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 Aetheria-Labs1/storefront-skills --skill design-pagegit clone --depth 1 https://github.com/Aetheria-Labs1/storefront-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/aetheria-labs1/storefront-skills/design-page)<a href="https://agentmods.dev/skills/aetheria-labs1/storefront-skills/design-page"><img src="https://agentmods.dev/badge/skills/aetheria-labs1/storefront-skills/design-page/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/aetheria-labs1/storefront-skills/design-page"><img src="https://agentmods.dev/badge/skills/aetheria-labs1/storefront-skills/design-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.03027 |
| Opus 5 | $0.00015 | $0.01514 |
| Sonnet 5 | $0.00006 | $0.00605 |
| Haiku 4.5 | $0.00003 | $0.00303 |
Grade A, and why
design-page 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 2d 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design the Page
Create the real page source, compile it, and create one unpublished hosted draft for review. Never publish.
Read:
references/design-rules.mdreferences/animation-system.mdwhen the plan names a motion momentreferences/consumer-behavior-cro.mdreferences/island-presets.mdreferences/merchant-templates.mdreferences/workflow-intent.mdreferences/design-concepts.mdonly when the user wants a visual concept before source authoringreferences/page-layout.md
Use lexsis_brand.context, lexsis_brand.get_theme,
lexsis_template_library.search_page_kits,
lexsis_template_library.search_sections, lexsis_design.guide,
lexsis_design.islands, lexsis_design.island_schema,
lexsis_design.get_section, lexsis_template_library.get_kit,
lexsis_asset_library.search, lexsis_catalog.get, lexsis_catalog.reviews,
lexsis_assets.capabilities, lexsis_assets.view,
lexsis_workspace.credits,
lexsis_drafts.asset_generate, lexsis_asset_upload.import, and
lexsis_pages.compile, and lexsis_page_create.create.
When the user wants one of their saved reusable sections, use
lexsis_template_library.list_mine and get_mine. Treat its source as a
starting section in the page, not as an inherited renderer shell.
Resolve only unfamiliar argument schemas through exact router/action
discovery.
Inputs
Use the approved page-plan.md and its saved store/theme binding. The plan
defines strategy, the Design direction, the Imagery and background plan, the
asset slots and section intent; it must not define islands or implementation
details.
Implement the plan's Consumer decision model without adding generic CRO modules. Preserve its visitor mode, top decision questions, selected patterns, gallery jobs, merchandising relationship, risk treatment, mobile context, and metric. Reopen a decision only when live catalog, asset, or policy evidence contradicts the plan.
If the user explicitly skips /plan-page, write a short one-page plan with
the same blocks and record the skip. Never run /setup or /plan-page
automatically.
What ships with it
14 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.
- agents/openai.yaml 417 B
- references/animation-system.md 11 KB
- references/consumer-behavior-cro.md 13 KB
- references/design-concepts.md 2.8 KB
- references/design-rules.md 17 KB
- references/generate-pdp.md 5.7 KB
- references/generation-protocol.md 12 KB
- references/island-presets.md 50 KB
- references/merchant-templates.md 2.6 KB
- references/page-layout.md 1.3 KB
- references/source-artifact-workflow.md 4.0 KB
- references/source-format.md 8.6 KB
- references/workflow-intent.md 3.0 KB
- scripts/design_lint.py 3.5 KB runs code
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.
- 2d ago Changed · -19 lines 35296ec34fb0
- 4d ago Changed · +65 lines 45ed9d003595
- 5d ago First seen · 237 lines · 30 tokens per session scan A dd31a2775d0d
design-page is a skill published in the GitHub repository Aetheria-Labs1/storefront-skills (8 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 3,027 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
shopify-theme-optimization
Theme speed and UX optimization — Core Web Vitals, Liquid code, image loading, mobile responsiveness.
shopify
Expert Shopify theme development guidelines for Liquid, Online Store 2.0, CSS, JavaScript, and UX best practices.
shopify-theme-development-guidelines
Expert Shopify theme development with Liquid, Online Store 2.0, and performance best practices.
sfcc-sfra-scss
Best practices for styling and theming SFRA storefronts using SCSS. Use when asked to create style overrides, theming, responsive layouts, or CSS customizations in SFCC.
wc-product-attribute-swatches
Build or audit WooCommerce product attribute swatch integrations around the experimental wc-visual attribute type. Covers feature gating, global pa attribute taxonomies, the WooCommerce 11 slug byte limit, color/image term meta, visual admin search results, Store API experimentalvisual / experimentalVisual, classic…
evo-nextjs-visual-stability
Fix visual stability issues (CLS, FOUC, FOIT) in Next.js e-commerce apps. Addresses theme flicker, font loading, image dimensions, and async content placeholders.