A design-page generator for omit-design projects that starts from a product requirements document (PRD). It chooses an existing page pattern or creates one when no suitable pattern exists.

Use it to turn a PRD into a new page under the design directory, fill a reusable template, and register the page for automatic discovery.

It avoids rebuilding the same page structure for every design request. It also makes the chosen pattern explicit before generating the page.

new-design — Skill for Claude Code by leefanv

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 leefanv/omit-design --skill new-design

Clone the repo

git clone --depth 1 https://github.com/leefanv/omit-design

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/leefanv/omit-design/new-design.svg)](https://agentmods.dev/skills/leefanv/omit-design/new-design)

Your own site

<a href="https://agentmods.dev/skills/leefanv/omit-design/new-design"><img src="https://agentmods.dev/badge/skills/leefanv/omit-design/new-design.svg" alt="Measured on agentmods" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 903 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.

Model	Per session	Once invoked
Fable 5.1	$0.00072	$0.00903
Opus 5	$0.00036	$0.00451
Sonnet 5	$0.00014	$0.00181
Haiku 4.5	$0.00007	$0.00090

Measured 8d ago against content hash c565a4363911, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

new-design 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 8d 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.

packages/cli/templates/init/.claude/skills/new-design/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

new-design — generate a design page from a PRD

When to trigger

The user provides a PRD.
The user says "make a design for the X page" / "add a design for X".

Decision tree (stop here — confirm pattern + whitelist before going further)

Find or create the matching pattern in <project>/patterns/.
- If patterns/ is empty:
  - User provided a PRD → invoke /distill-patterns-from-prd first. Resume here only after files land and the user approves.
  - No PRD → invoke /add-pattern in conversational mode (it asks 3-5 clarifying questions and produces a minimal pattern). Resume here only after the user approves.
- If patterns/ is non-empty:
  - Read each <project>/patterns/<id>/README.md and decide. If nothing fits → invoke /add-pattern to create one. Surface the choice to the user before proceeding.
- Never pick a pattern silently — the chosen pattern name must be confirmed in chat.
All required components are on the preset Om whitelist* (exported from @omit-design/preset-mobile). If a component is missing → stop. Either re-scope the pattern via add-pattern, or propose adding an upstream Om* wrapper. Never bypass the whitelist by importing visual components directly from @ionic/react.

Execution flow

See references/checklist.md for the full 7-step checklist (read PRD / read patterns/ / check whitelist / prepare mock / copy template / self-check / verify).

The core point: step 5, "write the page," really means "copy <project>/patterns/<chosen>/template.tmpl.tsx and replace placeholders" — not write from scratch.

Delegate the mechanical work (when `pattern-applier` agent is present)

Once the HARD-GATE passes (pattern confirmed + whitelist verified) and the user has approved the chosen pattern + target path, delegate steps 5–7 (template copy → self-check → verify) to the pattern-applier sub-agent if .claude/agents/pattern-applier.md exists. This keeps the main conversation focused on user dialogue and prevents the template + lint-output from clogging context.

Read the full file on GitHub · 61 lines

Files

What ships with it

1 file 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.

references/checklist.md 3.1 KB

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.

8d ago First seen · 61 lines · 72 tokens per session scan A c565a4363911

Subscribe to this mod's changes

new-design is a skill published in the GitHub repository leefanv/omit-design (54 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 903 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 2026-08-30.

Design and UX Planning agentic-workflow ai-figma omit-design

moai-design-tools

Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.

modu-ai/moai-adk · 45 tokens

moai-domain-uiux

UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.

modu-ai/moai-adk · 49 tokens

ux-design

Create comprehensive UX design with user flows, wireframes, and design systems.

a5c-ai/babysitter · 0 tokens

premium-experience

Premium app generation that creates WOW-factor experiences. Multi-page apps with smooth animations, zero TypeScript errors, and production-ready quality. Lovable-style experience: one prompt, complete app, instant delight. MUST be used alongside vibe-orchestrator for new projects.

wasintoh/toh-framework · 56 tokens

ui-first-builder

Creates production-ready UI immediately from any description. Generates complete pages, components, and realistic mock data in FIRST response. Uses Next.js 16 + Tailwind + shadcn/ui. Never asks questions - infers everything from context. Triggers: UI creation, page building, component generation, build interface…

wasintoh/toh-framework · 75 tokens

agentic

Conversational AI-first interface with minimal controls, clear outcomes, and delegated task flows for agentic workflows.

bergside/awesome-design-skills · 24 tokens