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 HK-hub/AgentSkills --skill awesome-design-mdgit clone --depth 1 https://github.com/HK-hub/AgentSkillsWrote 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/hk-hub/agentskills/awesome-design-md)<a href="https://agentmods.dev/skills/hk-hub/agentskills/awesome-design-md"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/awesome-design-md/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/hk-hub/agentskills/awesome-design-md"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/awesome-design-md.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 | $0.00096 | $0.02534 |
| Opus 5.5 | $0.00038 | $0.01014 |
| Sonnet 5.5 | $0.00019 | $0.00507 |
| Haiku 4.5 | $0.00010 | $0.00253 |
Grade A, and why
awesome-design-md 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 1mo 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Awesome DESIGN.md
A curated collection of 54 DESIGN.md files extracted from real, developer-focused websites. Each file is a complete design system specification that AI agents can read to generate pixel-perfect, brand-consistent UI.
What is DESIGN.md?
DESIGN.md is a concept introduced by Google Stitch — a plain-text design system document that AI agents read to generate consistent UI. It's just a markdown file. Drop it into your project root and any AI coding agent instantly understands how your UI should look.
How to Use
- User says "make it look like [brand]" → Find the matching reference file below
- Read the reference file from
references/{site-name}.md - Copy the DESIGN.md content into the user's project root as
DESIGN.md - Use the design tokens (colors, typography, spacing, components) when generating UI code
Available Design Systems
AI & Machine Learning
| Site | Reference | Style |
|---|---|---|
| Claude | references/claude.md |
Warm terracotta accent, clean editorial layout |
| Cohere | references/cohere.md |
Vibrant gradients, data-rich dashboard aesthetic |
| ElevenLabs | references/elevenlabs.md |
Dark cinematic UI, audio-waveform aesthetics |
| Minimax | references/minimax.md |
Bold dark interface with neon accents |
| Mistral AI | references/mistral.ai.md |
French-engineered minimalism, purple-toned |
| Ollama | references/ollama.md |
Terminal-first, monochrome simplicity |
| OpenCode AI | references/opencode.ai.md |
Developer-centric dark theme |
| Replicate | references/replicate.md |
Clean white canvas, code-forward |
| RunwayML | references/runwayml.md |
Cinematic dark UI, media-rich layout |
| Together AI | references/together.ai.md |
Technical, blueprint-style design |
| VoltAgent | references/voltagent.md |
Void-black canvas, emerald accent, terminal-native |
| xAI | references/x.ai.md |
Stark monochrome, futuristic minimalism |
What ships with it
55 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.
- _skillhub_meta.json 158 B
- references/airbnb.md 14 KB
- references/airtable.md 3.5 KB
- references/apple.md 20 KB
- references/bmw.md 9.6 KB
- references/cal.md 17 KB
- references/claude.md 20 KB
- references/clay.md 17 KB
- references/clickhouse.md 15 KB
- references/cohere.md 14 KB
- references/coinbase.md 4.9 KB
- references/composio.md 20 KB
- references/cursor.md 19 KB
- references/elevenlabs.md 15 KB
- references/expo.md 18 KB
- references/figma.md 11 KB
- references/framer.md 17 KB
- references/hashicorp.md 15 KB
- references/ibm.md 19 KB
- references/intercom.md 6.3 KB
- references/kraken.md 4.2 KB
- references/linear.app.md 22 KB
- references/lovable.md 17 KB
- references/minimax.md 14 KB
- references/mintlify.md 17 KB
- references/miro.md 4.7 KB
- references/mistral.ai.md 15 KB
- references/mongodb.md 15 KB
- references/notion.md 18 KB
- references/nvidia.md 17 KB
- references/ollama.md 15 KB
- references/opencode.ai.md 15 KB
- references/pinterest.md 12 KB
- references/posthog.md 18 KB
- references/raycast.md 18 KB
- references/replicate.md 14 KB
- references/resend.md 18 KB
- references/revolut.md 8.4 KB
- references/runwayml.md 14 KB
- references/sanity.md 21 KB
- references/sentry.md 14 KB
- references/spacex.md 11 KB
- references/spotify.md 13 KB
- references/stripe.md 20 KB
- references/supabase.md 14 KB
- references/superhuman.md 18 KB
- references/together.ai.md 14 KB
- references/uber.md 18 KB
- references/vercel.md 19 KB
- references/voltagent.md 26 KB
- references/warp.md 16 KB
- references/webflow.md 4.0 KB
- references/wise.md 8.3 KB
- references/x.ai.md 16 KB
- references/zapier.md 18 KB
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.
- 1mo ago First seen · 178 lines · 96 tokens per session scan A 4c0d7f928c8a
awesome-design-md is a skill published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 2,534 once invoked, about $0.0004 per session on Opus 5.5. 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
mermaid
Create, validate, and repair Mermaid.js diagrams. Use when generating flowcharts, sequence, class, ER, state, or Gantt diagrams, or any visualization.
archify
Create validated architecture, workflow, sequence, data-flow, lifecycle/state, ERD, class, tree, timeline, and waterfall diagrams as explorable standalone HTML with dark/light themes, motion and image/SVG/WebM export. Accept requirements or Mermaid; inspect repository evidence for code-backed diagrams. Use when…
archify-tuning
Improve Archify diagram accuracy, visual quality and complete authoring speed with fewer repairs. Use for generation experiments or evaluating changes to layout, routing, diagnostics, authoring instructions and acceptance rules against actual diagrams and agent traces.
loft
Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks.…
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces: an Apple HIG-based checklist, paired light/dark captures at phone and desktop widths, screenshot evidence, and a per-item PASS/FAIL verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right or follows the…
frontend
Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain…