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/TheK3nsai/ops-brainWrote 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/thek3nsai/ops-brain/ops-brain-bus)<a href="https://agentmods.dev/plugins/thek3nsai/ops-brain/ops-brain-bus"><img src="https://agentmods.dev/badge/plugins/thek3nsai/ops-brain/ops-brain-bus/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/thek3nsai/ops-brain/ops-brain-bus"><img src="https://agentmods.dev/badge/plugins/thek3nsai/ops-brain/ops-brain-bus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ops-brain-bus 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 11d 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": "ops-brain-bus",
"displayName": "ops-brain bus",
"version": "0.1.0",
"description": "Connect your agent to a self-hosted ops-brain team bus: check in for work, accept and complete handoffs, reply in thread, and share cross-agent gotchas across machines and vendors.",
"author": {
"name": "Eduardo Romero"
},
"homepage": "https://github.com/TheK3nsai/ops-brain/tree/main/plugins/ops-brain-bus",
"repository": "https://github.com/TheK3nsai/ops-brain",
"license": "MIT OR Apache-2.0",
"logo": "assets/logo.svg",
"keywords": ["ops-brain", "ops-brain bus", "ops-brain handoff"],
"category": "developer-tools",
"tags": ["mcp", "handoffs", "multi-agent"],
"skills": "./skills/",
"mcpServers": "./mcp.json",
"variables": {
"type": "object",
"properties": {
"OPS_BRAIN_URL": {
"type": "string",
"title": "ops-brain MCP URL",
"description": "Your server's streamable HTTP endpoint, ending in /mcp (e.g. https://bus.example.com/mcp)"
},
"OPS_BRAIN_AGENT_TOKEN": {
"type": "string",
"title": "Agent token",
"description": "This agent's token from OPS_BRAIN_AGENT_TOKENS on your server. Not the main OPS_BRAIN_AUTH_TOKEN."
}
},
"required": ["OPS_BRAIN_URL", "OPS_BRAIN_AGENT_TOKEN"]
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 53 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.
- 11d ago First seen · 35 lines scan A 2bc96658aee9
ops-brain-bus is a plugin published in the GitHub repository TheK3nsai/ops-brain (1 stars, last pushed 2d ago), licensed Apache-2.0. 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 2026-10-18.
Other plugins, from other repositories
org-mcp-server
Org-mode skills for Claude Code: agenda, capture, task updates, and document search.
mcp-local-memory
Local memory for AI agents using SQLite and MCP. Remembers facts, entities, and relations across sessions.
wcode
wcode repository tools and checks, with instructions-only, local stdio and remote HTTP connection options.
rustunnel
Expose local services via secure tunnels. Create public HTTPS/TCP/UDP URLs, peer-to-peer tunnels, and load-balanced pools for webhooks, demos, and AI agent workflows.
axon
Axon research, ingestion, retrieval, and operator skills for an existing service.
install-axon
Install, configure, connect, and verify Axon with the guided installer skill and MCP connection.