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 skills add finsilabs/awesome-ecommerce-skills --skill storefront-theminggit clone --depth 1 https://github.com/finsilabs/awesome-ecommerce-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/skills/finsilabs/awesome-ecommerce-skills/storefront-theming)<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/storefront-theming"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/storefront-theming/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.
<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/storefront-theming"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/storefront-theming.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00031 | $0.02740 |
| Opus 5.5 | $0.00012 | $0.01096 |
| Sonnet 5.5 | $0.00006 | $0.00548 |
| Haiku 4.5 | $0.00003 | $0.00274 |
Grade A, and why
storefront-theming 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 1mo 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storefront Theming
Overview
Architect a theming system using design tokens and CSS custom properties that allows a storefront to be re-skinned for multiple brands without modifying component code. Covers the token taxonomy (color, typography, spacing, radius), runtime theme switching for dark mode, and white-label multi-tenant architecture where each tenant supplies their own token overrides.
When to Use This Skill
- When building a platform that will power multiple branded storefronts from a single codebase
- When implementing dark mode for a storefront
- When a rebrand requires changing colors across thousands of component instances without hunt-and-replace
- When handing off a design system to a team that needs to maintain brand consistency
Core Instructions
Step 1: Determine the merchant's platform and choose the right approach
| Platform | Recommended Approach | Why |
|---|---|---|
| Shopify | Use the Theme Editor's Color scheme system + edit config/settings_schema.json and assets/base.css to add custom CSS variables |
Shopify OS2.0 themes expose all brand colors, fonts, and border radii as Theme Editor settings that write to CSS variables automatically; no build step required |
| WooCommerce | Use the WordPress Global Styles system (WordPress 5.9+) with a block theme, or configure CSS variables in Appearance → Customize → Additional CSS for classic themes | Block themes using theme.json support a full design token system natively; classic themes need CSS custom properties added manually |
| BigCommerce | Configure theme settings in Storefront → My Themes → Customize — Cornerstone exposes colors, fonts, and spacing as Theme Editor variables; advanced customization via config.json and SCSS |
Cornerstone compiles SCSS with Handlebars template variables; custom CSS variables can be added to the global stylesheet |
| Custom / Headless | Build a three-tier token system (global → semantic → component) using CSS custom properties, compiled from JSON using Style Dictionary | Full control over token taxonomy, dark mode, and multi-tenant overrides; see implementation below |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/dark-mode-implementation/criteria.json 2.8 KB
- evals/dark-mode-implementation/task.md 2.5 KB
- evals/multi-tenant-theme-injection/criteria.json 2.5 KB
- evals/multi-tenant-theme-injection/task.md 2.2 KB
- evals/token-taxonomy-and-build-pipeline/criteria.json 2.7 KB
- evals/token-taxonomy-and-build-pipeline/task.md 1.9 KB
- tile.json 238 B
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.
- 1mo ago First seen · 265 lines · 31 tokens per session scan A a57f0c10750b
storefront-theming is a skill published in the GitHub repository finsilabs/awesome-ecommerce-skills (60 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 2,740 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
Dark Mode Bug Finder
Detect dark mode rendering issues including contrast failures, missing theme tokens, image inversions, and transition glitches across components.
7onic-setup
Detect, configure, and verify a project for the 7onic Design System — framework/Tailwind detection, token CSS wiring, and an idempotent health check. Run after installing @7onic-ui packages, after npx 7onic init, or whenever styles look wrong.
7onic-design
Build UI with the 7onic Design System the right way — guided workflow that drives the 7onic MCP tools (component discovery, token resolution, layout recipes, validatecode loop) from a plain-language request like "SaaS dashboard" or "pricing page". Queries work in English, Japanese, and Korean.
css-in-js-architect
Architect scalable styling systems with Tailwind v4, CSS Modules, design tokens, dynamic theming, and container queries. Activate on: design tokens, theming system, Tailwind config, CSS architecture, container queries, dark mode. NOT for: component library creation (use design-system-creator), animation systems (use…
typography
Generate a type scale token file (CSS variables, tailwind config, or JS module) anchored on the type ratio detected by /scan. Use when the user wants to formalize their typography system, extract a scale from existing code, or scaffold typography tokens. Defaults to dry-run preview; pass --apply to write. Auto-picks…
color
Generate a color palette token file (CSS variables, tailwind config, or JS module) from the palette detected by /scan. Uses inferred role names (foreground, background, accent, danger, etc.) where possible, numeric fallback otherwise. Use when the user wants to formalize color tokens, extract a palette from existing…