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.
npx skills add WYRE-AI/msp-claude-plugins --skill network-health-sweepgit clone --depth 1 https://github.com/WYRE-AI/msp-claude-pluginsWrote 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/skills/wyre-ai/msp-claude-plugins/network-health-sweep)<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/network-health-sweep"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/network-health-sweep/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/skills/wyre-ai/msp-claude-plugins/network-health-sweep"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/network-health-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.01954 |
| Opus 5 | $0.00042 | $0.00977 |
| Sonnet 5 | $0.00017 | $0.00391 |
| Haiku 4.5 | $0.00008 | $0.00195 |
Grade A, and why
Network Health Sweep 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 7d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Network Health Sweep
Overview
"Is the network healthy" is a portfolio question, not a single-device question. This skill runs a normalized health check across every connected network-monitoring tool and rolls the result up into one ranked view — the same sweep a senior network engineer would run by hand across each vendor's console, made explicit, repeatable, and vendor-agnostic.
This is infrastructure-substrate health: is the network itself up, are
interfaces clean, has the topology changed unexpectedly. It is not ticket
triage (see ops-pack) and it is not application-layer reliability (see
devops-pack, if connected) — this skill only answers whether the wires,
switches, firewalls, and access points a client depends on are functioning.
Anti-triggers
- One vendor's device, alert, or interface data — use
auvik-devices,auvik-alerts,meraki-devices, ordomotz-deviceswhen the question is what that platform returns, rather than how to rank findings across all of them. - Hands-on diagnostics against a specific device — ping, cable test,
throughput, and reboots are live tools, not a sweep; use
meraki-troubleshooting. - Collector health as its own subject — use
domotz-agents; this skill checks agent status only to decide whether "down" or "unknown" applies to the devices behind it.
Discovering available tools first
Because this pack is cross-vendor, never assume which network-monitoring tool is connected, or what its tools are literally named:
- Call
conduit__search_toolswith a query like"list devices","network health", or"device status"to discover which network-monitoring connector(s) are actually live for this org, and the exact tool names each exposes (they follow<vendor-slug>__<tool_name>, e.g.auvik__devices_list,meraki__list_networks,domotz__list_agents). - More than one network-monitoring tool can be connected at once (e.g. Auvik for one site, Meraki for another) — discovery may return multiple vendor families. Sweep all of them; do not stop at the first match.
- Only after discovery, call the concrete tools that came back. Never speculatively call a tool name that discovery didn't return — an unrecognized tool call is a worse failure mode than reporting "no network monitoring connector found."
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.
- 7d ago First seen · 173 lines · 84 tokens per session scan A 570702c4b260
Network Health Sweep is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 9d ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,954 once invoked, about $0.0004 per session on Opus 5. 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 skills, from other repositories
scan-my-machine
Scans the user's actual hardware and tells them exactly which local AI models they can run, by name, with expected speed. Use when the user asks "what models can my computer run", "can I run a local LLM", "how much VRAM do I have", "which model should I download", "is my Mac good enough for local AI", "scan my…
dell-idrac-bmc-ops
Bring a Dell PowerEdge BMC (iDRAC) onto the network headlessly, standardize its baseline settings, stage its firmware, and drive an unattended Proxmox/Linux install through it — including generation-specific Redfish/racadm gotchas, the identity-before-power-action rule, and the phantom-drive failure mode caused by…
pxe-netboot
Reliable remote OS install over PXE when a server's virtual-media/remote-KVM path is broken or unreliable — proxyDHCP + TFTP via dnsmasq, kernel/initrd served over plain HTTP, and a custom-built iPXE binary with an embedded autoexec script (because a distro-packaged one won't auto-chainload). Use when a legacy BMC's…
ha-addon-scaffold
Scaffold a production-ready Home Assistant add-on: config.yaml with UI options schema, multi-arch Dockerfile + build.yaml, s6-overlay services, Ingress web UI wiring, GHCR CI, DOCS/CHANGELOG, and an add-on repository.yaml. Use when creating a new Home Assistant add-on, adding an add-on to a repository, or setting up…
automatic-cybernetic-flow-design
Use when the user wants a cybernetic flow design document for an interactive system. Specifies sensors, actuators, feedback paths, delays, and oscillation risk, and writes the design to a named local file. Not for implementing or deploying the system.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…