design-page

design-page is a skill for Claude Code, Codex from Aetheria-Labs1/storefront-skills. It costs 30 tokens per session (3,027 once invoked), scanned A, original, MIT.

A skill that turns an approved one-page storefront plan into page source and a responsive browser preview. It uses the plan's store and theme information and checks unresolved asset slots.

In plain words
What is it for?
Use it to create a storefront page, select or inspect template sections and assets, compile the page, and review its interactive preview.
Why use it?
It separates page implementation from earlier planning, reducing the risk of inventing layout details that the approved plan did not specify. It does not publish the page.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions subagents.

Part of the lexsis-storefront-skills plugin — 11 skills, 2 agents shipped together

Good fit Use it to create a storefront page, select or inspect template sections and assets, compile the page, and review its interactive preview.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aetheria-labs1/storefront-skills/design-page
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.

Any agent
npx skills add Aetheria-Labs1/storefront-skills --skill design-page
Clone the repo
git clone --depth 1 https://github.com/Aetheria-Labs1/storefront-skills

Made for: Claude Code, Codex.

Or install lexsis-storefront-skills, the plugin that ships this one along with the rest of its 11 skills, 2 agents.

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 design-page

README.md
[![agentmods](https://agentmods.dev/badge/skills/aetheria-labs1/storefront-skills/design-page/github.svg)](https://agentmods.dev/skills/aetheria-labs1/storefront-skills/design-page)
Your own site
<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.

agentmods 80×15 button for design-page

Your own site · 80×15
<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>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,027 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00030 $0.03027
Opus 5 $0.00015 $0.01514
Sonnet 5 $0.00006 $0.00605
Haiku 4.5 $0.00003 $0.00303

Measured 2d ago against content hash 35296ec34fb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/design_lint.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/design-page/SKILL.md · 283 lines

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.md
  • references/animation-system.md when the plan names a motion moment
  • references/consumer-behavior-cro.md
  • references/island-presets.md
  • references/merchant-templates.md
  • references/workflow-intent.md
  • references/design-concepts.md only when the user wants a visual concept before source authoring
  • references/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.

Read the full file on GitHub · 283 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. 2d ago Changed · -19 lines 35296ec34fb0
  2. 4d ago Changed · +65 lines 45ed9d003595
  3. 5d ago First seen · 237 lines · 30 tokens per session scan A dd31a2775d0d

Subscribe to this mod's changes

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.