Design System — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Design System (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Design tokens in Git. Readable by AI. Beautiful to edit.
This repo is managed by Basalt — a design system platform that stores tokens, components, and documentation in Git and serves them to AI coding tools via MCP.
tokens/
├── primitives.json # Raw values (colors, spacing, radii)
├── semantic.light.json # Light theme semantic tokens
└── semantic.dark.json # Dark theme semantic tokensAll tokens use the DTCG 2025.10 format (W3C standard).
Basalt serves this design system to Cursor, Claude Code, Claude Design, and Windsurf via an MCP server. AI tools query your real token values instead of guessing.
See [MCP.md](MCP.md) for setup instructions and available tools.
Quick config (Cursor / Claude Code / Windsurf):
{
"mcpServers": {
"basalt": {
"url": "https://basalt.run/api/mcp",
"headers": {
"Authorization": "Bearer bsk_your_key_here"
}
}
}
}Get a free API key at basalt.run.
Three tiers, each referencing the layer above:
Primitive → raw values (color.orange.500 = #F97316) Semantic → intent + theming (color.action.default → color.orange.500) Component → scoped to UI elements (button.background.default → color.action.default)
AI tools resolve the full chain automatically via MCP.
basaltMIT — see LICENSE.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.