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/2aronS/notion-md-agentWrote 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/2arons/notion-md-agent/notion-md-agent)<a href="https://agentmods.dev/plugins/2arons/notion-md-agent/notion-md-agent"><img src="https://agentmods.dev/badge/plugins/2arons/notion-md-agent/notion-md-agent/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/2arons/notion-md-agent/notion-md-agent"><img src="https://agentmods.dev/badge/plugins/2arons/notion-md-agent/notion-md-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
notion-md-agent 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 1mo 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": "notion-md-agent",
"description": "Comprehensive Notion API integration — 9 composite tools, ~95% coverage",
"version": "2.33.2",
"userConfig": {
"NOTION_TOKEN": {
"type": "string",
"title": "Notion integration token",
"description": "From https://www.notion.so/my-integrations (starts with ntn_)",
"sensitive": true,
"required": true
}
},
"author": {
"name": "user",
"url": "https://github.com/user"
},
"homepage": "https://github.com/user/notion-md-agent",
"mcpServers": {
"notion-md-agent": {
"command": "npx",
"args": [
"--yes",
"@user/notion-md-agent@latest"
],
"env": {
"MCP_TRANSPORT": "stdio",
"NOTION_TOKEN": "${user_config.NOTION_TOKEN}"
}
}
}
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 42 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.
- 1mo ago First seen · 33 lines scan A 50a8c4155332
notion-md-agent is a plugin published in the GitHub repository 2aronS/notion-md-agent (9 stars, last pushed 5mo 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.
Other plugins, from other repositories
founder-os
An operating system with your first team already on it. Five named digital employees with written job descriptions, gated until you grade their runs, plus a brain that keeps everything you tell it in plain markdown you own. 97 skills, 47 commands, six role modes. The setup wizard interviews you and builds the OS…
pm-job-search
An opinionated daily-driver for senior PM / Head of Product job searches. Pure markdown, zero external dependencies.
codex-obsidian-loop
Task-driven Codex + Obsidian loop for agent memory, source boundaries, durable result writeback, and lint.
Pagecraft marketplace
Pagecraft combines a durable wiki control plane with an execution layer for ambiguity control, minimal edits, and verified outcomes. It supports active-memory retrieval through wiki/hot.md, canonical index/log discipline, immutable raw sources, and reusable ingest workflows.
agent-deck
Complete guide for managing AI coding agent sessions via agent-deck CLI - session lifecycle, MCP management, groups, profiles, and automation.
handoff
Session quality gate for Claude Code. Health checks, resume points, and cross-machine continuity.