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/duvoai/skillsWrote 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/duvoai/skills/duvo)<a href="https://agentmods.dev/plugins/duvoai/skills/duvo"><img src="https://agentmods.dev/badge/plugins/duvoai/skills/duvo/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/duvoai/skills/duvo"><img src="https://agentmods.dev/badge/plugins/duvoai/skills/duvo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
duvo 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 8d 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": "duvo",
"source": "./",
"displayName": "Duvo",
"description": "Operate Duvo from Claude: debug failed Runs, audit Agents and Queues, doctor Connections, and write AOPs — with the Duvo MCP connector wired in.",
"category": "productivity",
"skills": [
"./skills/aop-writer",
"./skills/run-debugger",
"./skills/workflow-debugger",
"./skills/connection-doctor",
"./skills/improve-agent",
"./skills/improve-queue"
],
"mcpServers": {
"duvo": {
"type": "http",
"url": "https://api.duvo.ai/v2/mcp"
}
}
}What it installs
The manifest is a name and a version. 6 skills travel with it, and installing the plugin installs all of them — 879 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
2 files beside marketplace.json#duvo 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.
- 8d ago First seen · 21 lines scan A 8f98c411c409
duvo is a plugin published in the GitHub repository duvoai/skills (7 stars, last pushed 2d 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 2026-09-04.
Other plugins, from other repositories
agent-deck
Complete guide for managing AI coding agent sessions via agent-deck CLI - session lifecycle, MCP management, groups, profiles, and automation.
vault-template
Personal Knowledge Management system for Obsidian with AI-powered workflows, goal tracking, and productivity coaching.
obw
Obsidian Workspace — project-scoped vault productivity (capture / notes / PM). Skills-only: owns folder layout and templates; /obw:pm splits a spec into blocking tickets; runs the Obsidian CLI directly via the official obsidian-cli skill.
clipboard-mcp-server
Read, write, and inspect the system clipboard across macOS, Linux (X11/Wayland), and Windows via MCP. STDIO or Streamable HTTP.
paigy
Call, text, or push the user's phone when you need input mid-task — get their answer by voice or reply, then continue. For long-running or blocked agent work.
handoff
Session quality gate for Claude Code. Health checks, resume points, and cross-machine continuity.