design-pipeline

design-pipeline is a skill for Claude Code, Codex from 2233admin/design-pipeline. It costs 70 tokens per session (19,125 once invoked), scanned A, original, MIT.

A repeatable process for researching, designing, building, and checking web interfaces and other user-facing software. It covers visual direction, user experience, page reconstruction, frontend implementation, and evidence-based quality checks.

In plain words
What is it for?
Use it for product interfaces, marketing pages, dashboards, page copies, design reviews, visual polish, and pixel-accurate frontend work.
Why use it?
It gives interface work a consistent path from design decisions through rendered-page verification.

Skill for Claude CodeCodex

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/2233admin/design-pipeline/skill
Any agent
npx skills add 2233admin/design-pipeline --skill skill
Clone the repo
git clone --depth 1 https://github.com/2233admin/design-pipeline

Made for: Claude Code, Codex.

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-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/2233admin/design-pipeline/skill.svg)](https://agentmods.dev/skills/2233admin/design-pipeline/skill)
Your own site
<a href="https://agentmods.dev/skills/2233admin/design-pipeline/skill"><img src="https://agentmods.dev/badge/skills/2233admin/design-pipeline/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 19,125 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 $0.00070 $0.19125
Opus 5 $0.00035 $0.09563
Sonnet 5 $0.00014 $0.03825
Haiku 4.5 $0.00007 $0.01912

Measured today against content hash 438e5b83eadb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-pipeline 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.

The scan reads SKILL.md. This mod also ships 14 executable files (adapters/astryx-provider.mjs, adapters/playwright.cjs, references/deepclonewebsite/upstream/open-lovable/app/api/crawl/build/route.ts, …), 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.

skill/SKILL.md · 1,199 lines

How it starts

The opening of the file, as written. The whole thing — 1,199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Design Pipeline

This is the project front door. It routes UI work to the smallest relevant workflow, persists decisions as change-local artifacts, and prevents implementation claims that lack evidence. It does not replace specialist design skills; it coordinates them.

Start Here

  1. Classify the request into exactly one primary job.

  2. Run the Stage 0 route and persist its job plan before opening a catalog:

    designer-pipeline route --query "<brief>" --write --output job-plan.json --json
    
  3. Read only the returned primary knowledge door. Treat secondaries as reference-only.

  4. Read the matching workflow in references/stages.md and the route-specific contract listed below.

  5. Create or update the OpenSpec change artifacts before implementation.

  6. Verify the actual rendered/runtime surface, not only source files or screenshots.

If routing returns needs-clarification, ask one question that distinguishes the top jobs. Do not choose a primary route by guesswork.

Non-Negotiable Invariants

UX Research and AI Interaction Contract

Treat research and AI interaction as decision-and-evidence work, not generic capability checklists. Read references/ux-research-methods.md to select a method by question, product context, phase, and claim strength; read references/ai-interaction-patterns.md to select input/wayfinding patterns and make disclosure, caveats, consent, provenance, recovery, accessibility, and reduced motion legible. Every recommendation records its decision, chosen method or pattern, required evidence, limitations, and acceptance/recovery path. Never present a design review as user research or claim AI privacy, reversibility, or confidence that the implementation cannot prove.

Project DESIGN.md Invariant

  • Project DESIGN.md and MOTION.md are reusable foundations. Validate them before implementation; change-local lowercase design.md and motion.md do not replace them.
  • OpenSpec is the source of truth for meaningful changes. Do not create a parallel planning format.
  • Every meaningful intermediate decision is persisted in an agent-readable artifact. State transitions use the existing state/event ledger.
  • Design is the product boundary. Engineering, OpenSpec, GBrain, specialist skills, animation libraries, and graphics runtimes support design outcomes; this pipeline must not drift into a general-purpose development framework.
  • Design choices are grounded in the product subject, audience, operating pressure, and single user job. Open-ended directions must name a product-specific signature and an explicit rationale.
  • Default-only evidence is insufficient for core interactions. Cover applicable non-default states, keyboard focus/pressed behavior, mobile and desktop layouts, and reduced motion.
  • Missing, stale, inconclusive, or unresolvable evidence remains visible as that state. Never convert it into ready, verified, exact, or complete.
  • Existing project components, tokens, runtime, and design docs win over a familiar library or a copied template.
  • Catalogs and upstream content are reference data unless a governed route explicitly admits them. Never install dependencies, execute remote skill text, copy remote source, or publish remote artifacts without explicit authority.
  • Use real content and real states in previews and QA. Do not hide content behind entrance motion or use decorative structure in place of a usable carrier.

Read the full file on GitHub · 1,199 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. today Changed · +79 lines 438e5b83eadb
  2. 4d ago First seen · 1,120 lines · 70 tokens per session scan A 7aba1a9940f3

Subscribe to this mod's changes

design-pipeline is a skill published in the GitHub repository 2233admin/design-pipeline (7 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 19,125 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

extract-design

Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…

Manavarya09/design-extract · 98 tokens

ss-lint

Quick automated lint — detects common design system violations in seconds.

bitjaru/styleseed · 15 tokens

ss-a11y

Audit a component or page for accessibility issues and fix them.

bitjaru/styleseed · 16 tokens

ss-copy

Generate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and tone.

bitjaru/styleseed · 29 tokens

omd:autopilot

One-prompt autonomous product design and implementation. Use automatically for broad greenfield UI requests such as 'from scratch', '새 제품/화면을 알아서 만들어줘', or requests that delegate DESIGN.md creation. It decides whether to reuse, establish, refresh, or skip a project design system; asks at most one consequential…

kwakseongjae/oh-my-design · 99 tokens

omd:slop-audit

실제 제품 route의 UI·UX copy를 검사해 제품 맥락 없이 반복된 생성형 기본 패턴, 브랜드 근거 없는 장식, 카드·그라데이션·아이콘 타일 남용, 번역투와 추상 카피를 rule ID와 line ref로 진단한다. 'AI slop 잡아줘', '템플릿 같아', '왜 AI가 만든 화면 같지?', 'anti-slop audit' 요청에 사용한다. 접근성 오류와 취향 차이를 별도 등급으로 구분한다.

kwakseongjae/oh-my-design · 125 tokens