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/sageox/oxWrote 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/sageox/ox/cursor-plugin)<a href="https://agentmods.dev/plugins/sageox/ox/cursor-plugin"><img src="https://agentmods.dev/badge/plugins/sageox/ox/cursor-plugin/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/sageox/ox/cursor-plugin"><img src="https://agentmods.dev/badge/plugins/sageox/ox/cursor-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sageox 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": "sageox",
"displayName": "SageOx",
"version": "1.0.0",
"minClientVersions": {
"cursor": "never"
},
"description": "Search your team's discussions, docs, and sessions, and save chats to Team Context.",
"author": {
"name": "SageOx",
"email": "[email protected]"
},
"homepage": "https://sageox.ai/docs/mcp",
"repository": "https://github.com/sageox/ox",
"license": "MIT",
"logo": "assets/logo.png",
"keywords": [
"sageox",
"sageox team context"
],
"category": "integrations",
"tags": [
"sageox",
"mcp"
],
"mcpServers": "./mcp.json",
"skills": "./skills/"
}
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 First seen · 29 lines scan A 321214363fd3
sageox is a plugin published in the GitHub repository sageox/ox (64 stars, last pushed today), 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 2026-10-09.
Other plugins, from other repositories
contorium
Contorium: AI Project Intelligence Layer — project cognition assets for Claude Code via MCP inspect and CLI derive.
agent-recall
Persistent memory system for Claude Code - knows who it is, who you are, and what you were doing.
agent-recall
Persistent memory system for AI coding agents - knows who it is, who you are, and what you were doing.
rembric
Memory for Claude Code, backed by your self-hosted Rembric server.
ravenclaw
Personal work context management for AI-powered development. Track epics, issues, wiki pages, and knowledge ontology across AI agent sessions.
agent-reflectmem
Cross-session shell reflection memory for code agents with SQLite persistence and guardable automation.