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 agentmods add plugins/saadeghi/daisyui/blueprint/plugin marketplace add saadeghi/daisyuigit clone --depth 1 https://github.com/saadeghi/daisyuiGrade A, and why
daisyui-blueprint 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 yesterday.
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
{
"name": "daisyui-blueprint",
"displayName": "daisyUI Blueprint MCP",
"version": "1.5.0",
"description": "Official daisyUI MCP server. Requires a paid license from https://daisyui.com/blueprint",
"author": {
"name": "daisyUI",
"url": "https://daisyui.com"
},
"homepage": "https://daisyui.com/blueprint",
"repository": "https://github.com/saadeghi/daisyui",
"license": "Paid license",
"keywords": ["ui", "tailwind", "components", "figma", "daisyui"],
"userConfig": {
"license": {
"type": "string",
"title": "Blueprint License Key",
"description": "Get your license key from https://daisyui.com/blueprint",
"sensitive": true,
"required": true
},
"email": {
"type": "string",
"title": "Email",
"description": "Email used for your Blueprint license",
"required": true
},
"figma_api_key": {
"type": "string",
"title": "Figma Personal Access Token (optional)",
"description": "Get it from Figma: \nSettings > Security > Personal Access Tokens > Generate new token. \nRequired permissions are \n`file_content:read` \n`file_metadata:read` \n`library_assets:read` \n`library_content:read` \n`team_library_content:read` \n`file_dev_resources:read`",
"sensitive": true,
"required": false
}
},
"mcpServers": "./mcp.json"
}
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.
- yesterday First seen · 38 lines scan A d56ee7568bee
daisyui-blueprint is a plugin published in the GitHub repository saadeghi/daisyui (42,247 stars, last pushed 8d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
genjutsu
Plugin marketplace listing 1 plugin: genjutsu.
cranpose-marketplace
Plugin marketplace listing 1 plugin: cranpose.
marmoui-plugins
Claude Code plugins for Marmo UI — the AI agentic designer. Install marmo-ui to give Claude a real design system: live component APIs, patterns, and validated generation.
design-to-ui-marketplace
Plugin marketplace listing 1 plugin: design-to-ui.
ai-design-components
Comprehensive full-stack development skills for AI-assisted development covering UI/UX, backend, DevOps, infrastructure, security, and AI/ML.
figma-design-skills
Two composable skills for design-to-code fidelity: figma-design-extract pulls exact specs from Figma into a build-ready spec table; design-fidelity-verify proves the running web or mobile app matches them by measuring rendered values.