agentmods.dev

init-store

A project-initialization command that creates a new Shopify Hydrogen storefront from a standard starter project.

In plain words
What is it for?
Use it to create a named storefront, set its package metadata, remove inherited Git history, and add the initial brand configuration and agent dependency.
Why use it?
It avoids manually cloning, renaming, cleaning, and preparing the starter repository. It also prevents overwriting an existing directory.

Command

1 4mo ago A scan 26 tokens original MIT
View the source file commerce-atoms/agents
Install

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.

agentmods
npx agentmods add commands/commerce-atoms/agents/init-store
Clone the repo
git clone --depth 1 https://github.com/commerce-atoms/agents
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 931 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00931
Opus 5 $0.00013 $0.00465
Sonnet 5 $0.00005 $0.00186
Haiku 4.5 $0.00003 $0.00093

Measured yesterday against content hash 9a1821fc9401, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init-store 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 yesterday.

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.

kit/commands/init-store.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/init-store <store-name>

Initialise a new Shopify Hydrogen storefront from the canonical starter, with the agent layer pinned and a brand-layer placeholder ready to fill in.

Convention

By convention (see rules/stores.md), run this command from ~/Projects/commerce-atoms/stores/. The new store is created as a sibling under stores/, never at the top level of commerce-atoms/.

Workflow

  1. Validate the name. Lowercase letters, digits, hyphens; starts with a letter; 2–50 chars. Reject anything else and surface the validation error.

  2. Refuse to overwrite. If <cwd>/<store-name> already exists, abort with a clear message — do not destroy work.

  3. Run the CLI:

    cd ~/Projects/commerce-atoms/stores
npx @commerce-atoms/agents init <store-name>

    This wraps:

    1. git clone --depth=1 --branch main https://github.com/commerce-atoms/hydrogen-storefront-starter.git <store-name>
    2. Remove the inherited .git/ history.
    3. Rename package.json#name to <store-name>, set private: true, reset to 0.1.0.
    4. Replace README.md with a store-specific stub (linked to @commerce-atoms/agents version).
    5. Seed app/config/brand.ts and app/assets/brand/ with placeholders if the starter doesn't provide them.
    6. Run commerce-atoms-agents sync internally to materialise AGENTS.md, CLAUDE.md, copilot-instructions.md, and .cursor/rules/*.mdc.
    7. git init --initial-branch=main + initial commit.

  4. Print the next-steps checklist (the CLI does this; surface it verbatim to the user):

    1. cd <store-name>
2. Edit app/config/brand.ts (name, locales, colours, fonts).
3. Replace app/assets/brand/* with your real assets.
4. Set up Shopify Admin (storefront token, products, theme).
5. Wire CI: /deploy-setup
6. First deploy: git push origin main

Done when

  • The directory <cwd>/<store-name> exists.
  • package.json#name is <store-name>.
  • agents.config.json pins the current @commerce-atoms/agents version.
  • AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, and .cursor/rules/*.mdc are present.
  • app/config/brand.ts exists with placeholder values.
  • The repo has a single initial commit on main.

Read the full file on GitHub · 73 lines

Changes

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.

  1. yesterday First seen · 73 lines · 26 tokens per session scan A 9a1821fc9401

Subscribe to this mod's changes

init-store is a command published in the GitHub repository commerce-atoms/agents (1 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 931 once invoked, about $0.0001 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.

Data and AIE-commerceGit and workflowaiai-agentscopilotcursorcursor-rules
Related

Other commands, from other repositories

fastapi_stripe

A Stripe Checkout implementation takes four steps.

iloveitaly/llm-ide-rules · 0 tokens

core-review

Review code changes against SpecOps project-specific patterns. Catches recurring failure modes from real PRs — tool abstraction violations, generated file drift, cross-platform gaps, variable inconsistencies, and more. Complements full-review-gate (generic quality) and pr-fix (applying bot comments).

sanmak/specops · 0 tokens

resolve-conflicts

Resolve merge conflicts on a GitHub PR by merging the base branch into the PR branch in an isolated git worktree, with JSON/markdown-aware conflict resolution.

sanmak/specops · 0 tokens

ship-pr

Commit all changes to a new branch, push, and open a PR for review. The original branch stays clean.

sanmak/specops · 0 tokens

brownfield-map

Run a complete brownfield analysis on the codebase and generate MASTER.md, summaries, risk scores, and all derived analytics.

wednesday-solutions/ai-agent-skills · 0 tokens

react-router-client-loader

Do this in a clientLoader and use loaderData to render the component. DO NOT create mock data, new interfaces, or mock data loader functions. Instead, assume loaderData has all of the data you need to render the component.

iloveitaly/llm-ide-rules · 0 tokens