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/spree/agent-skills/agents-mdgit clone --depth 1 https://github.com/spree/agent-skillsWhat 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 | $0.03126 | $0.03126 |
| Opus 5 | $0.01563 | $0.01563 |
| Sonnet 5 | $0.00625 | $0.00625 |
| Haiku 4.5 | $0.00313 | $0.00313 |
Grade A, and why
agent-skills AGENTS.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 3d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spree Commerce — Agent Guidance
This file follows the agents.md cross-tool standard. It's a portable summary of how to be effective on a Spree Commerce codebase, written for any agentic CLI (Codex, Cursor, Copilot, Aider, Windsurf, Zed, Amp, etc.) that reads AGENTS.md.
If you're running in Claude Code, install this package as a plugin and you'll get the 26 SKILL.md files under skills/ as on-demand context, the spree-expert subagent, and two safety hooks. See README.md for install instructions.
If you're running in any other tool: read this file, then dive into the relevant skills/<name>/SKILL.md when the task matches its domain.
What Spree is
Spree Commerce is an open-source, self-hosted commerce platform built on Ruby on Rails. The thing people choose it for is the ability to customize and extend it without forking. Architecture in three layers:
- Backend (Ruby gems) —
spree_core(models, services, business logic),spree_api(Store + Admin REST APIs under/api/v3/),spree_admin(Rails admin UI), optional payment/integration gems (spree_stripe,spree_adyen,spree_paypal_checkout,spree_i18n). - Frontend SDKs (TypeScript) —
@spree/sdk(Store API client),@spree/admin-sdk(Admin API client). - Admin UI —
spree_admin(the Rails/Turbo admin).
Users run Spree in their own infrastructure — there's no Spree cloud. Everything is opt-in customization.
Core conventions (don't violate these without a reason)
Ruby / Rails
- All Spree code is namespaced under
Spree::. - All models inherit from
Spree.base_class— notApplicationRecorddirectly. - Use
Spree.user_classandSpree.admin_user_classinstead ofSpree::Userso apps can swap the user model. - Always scope queries through
current_store(e.g.current_store.orders, notSpree::Order.all). Multi-store apps share a database; un-scoped queries leak data across stores. - State/status fields on state-machine models (Order, Payment, Shipment) are string columns — don't convert them to Rails enums. (Core does use integer enums for a few non-workflow fields like
Promotion#kind; string + state machine is still the default for anything with transitions.) - IDs are treated as strings (Stripe-style prefixed IDs at the API surface; integer PKs internally — never
.to_ian ID). - State machines use the
state_machines-activerecordgem. - Uniqueness validations use
scope: spree_base_uniqueness_scopeplus a DB index. - Always pass
class_nameanddependenton associations. - Use the events system (
publish_event+ subscribers) for side effects — notafter_*callbacks.
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.
- 3d ago First seen · 170 lines · 3,126 tokens per session scan A e4444c7f1eb4
agent-skills AGENTS.md is an instructions file published in the GitHub repository spree/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 3,126 tokens to every session, about $0.0156 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.