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.
git clone --depth 1 https://github.com/referodesign/refero_skillWrote 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/plugins/referodesign/refero_skill/gemini-extension)<a href="https://agentmods.dev/plugins/referodesign/refero_skill/gemini-extension"><img src="https://agentmods.dev/badge/plugins/referodesign/refero_skill/gemini-extension/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/plugins/referodesign/refero_skill/gemini-extension"><img src="https://agentmods.dev/badge/plugins/referodesign/refero_skill/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
refero 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
{
"name": "refero",
"version": "1.0.3",
"description": "Research real product interfaces and design with evidence from Refero.",
"mcpServers": {
"refero": {
"httpUrl": "https://api.refero.design/mcp"
}
}
}
What ships with it
3 files beside gemini-extension.json 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.
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 Changed 5494d210aad0
- 1mo ago First seen · 11 lines scan A 52d05ca2662e
refero is a plugin published in the GitHub repository referodesign/refero_skill (326 stars, last pushed 10d 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 2026-09-06.
Other plugins, from other repositories
figma-mcp-bridge
Figma tasarım verilerini 63 MCP aracı ile AI asistanlarına açar. 29 uzman skill, 10 komut. REST API token gerektirmez, Zero Trust mimarisi.
canicode
Lint Figma designs for AI code-gen and roundtrip the answers back into the file. CLI + MCP server.
whimsical
Whimsical's official MCP server. Create and edit boards, docs, flowcharts, mind maps, sequence diagrams, wireframes, tables and sticky notes, then read, search and comment on anything already in the workspace. OAuth 2.1, no API key; a free Whimsical account can use every tool.
yesterday-pages
Use when Markdown, research, concepts, analyses, offers, image folders, or mechanisms need to become a branded Yesterday HTML page, visual report, whitepaper, visual story, data narrative, interactive explainer, or lightweight prototype.
skills-for-figma
18 skills for the native Figma MCP: export/import design tokens, manage variables, analyze and document component sets, lint for WCAG and design-system compliance, audit accessibility, and author Slides and FigJam content.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.