design-web

design-web is a skill for Claude Code, Codex from fusengine/agents. It costs 36 tokens per session (3,100 once invoked), scanned A, original, MIT.

A design guide for marketing, landing, and campaign pages. It covers page structure, hero sections, calls to action, grids, spacing, motion, and checks for generic visual patterns.

In plain words
What is it for?
Use it when building or revising a public-facing marketing page, landing page, or campaign page. It guides the hero, body sections, visual hierarchy, and final silhouette review.
Why use it?
It helps marketing pages communicate one clear message without falling into repetitive layouts or default-looking interface styles.

Skill for Claude CodeCodex

Part of the fuse-design plugin — 9 skills, 5 commands, 1 agent shipped together

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.

agentmods
npx agentmods add skills/fusengine/agents/design-web
Any agent
npx skills add fusengine/agents --skill design-web
Clone the repo
git clone --depth 1 https://github.com/fusengine/agents

Made for: Claude Code, Codex.

Or install fuse-design, the plugin that ships this one along with the rest of its 9 skills, 5 commands, 1 agent.

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-web

README.md
[![agentmods](https://agentmods.dev/badge/skills/fusengine/agents/design-web.svg)](https://agentmods.dev/skills/fusengine/agents/design-web)
Your own site
<a href="https://agentmods.dev/skills/fusengine/agents/design-web"><img src="https://agentmods.dev/badge/skills/fusengine/agents/design-web.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,100 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.03100
Opus 5 $0.00018 $0.01550
Sonnet 5 $0.00007 $0.00620
Haiku 4.5 $0.00004 $0.00310

Measured yesterday against content hash 0f310abbfa90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-web 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 yesterday.

The scan reads SKILL.md. This mod also ships 6 executable files (references/refs-design/cursor-recode/motion-nav.js, references/refs-design/cursor-recode/motion-scroll.js, references/refs-design/cursor-recode/motion.js, …), 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.

plugins/design-expert/skills/design-web/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Covers hero discipline (headline/subhead word caps, single primary CTA), body-sequence selection against the canonical-order default, asymmetric grids instead of a uniform 3-column layout, and a set of mechanical anti-slop flags (uniform grids, uniform padding, the AI-signature entrance motion, the reflex blue/Inter/rounded-2xl combo).

Declares the three reproduced elements (Je reproduis, corpus procedures vs sector register) that design-review verdicts, and runs the silhouette Lookalike Test before the page can be called done: a fail is structural and goes back to the hero/body picks, not to a cosmetic tweak.

Design Web — Marketing & Landing, Register Brand

When

After design-system tokens exist and design-method's Gate 0 has locked register brand (one dominant, expressive message). Read design-method's routing table first — a dashboard/app/utility surface routes to design-webapp instead. Exception: a marketing-adjacent surface living inside an app shell (e.g. an in-app pricing page) still routes here for that one page (see design-webapp's reciprocal note).

Input

  • design-system.md — OKLCH palette, type pair, spacing density, the 3 dials.
  • ../design-method/references/register/brand.md — the page's POV sentence and the per-section Competitor Lift Test (loaded once per task, not re-read per step).
  • The generate move report (../design-method/references/moves/generate.md) if this task started from Gate 0 — steps 1-4 of that report (register, inspiration, tokens, and step 4's two picks: hero treatment + body sequence) are inputs here, not repeated.

Steps

  1. Structure comes from register + two structural picks, never from template reproduction. references/design-inspiration.md sources taste in a fixed order: the local corpus (references/refs-design/, fifteen rebuilt pages whose tokens-*.md carry measured procedures) supplies palette, typography, depth and craft; 1-2 real production sites in the client's own sector supply register only — vocabulary, codes, level of formality. Section flow, spacing rhythm and layout are never copied from either. The actual skeleton is the pair named in design-method's generate move: a hero treatment from ../design-method/references/macrostructure-bank.md (first screen only — it decides nothing past the fold) plus a body sequence from ../design-method/references/body-sequence-bank.md, both filtered through the POV in register/brand.md. Naming one without the other is an incomplete plan. Reproducing an inspiration site's structure verbatim is the single biggest source of templated output — treat it as a hard boundary, not a style preference.

Read the full file on GitHub · 180 lines

Files

What ships with it

60 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.

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. yesterday First seen · 180 lines · 36 tokens per session scan A 0f310abbfa90

Subscribe to this mod's changes

design-web is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 3,100 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 2026-09-03.