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.
npx skills add aiatelie/ai-atelie --skill design-md-authorgit clone --depth 1 https://github.com/aiatelie/ai-atelieWrote 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.
[](https://agentmods.dev/skills/aiatelie/ai-atelie/design-md-author)<a href="https://agentmods.dev/skills/aiatelie/ai-atelie/design-md-author"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/design-md-author/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.
<a href="https://agentmods.dev/skills/aiatelie/ai-atelie/design-md-author"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/design-md-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00059 | $0.01871 |
| Opus 5 | $0.00030 | $0.00936 |
| Sonnet 5 | $0.00012 | $0.00374 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
design-md-author 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DESIGN.md author
Read, write, or update a DESIGN.md at the project root. DESIGN.md is the Google-Labs-published cross-tool spec for documenting a design system: tokens, typography, components, motion, do's-and-don'ts. When present, it grounds every subsequent prompt in this project — the agent reads it as project-context before generating UI.
When to use
- The user asks to "set up the design system", "create a DESIGN.md", "import this design system", "capture our look".
- A project doesn't have a
DESIGN.mdyet and the user wants to commit to a direction once instead of re-deciding per prompt. - The user wants to import a DESIGN.md from elsewhere (a Stitch export, a community gallery, another project).
- The user wants to update tokens, typography rules, or component specs declared in the project's existing
DESIGN.md.
Skip when:
- The user is generating a one-off design —
DESIGN.mdis for projects with continuity, not single artifacts. - The change is implementation, not specification. (Component code changes go through
frontend-design; the DESIGN.md only changes when the spec shifts.)
The schema (Google spec)
A valid DESIGN.md has YAML front-matter and a fixed set of markdown sections in order. Every section is required.
---
version: "0.1.0"
name: "Project name"
description: "One-sentence aesthetic direction."
colors:
bg: "#hex"
surface: "#hex"
ink: "#hex"
brand: "#hex"
# … semantic tokens, named by purpose
typography:
display: "Font Name, fallback"
body: "Font Name, fallback"
mono: "Font Name, fallback"
rounded:
none: "0"
sm: "4px"
md: "8px"
lg: "16px"
spacing:
unit: "4px"
scale: [0, 1, 2, 3, 4, 6, 8, 12, 16, 24]
components:
button:
primary:
bg: "{colors.brand}"
ink: "{colors.bg}"
# … per-component variants
---
Token references use {path.to.token} so semantic relationships survive when individual values change.
Required markdown sections, in this order:
## Overview— the aesthetic direction in 2–4 paragraphs. What feeling, what posture, what's the differentiation.## Colors— semantic role per color, with hex and a one-line use-case. Reference front-matter tokens.## Typography— display vs body vs mono roles, the type scale, tracking rules, letter-spacing floors.## Layout— grid system, spacing scale, breakpoints, content max-widths.## Elevation & Depth— shadow tokens, when to use which.## Shapes— radii, border weights, decorative elements.## Components— per-component spec: button, card, input, dialog, navigation, etc. Each with state variants (default, hover, active, disabled, error).## Do's and Don'ts— the project-specific anti-patterns, paired with what to do instead.
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.
- 12d ago First seen · 152 lines · 59 tokens per session scan A 77aff50f43e9
design-md-author is a skill published in the GitHub repository aiatelie/ai-atelie (8 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,871 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.
Other skills, from other repositories
design-brief
Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief"…
open-design-landing
Produce a world-class single-page editorial landing site in the Atelier Zero visual language (Monocle / Apartamento / Études editorial collage) — the same aesthetic OpenDesign uses for its own marketing surface. The agent fills a typed inputs.json from a brand brief, optionally generates 16 collage assets via…
tweaks
Wrap any HTML artifact with a side panel of live, parameterized controls — accent color, type scale, density, motion, theme — that rewrite CSS custom properties in real time and persist to localStorage. Lets the user explore variants of a design without re-prompting the agent. Use when the brief asks for "variants"…
fs-electric-studio
OpenDesign as an enterprise design platform: a buyer-forwardable proposal for a design-org's economic buyer — pain, value, ROI, rollout. Built as a decision-grade B2B sales deck for economic buyer, design VP, procurement.
critique
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.