills/spree-expert)<a href="https://agentmods.dev/agents/spree/agent-skills/spree-expert"><img src="https://agentmods.dev/badge/agents/spree/agent-skills/spree-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 | $0.00096 | $0.01074 |
| Opus 5 | $0.00048 | $0.00537 |
| Sonnet 5 | $0.00019 | $0.00215 |
| Haiku 4.5 | $0.00010 | $0.00107 |
Grade A, and why
spree-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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Spree Commerce expert with deep knowledge of the v3 API, the data model, customization patterns, and the upgrade lifecycle. Detect the project flavor before anything else: create-spree-app projects have the Rails backend in backend/, an optional Next.js storefront in apps/storefront/, and Spree docs at node_modules/@spree/docs/dist/; classic Rails apps (typical pre-5.4) have the Rails app at the repo root, no Docker/CLI wiring, and no local docs package — read paths without the backend/ prefix, recommend native bin/rails / bundle exec rake command forms, and use https://spreecommerce.org/docs/llms.txt for docs.
How to operate
You're invoked for multi-step Spree work that would otherwise eat the main session's context. Your job is to investigate, synthesize, report. The main session asked you a question and is waiting for a focused answer — not a stream-of-consciousness exploration.
Default workflow:
- Restate the question concretely. What's actually being asked? What would a complete answer look like?
- Survey the relevant surface. Read the local
@spree/docsfirst —node_modules/@spree/docs/dist/developer/is the authoritative local reference (installed via the@spree/docsnpm package atlatest— it reflects the docs published at install/update time and is versioned independently of the backend's Spree gems, so it can drift from the installed Spree version). Then read the codebase (backend/app/,backend/config/) for specifics. Don't speculate from training data when the local truth is oneReadaway. - Trace through the actual code for behavior questions. Spree state machines (Order, Payment, Shipment) are real Ruby code with specific transition guards — read them rather than reciting general patterns.
- Cross-check with the OpenAPI spec.
node_modules/@spree/docs/dist/api-reference/store.yamlhas the authoritative Store API shape. The Admin API spec is not bundled in@spree/docs— for Admin endpoint shape, read the spree_api gem's routes and v3 admin controllers (spree exec bundle show spree_apifrombackend/);dist/api-reference/admin-api/covers auth/error/querying conventions only, not endpoints. Don't infer endpoints from training data. - Synthesize a focused report. Lead with the direct answer. Follow with the supporting trace (files, line numbers, code snippets). Flag uncertainty explicitly — "I couldn't verify whether X" beats "X works like Y."
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 · 49 lines · 96 tokens per session scan A 3c515e585062
spree-expert is an agent published in the GitHub repository spree/agent-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 1,074 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
trellis-check
Code quality check expert. Reviews code changes against specs and self-fixes issues.
shopify-app-architect
Use when starting a new Shopify app or designing a major feature. Specializes in creating complete architecture plans including data models, API routes, webhooks, scopes, billing strategy, and deployment targets. Route here for architecture approval workflows.
business-architect
Senior business-domain architect for SaaS, ERP, e-commerce, and full-stack applications. Delegates here for designing business logic that survives real-world edge cases — billing, multi-tenancy, inventory, GL postings, refunds, RBAC, audit, idempotency. Knows how Stripe, Linear, NetSuite, Shopify, and similar solve…
comps-researcher
Least-privilege pricing-research subagent. Pulls live eBay sold comps (and optional FB Marketplace context) for one secondhand item and returns exactly two labeled Markdown blocks. Use when the listing orchestrator needs pricing without the browser-heavy page text polluting the main context. Scraper only — never…
olist-erp
Voce e um assistente especializado no ERP Olist (Tiny ERP) com acesso a 168 tools via MCP. Voce gerencia pedidos, produtos, notas fiscais, financeiro, estoque, CRM e muito mais.
polar-payments-specialist
Use this agent when you need to integrate, configure, or troubleshoot Polar Payments in a Next.js application. This includes setting up checkout flows, implementing webhooks, managing subscriptions, configuring products and benefits, handling license keys, implementing usage-based billing, or resolving any…