agentmods.dev

shop-e-design

shop-e-design is a skill for Claude Code, Codex from Ertinox7711/SGRR-AGI-V2. It costs 307 tokens per session (16,065 once invoked), scanned B, original, MIT.

A project-specific guide for creating and changing the visible parts of the SHOP-E online shop, including its text, layout, images, styles, and search settings. It records the shop's brand rules, files, and required checks.

In plain words
What is it for?
Use it when editing SHOP-E product pages, collections, articles, emails, menus, footers, questions and answers, CSS, images, or search-related content.
Why use it?
It keeps changes consistent with SHOP-E's established look, tone, facts, and sales requirements. It also reduces the risk of copying another brand or adding made-up design choices.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/_catalogue-v2-build.py.

not rated 1repo 1mo ago B scan 307 tokens original MIT

Good fit Use it when editing SHOP-E product pages, collections, articles, emails, menus, footers, questions and answers, CSS, images, or search-related content.

Compare 6 skills from other repositories ↓
View source ↗ Ertinox7711/SGRR-AGI-V2
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2
agentmods
npx agentmods add skills/ertinox7711/sgrr-agi-v2/shop-e-design

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for shop-e-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/shop-e-design/github.svg)](https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/shop-e-design)
Your own site
<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/shop-e-design"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/shop-e-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for shop-e-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/shop-e-design"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/shop-e-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 307 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 16,065 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00307 $0.16065
Opus 5.5 $0.00123 $0.06426
Sonnet 5.5 $0.00061 $0.03213
Haiku 4.5 $0.00031 $0.01606

Measured 23d ago against content hash bb0457ef1144, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

shop-e-design scanned grade B with 1 finding 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 23d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

> **Préséance** (règle the operator du 2026-09-13, écrite dans `~/.claude/settings.json`) :
skills/shop-e-design/SKILL.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SHOP-E — DA verrouillée + anti-AI-slop

SHOP-E = tapis berbères faits main (Maroc, Moyen Atlas), marché FR, EUR, thème Horizon, store shop-e-handle. Esthétique : sable + terre cuite + encre, maison de négoce française, sobre, honnête, dense comme la référence tamazi.fr mais jamais copiée (ni nom, ni copy, ni bordeaux). TOUT contenu visible (texte, section, image, CSS) passe par ce skill. Une valeur hors des listes ci-dessous (hex, font, radius, mot) = red flag AI-slop → corriger avant livraison.

Références durables : docs/DESIGN-SYSTEM.md (source de ce skill, verrouillé 2026-09-10), docs/BRAND-BRIEF.md + docs/BRAND-BRIEF-s2-s5.md (promesse, persona, voix, naming), docs/GMC-GATES.md, docs/JOURNAL.md (journal ✅ daté, sorti de CLAUDE.md le 2026-09-17), sections/shop-e-*.liquid (38 sections sources), assets/shop-e-base.css / assets/shop-e-ui.js, data/brand-facts.json (faits de marque : livraison, retours, matière, familles, couleurs, tailles).

Préséance (règle the operator du 2026-09-13, écrite dans ~/.claude/settings.json) :

  • Une demande de the operator et le modèle SHOP-B passent avant ce skill.
  • Ce skill ne sert jamais de motif pour retirer, alléger, refuser ou déconseiller ce qu'il a demandé : on crée.
  • Rien de ce qui est posé ne se retire sans sa demande pour cet élément précis.

0. VERROU IDENTITÉ (avant tout, prioritaire sur tout)

  • SHOP-E = shop-e-handle / shop-e-handle.myshopify.com. JAMAIS confondre avec SHOP-A shop-a-handle ni SHOP-B shop-b-handle (même owner, stores différents). Handle/GID = COPIÉ du banner (CLAUDE.md L1-14) ou du registre ~/.claude/shops-registry.md, jamais de mémoire. Un GID de thème ne s'écrit jamais en dur : shop.mainThemeId().
  • Identité = LE DOSSIER : si cwd ≠ C:\Users\YOU\Documents\BUSINESS\shop-e → STOP, pwd + fingerprints (sections shop-e-* présentes, pas wolf-* ni shop-b-*). Chemins absolus toujours, token en chemin absolu : .secrets/access-token.txt (24 h, bash scripts/get-token.sh). Le compte Shopify de CETTE boutique est <ACCOUNT_EMAIL>, pas celui de SHOP-A.
  • Un token = un store. scripts/lib/shop.js fait assertShop() (domaine + nom du registre) avant toute requête ; chaque run imprime Shop OK: SHOP-E | shop-e-handle.myshopify.com | EUR | Europe/Paris. Pas cette ligne = on n'est pas au bon endroit.
  • Écriture AUTONOME (décision the operator 2026-09-10 : « la règle read-only c'est pour les autres sites, là c'est un nouveau donc adapte les règles ») : registre write_policy = read-write. Edit/Write du dossier et mutations Shopify (themeFilesUpsert, productSet, metafieldsSet, themePublish, menus, policies) sans redemander. GO explicite seulement pour le destructif (suppression en masse, reset thème, purge Files) et le cross-boutique. Après chaque push : montrer le résultat (lien admin/éditeur + captures) — the operator veut voir le site.
  • Jamais : créer un compte, saisir un mot de passe (y compris la page mot de passe du storefront), facturation, achat de domaine, campagne payante, CAPTCHA. Secrets lus = jamais affichés.

Read the full file on GitHub · 345 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. 23d ago First seen · 345 lines · 307 tokens per session scan B bb0457ef1144

Subscribe to this mod's changes

shop-e-design is a skill published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 1mo ago), licensed MIT. It adds 307 tokens to every session and 16,065 once invoked, about $0.0012 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.

Design and UXE-commerceaiautomationclaudedeveloper-tools
Related

Other skills, from other repositories

hero-receipt-print

A thermal receipt feeds down from a dark checkout slot. Function: transaction / publish confirmation print.

Unclecheng-li/AI_Animation · 0 tokens

product-configurator-design

Designing build-your-own product configurators (Tesla-style, custom-pricing, plan-builders) with constraint logic, real-time pricing, validation, and save-and-share mechanics. Honest about infinite-options (decision paralysis), canned-bundles-only (no real customization), and guided-configuration (smart defaults plus…

rampstackco/claude-skills · 129 tokens

style

Luxe fashion-commerce editorial design with a deep-indigo canvas, oversized numerals, large image-led storytelling, rounded capsules/cards, and restrained monochrome accents.

aimeos/pagible · 33 tokens

etsy-shop-branding

Shop branding — banner design, logo, brand story, cohesive listing photography, packaging.

nexscope-ai/eCommerce-Skills · 21 tokens

revenuecat-paywall-design

Must invoke for any request to create, edit, evaluate, understand, or improve a RevenueCat Paywall in the dashboard — including questions about a specific paywall or general paywall design recommendations, and uploading images or fonts to paywall resources / the Media Gallery. Not for presenting a paywall in app code…

RevenueCat/ai-toolkit · 76 tokens

linkfox-multimodal-product-similarity

An image-comparison tool that groups products whose main photos look alike, using features such as appearance, colour, composition, and material.

linkfox-ai/linkfox-skills · 163 tokens