DESIGN.md is a structured markdown file that defines your project's brand spec — tokens (colors, typography, spacing, radius), voice, narrative, principles, personas, states, and motion. AI coding agents (Claude Code, Codex, OpenCode, Cursor) read it as authoritative context before generating any UI, so the output looks like your brand instead of generic 'modern minimalist' slop.

How does oh-my-design work?

Run `npx oh-my-design-cli install-skills` once in your project. It installs 18 skills (core flow + live-capture + asset + the v0.2 agent layer: orchestrator, kr-writer, locale-adapter, designer-review, final-qa, codex-image), 16 sub-agents (master orchestrator + 15 specialists), 4 hooks, and 356 reference DESIGN.md files. After restarting your AI coding agent, you just talk in natural language — skills route to the right sub-agents automatically.

Does it call any AI provider during install?

No. The install is a pure markdown copy — zero API calls, zero data leaves your machine. Your AI coding agent (Claude Code, Codex, OpenCode, or Cursor) is the inference layer; install just teaches it where to look.

Which AI coding agents are supported?

Claude Code, Codex, OpenCode, and Cursor — Cursor has a dedicated install channel (--agent cursor) that writes the .cursor/rules shim plus the shared reference catalog. The skill markdown files are agent-agnostic; hooks ship for Claude Code specifically.

What is the design harness?

The omd-harness skill runs a 10-phase design pipeline (Discovery → Research → IA → Wireframes → Design system → Components → Asset sourcing → Microcopy → Validation → Handoff). It dispatches sub-agents in parallel where independent, asks 3 mandatory user checkpoints, and emits a v0/Cursor-ready package. Trigger it by saying things like 'design the entire onboarding from scratch' or '/omd-harness '.

Yes — MIT licensed, open source, no signup, no API key, no paid tier. The references in the bundle belong to their respective companies and are reproduced for educational reference only.

oh-my-design v1.8.7 (2026-06-26)

30 new Korean company references added (catalog 326 → 356; KR refs 119 → 149) via the full 탐색→선발→수집→검수→배포 pipeline — every ref Tier-1 brand-owned proof-gated.

Coverage deliberately steered toward under-represented categories: AI 7 (nota·rebellions·furiosaai·returnzero·makinarocks·supertone·neosapience), marketing 4 (airbridge·buzzvil·datarize·bigin), education 3 (goorm·elice·codeit), SaaS 3 (saramin·lemonbase·shiftee), ecommerce 3 (kyobobook·cafe24·queenit), developer-tools 2 (hackle·solapi), backend-devops 2 (lablup·moreh), consumer-tech 2 (hwahae·weverse), fintech 2 (portone·kcd), automotive 1 (greencar), healthcare 1 (vuno).
Standouts carry named / official design systems: goorm (Vapor UI), 교보문고 (KDS), 화해 (HDS), cafe24 (Smart Design), lablup (Backend.AI WebUI).
Discovery fanned 8 sector agents (101 raw → 89 unique, deduped vs the full 326-id catalog); two LLM-drift duplicates caught at curation (wadiz, yeogi==yeogiotte) and swapped for clean alternates. Build ran one CREATE subagent per brand in waves of 5 (Tier-1 live Playwright getComputedStyle over ≥2 brand-owned surfaces each).
All 30 pass verify-reference 27/27 + catalog-integrity (16 files / 594 tests). KR proof gate met for every ref: ≥2 brand-owned Tier-1 sources + ## Proof block (≥80 raw computed-style samples). Tier 2 (getdesign / refero) empty for all 30, as spec/regional-sources.yaml anticipates.
Audit: data/reference-audits/2026-06-26-kr30.md (23 High / 7 Medium / 0 Low). Counts propagated by sync-catalog.mjs (README ×4, llms.txt, SEO layouts, fingerprints ×3, design-md mirror).