DESIGN.md: A format spec for describing visual identity to coding agents

Google Labs released DESIGN.md, a format specification for describing a visual identity to coding agents. The file combines machine-readable design tokens (YAML front matter) with human-readable design rationale (markdown prose). Tokens give agents exact values; prose explains why those values exist and how to apply them.
Format Overview
A DESIGN.md file has two layers delimited by --- fences at the top: YAML front matter for tokens and a markdown body with ## sections. Example excerpt:
---
name: "Heritage"
colors:
primary: "#1A1C1E"
secondary: "#6C7278"
tertiary: "#B8422E"
neutral: "#F7F5F2"
typography:
h1:
fontFamily: "Public Sans"
fontSize: "3rem"
body-md:
fontFamily: "Public Sans"
fontSize: "1rem"
label-caps:
fontFamily: "Space Grotesk"
fontSize: "0.75rem"
rounded:
sm: "4px"
md: "8px"
spacing:
sm: "8px"
md: "16px"The tokens are the normative values. Prose provides context for application.
Key Features
- Token types: Colors (hex sRGB), Typography objects (fontFamily, fontSize, fontWeight, lineHeight, letterSpacing, fontFeature, fontVariation), Dimensions (number+unit), Token references (
{path.to.token}). - Components: Map a name to sub-token properties, e.g.
components.button-primary.backgroundColor: "{colors.tertiary}". - Section order (optional but enforced): Overview, Colors, Typography, Layout & Spacing, Elevation & Depth, Shapes, Components, Do's and Don'ts.
CLI Tools
Validate a DESIGN.md with the linter:
npx @google/design.md lint DESIGN.md
{
"findings": [
{
"severity": "warning",
"path": "components.button-primary",
"message": "textColor (#ffffff) on backgroundColor (#1A1C1E) has contrast ratio 15.42:1 — passes WCAG AA."
}
],
"summary": { "errors": 0, "warnings": 1, "info": 1 }
}Detect regressions between versions:
npx @google/design.md diff DESIGN.md DESIGN-v2.md
{
"tokens": {
"colors": {
"added": ["accent"],
"removed": [],
"modified": ["tertiary"]
},
"typography": { "added": [], "removed": [], "modified": [] }
},
"regression": false
}Use Case
An agent reading the Heritage example will produce a UI with deep ink headlines in Public Sans, a warm limestone background (#F7F5F2), and Boston Clay (#B8422E) call-to-action buttons — all from a single file.
📖 Read the full source: HN AI Agents
👀 See Also

ClawControl v1.7.1 fixes daily usage issues in OpenClaw client
ClawControl v1.7.1 is an open source client for OpenClaw available on Windows, Mac, Linux, iOS, and Android. This release focuses on fixing 'why is it doing that?' issues encountered during daily OpenClaw usage.

Crit: Local-first, single-binary CLI for reviewing agent plans and diffs
Crit is a single-binary CLI that opens files or diffs in a browser with a GitHub-inspired UI, allowing multi-round feedback loops with AI coding agents — no account needed.
Hugging Face's physics-intern: Multi-Agent Framework Doubles Gemini on CritPt Benchmark
Hugging Face released physics-intern, a multi-agent framework for theoretical physics research that doubles Gemini models' performance on the CritPt benchmark and sets a new SOTA vs GPT-5.5 Pro at lower cost.

tmux-IDE: A Terminal-Based Multi-Agent IDE for Claude
tmux-IDE is an open-source, declarative terminal IDE focused on agentic engineering that creates multi-agent layouts for Claude coding agents. It allows developers to boot into their IDE through SSH, give prompts to Claude, and close their machine while Claude continues working in tmux sessions.