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/Wuniq/wuniq-mcpWrote 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/wuniq/wuniq-mcp/wuniq-mcp)<a href="https://agentmods.dev/plugins/wuniq/wuniq-mcp/wuniq-mcp"><img src="https://agentmods.dev/badge/plugins/wuniq/wuniq-mcp/wuniq-mcp/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/wuniq/wuniq-mcp/wuniq-mcp"><img src="https://agentmods.dev/badge/plugins/wuniq/wuniq-mcp/wuniq-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
wuniq 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 2mo 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "wuniq",
"displayName": "Wuniq",
"version": "1.0.0",
"description": "A local-first knowledge engine for AI-assisted software work. Requires the free Wuniq desktop app, currently available for Windows and Linux.",
"author": {
"name": "Wuniq",
"email": "[email protected]",
"url": "https://www.wuniq.com/"
},
"homepage": "https://www.wuniq.com/",
"repository": "https://github.com/Wuniq/wuniq-mcp",
"license": "MIT",
"keywords": [
"knowledge-engine",
"memory",
"mcp",
"local-first",
"developer-tools"
]
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 51 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 2mo ago First seen · 23 lines scan A d685c9e97584
wuniq is a plugin published in the GitHub repository Wuniq/wuniq-mcp (0 stars, last pushed 3mo 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 2026-08-31.
wuniq compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wuniqWuniq/wuniq-mcp | Plugin | 0 | 3mo ago | MIT | A | — | Claude Code |
| anytype-toolbox-skillsstevelr/anytype | Plugin | 34 | 1mo ago | Apache-2.0 | A | — | Claude Code |
| obsidian-wikiAr9av/obsidian-wiki | Plugin | 3.7k | 3d ago | MIT | A | — | Claude Code |
| mindosGeminiLight/MindOS | Plugin | 705 | today | MIT | A | — | Claude Code |
| engraphis-memoryCoding-Dev-Tools/engraphis | Plugin | 182 | today | Apache-2.0 | A | — | Claude Code |
| journalmpazik/Binder | Plugin | 40 | 19d ago | MIT | A | — | Claude Code |
| liansLians-ai/Lians | Plugin | 17 | 6d ago | Apache-2.0 | A | — | Claude Code |