page-builder

page-builder is an agent for Claude Code from Aetheria-Labs1/storefront-skills. It costs 78 tokens per session (1,056 once invoked), scanned A, original, MIT.

An end-to-end page-generation agent for Shopify storefronts, covering brand context, layout planning, HTML creation, interactive components, validation, and draft publishing.

In plain words
What is it for?
Use it to generate or edit landing pages, apply a CROBLUEPRINT handoff, connect interactive sections, validate the result, and prepare a preview.
Why use it?
It coordinates the many steps needed to turn a brief, reference page, ad, or existing page into a Shopify storefront page while keeping publication in draft form.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

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

Good fit Use it to generate or edit landing pages, apply a CROBLUEPRINT handoff, connect interactive sections, validate the result, and prepare a preview.

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

Clone the repo
git clone --depth 1 https://github.com/Aetheria-Labs1/storefront-skills

Made for: Claude Code.

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 page-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/aetheria-labs1/storefront-skills/page-builder/github.svg)](https://agentmods.dev/agents/aetheria-labs1/storefront-skills/page-builder)
Your own site
<a href="https://agentmods.dev/agents/aetheria-labs1/storefront-skills/page-builder"><img src="https://agentmods.dev/badge/agents/aetheria-labs1/storefront-skills/page-builder/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 page-builder

Your own site · 80×15
<a href="https://agentmods.dev/agents/aetheria-labs1/storefront-skills/page-builder"><img src="https://agentmods.dev/badge/agents/aetheria-labs1/storefront-skills/page-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,056 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.
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 $0.00078 $0.01056
Opus 5 $0.00039 $0.00528
Sonnet 5 $0.00016 $0.00211
Haiku 4.5 $0.00008 $0.00106

Measured today against content hash c46636151d30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

page-builder 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 today.

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.

agents/page-builder.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lexsis Page Builder

Use the public commands as distinct stages:

/setup → /plan-page → /design-page → /generate

/publish remains a separate explicit action.

For the fastest unpublished draft, use /build; use /build-with-template when the user already supplied a page-kit or section template. These routes return DRAFT_CREATED before deeper QA. When the user wants to approve the appearance first, /design-page may generate a mobile-first visual concept with the existing Lexsis image tools.

Infer whether the user wants a quick reversible draft or production-ready verification from the complete request. Do not require a magic phrase. Reversible ambiguity defaults to a fast unpublished draft; publishing remains a separate explicit operation.

MCP Gate

Use the exact router/action pairs declared by each stage. Call lexsis_discover only for an unfamiliar argument schema, passing structured router and action fields. Never use a prose query for a known action. A zero-result directory lookup is not an MCP outage; report failures from the actual domain call. Do not replace a failed Lexsis operation with static HTML unless the user explicitly requests a separate offline prototype.

Setup

Read work/storefront/setup/setup.json and select one saved store/theme pair. If it is missing, tell the user to run /setup; do not invoke it automatically. Reuse saved brand design and theme CSS, while reading current products, prices, assets, schemas, permissions, credits, and page versions live.

Plan

Create or consume a concise one-page page-plan.md. Ask only for missing campaign, audience, product, traffic-source, CTA, proof, and claim details. Record section purpose and template direction, but no islands or implementation details. The plan carries the Design direction block, the wireframe with a slot id on every media box, the Imagery and background plan, and the resolved Asset slots table. Resolve slots through the Lexsis asset tools with one user choice (user picks, agent picks, or generate the gaps). When the runtime can spawn sub-agents, plan the wireframe, the imagery and asset slots, and the palette/type/motion decisions in parallel and merge.

Read the full file on GitHub · 116 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. today Changed · +26 lines c46636151d30
  2. 2d ago Changed · +3 lines · -2 tokens per session e2e758fdea40
  3. 3d ago Changed · +13 lines ecaa7f75b156
  4. 4d ago Changed · -42 lines · -146 tokens per session 02da5f2feef5
  5. 8d ago First seen · 116 lines · 226 tokens per session scan A 63b60e5f2a06

Subscribe to this mod's changes

page-builder is an agent published in the GitHub repository Aetheria-Labs1/storefront-skills (8 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,056 once invoked, about $0.0004 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.