A visual design-system workflow for a completed demand report. It records choices for typography, colors, layout, spacing, motion, decoration, and the overall visual direction in a DESIGN.md file.

Use it to define a brand's visual direction and create a source of truth for implementing that design.

It turns research findings into documented visual decisions while making clear which design choices are safer or more experimental.

design — Skill for Claude Code and Codex by Lab2A: A visual design-system workflow for a completed demand report.

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/lab2a/metalworks/design

Any agent

npx skills add Lab2A/metalworks --skill design

Clone the repo

git clone --depth 1 https://github.com/Lab2A/metalworks

Made for: Claude Code, Codex.

Or install metalworks, the plugin that ships this one along with the rest of its 22 skills, 1 hook, 1 MCP server.

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/lab2a/metalworks/design.svg)](https://agentmods.dev/skills/lab2a/metalworks/design)

Your own site

<a href="https://agentmods.dev/skills/lab2a/metalworks/design"><img src="https://agentmods.dev/badge/skills/lab2a/metalworks/design.svg" alt="Measured on agentmods" height="20"></a>

Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,231 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.

Model	Per session	Once invoked
Fable 5	$0.00148	$0.01231
Opus 5	$0.00074	$0.00616
Sonnet 5	$0.00030	$0.00246
Haiku 4.5	$0.00015	$0.00123

Measured 4d ago against content hash 79321e0c91cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

plugin/skills/design/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preamble (run first)

Before any other tool, run the preflight MCP tool (or metalworks preflight on the CLI). If it reports setup issues or that an update is available, surface that to the user in one line and help them resolve it (install the missing extra/key, or pip install -U metalworks) before continuing. Skip only if the user has already passed preflight this session.

Read the reference; never reverse-engineer the source. The moment you need to know how metalworks behaves — provider/model resolution, which source/reader runs, config precedence, an error you hit, or the async run loop — STOP and read docs/operating-metalworks.md (bundled with this plugin) before opening any file under src/. It is the source of truth; do not derive behavior from source. (Full docs: https://metalworks.lab2a.ai/docs.) For a long-running run, poll status with the Monitor tool or a bounded loop — never a blind sleep.

You are authoring the VISUAL design system for one report — the look's counterpart to positioning's words. Unlike copy, design is taste, so grounding here is DIRECTIONAL, never cited: the competitive landscape INFORMS the bet ("rivals skew serif → lean serif, or break to sans"); it does not cite it. Two honesty signals carry the weight: every choice is labelled SAFE (category baseline) or RISK (a deliberate departure), and the system records its GROUNDING TIER so the look is never overstated.

Steps

Get the report_id. No report yet → run /demand-report first; a design system stands on the report's audience + the competitive landscape.
Call the design_from_report MCP tool with the report_id (and name for the brand, else the model suggests one). On the CLI: metalworks design <report_id>. It builds the landscape, reads the competition at the richest tier available, and returns a DesignSystem + a self-contained preview HTML. It writes a DESIGN.md.

Pick a taste preset (the director voice) — pass taste= (MCP) or --taste (CLI). One small, curated set, each an opinionated director:
- editorial — the default house voice (editorial monochrome, dark-first). Use when the brief is silent; it preserves the original output.
- brutalist — raw, structural, anti-decorative; one loud signal color, hard edges.
- warm-minimal — calm, warm, paper-ground; a single muted earthy accent.
- technical — instrument-grade tool aesthetic; mono/grotesque, dense, precise.

Read the full file on GitHub · 82 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.

4d ago First seen · 82 lines · 148 tokens per session scan A 79321e0c91cd

Subscribe to this mod's changes

design is a skill published in the GitHub repository Lab2A/metalworks (6 stars, last pushed 2mo ago), licensed MIT. It adds 148 tokens to every session and 1,231 once invoked, about $0.0007 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.

Design and UX Marketing and SEO

material-ui-tailwind

Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.

mui/material-ui · 67 tokens

hallmark

Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.

Nutlope/hallmark · 61 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens

design