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 freema/mcp-design-system-extractor --skill design-extractiongit clone --depth 1 https://github.com/freema/mcp-design-system-extractorWrote 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/freema/mcp-design-system-extractor/design-extraction)<a href="https://agentmods.dev/skills/freema/mcp-design-system-extractor/design-extraction"><img src="https://agentmods.dev/badge/skills/freema/mcp-design-system-extractor/design-extraction/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/freema/mcp-design-system-extractor/design-extraction"><img src="https://agentmods.dev/badge/skills/freema/mcp-design-system-extractor/design-extraction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00452 |
| Opus 5 | $0.00024 | $0.00226 |
| Sonnet 5 | $0.00010 | $0.00090 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
design-extraction 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 9d 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.
What it actually says
When the user asks about design systems or building UIs with components, use the design-system MCP tools.
When to Use This Skill
Activate when the user:
- Asks about available components ("What buttons do we have?", "List form components")
- Needs component HTML ("Extract the card component", "Get the modal HTML")
- Wants theme info ("What colors are available?", "Show me the spacing scale")
- Builds UIs ("Create a login form using our components")
- Analyzes components ("What components does the header use?")
Tools Reference
| Task | Tool |
|---|---|
| List all | list_components (use compact: true) |
| Search | search_components |
| Extract HTML | get_component_html (async) |
| Check variants | get_component_html with variantsOnly: true |
| Get theme | get_theme_info |
| Get CSS | get_external_css |
| Dependencies | get_component_dependencies |
| Job status | job_status |
Async Operations
get_component_html is async by default:
get_component_html componentId="button--primary"
→ Returns: { job_id: "abc123" }
job_status jobId="abc123"
→ Returns: { status: "completed", result: "<button>..." }
Component ID Format
button--primary # component--story
card--default # component--story
button # auto-resolves to default variant
Example Workflows
List and extract:
list_components compact=true
get_component_html componentId="button" variantsOnly=true
get_component_html componentId="button--primary"
job_status jobId="..."
Build with theme:
get_theme_info
search_components purpose="form inputs"
get_component_html componentId="input--default"
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.
- 9d ago First seen · 67 lines · 49 tokens per session scan A 79ab4551251c
design-extraction is a skill published in the GitHub repository freema/mcp-design-system-extractor (69 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 452 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
uswds
Build, audit, or convert websites with the U.S. Web Design System (USWDS) using the unofficial uswds-mcp server. Use when work involves USWDS components, patterns, templates, accessibility guidance, design tokens, utilities, @uswds/uswds, or federal website implementation.
daisyui-colors
Color rules that you must use with daisyUI 5.
daisyui-config
Configuration options for daisyUI 5.
seed-design
An integration guide for SEED Design, covering shared component specifications and foundations plus React and Lynx implementation guidance.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
ss-lint
Quick automated lint — detects common design system violations in seconds.