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/jmagar/claude-homelabWrote 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/jmagar/claude-homelab/marketplace)<a href="https://agentmods.dev/plugins/jmagar/claude-homelab/marketplace"><img src="https://agentmods.dev/badge/plugins/jmagar/claude-homelab/marketplace/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/jmagar/claude-homelab/marketplace"><img src="https://agentmods.dev/badge/plugins/jmagar/claude-homelab/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
claude-homelab marketplace 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "claude-homelab",
"owner": {
"name": "jmagar",
"email": "[email protected]"
},
"metadata": {
"description": "Comprehensive Claude Code skills and agents for homelab service management - media automation, infrastructure monitoring, document management, and more",
"version": "1.1.0"
},
"plugins": [
{
"name": "homelab-core",
"source": "./",
"description": "Core homelab plugin bundling shared agents, commands, setup/health workflows, and the in-repo skill library until a skill graduates into its own standalone plugin repo.",
"version": "1.1.2",
"category": "core",
"tags": [
"agents",
"commands",
"skills",
"orchestration",
"setup",
"health"
],
"homepage": "https://github.com/jmagar/claude-homelab"
},
{
"name": "overseerr-mcp",
"source": {
"source": "github",
"repo": "jmagar/overseerr-mcp"
},
"description": "Overseerr media requests via MCP tools with HTTP fallback. Search movies and TV shows, submit requests, and monitor failed requests.",
"version": "1.0.0",
"category": "media",
"tags": [
"overseerr",
"media",
"requests",
"plex",
"mcp"
],
"homepage": "https://github.com/jmagar/overseerr-mcp"
},
{
"name": "unraid-mcp",
"source": {
"source": "github",
"repo": "jmagar/unraid-mcp"
},
"description": "Query, monitor, and manage Unraid servers via GraphQL API through MCP tools with HTTP fallback. Supports system info, Docker, VMs, array/parity, notifications, plugins, rclone, and live telemetry. Requires unraid-mcp MCP server running.",
"version": "1.2.0",
"category": "infrastructure",
"tags": [
"unraid",
"homelab",
"graphql",
"docker",
"nas",
"monitoring"
],
"homepage": "https://github.cThe plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
What ships with it
2 files beside marketplace.json 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.
- 10d ago First seen · 347 lines scan A f91cf7400cea
claude-homelab marketplace is a plugin published in the GitHub repository jmagar/claude-homelab (78 stars, last pushed 1mo 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 2026-08-30.
Other plugins, from other repositories
iot-pack
IoT domain pack: BLE communication, device telemetry ingestion, and health-metrics processing agents and skills. Opt-in; requires core.
uav-pack
UAV/drone domain pack: MAVLink integration, mission planning/creation, embedded and edge-runtime agents and skills. Opt-in; requires core.
arm-cortex-microcontrollers
ARM Cortex-M firmware development for Teensy, STM32, nRF52, and SAMD with peripheral drivers and memory safety patterns.
dgx-spark-ops
NVIDIA DGX Spark (GB10 Grace Blackwell) environment operations: aarch64/CUDA-13 stack setup, training gotcha preflights, and unified-memory/thermal management for local ML workloads.
cad
CAD, robotics, fabrication, and local review skills.
gap
Search robot skill registries, check robot/tool capabilities, and program, run, and debug verified robot task graphs (sim-first, safety-gated real) with the gap engine.