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 automateyournetwork/netclaw --skill multivendor-device-querygit clone --depth 1 https://github.com/automateyournetwork/netclawWrote 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/automateyournetwork/netclaw/multivendor-device-query)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/multivendor-device-query"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/multivendor-device-query/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/automateyournetwork/netclaw/multivendor-device-query"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/multivendor-device-query.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 | $0.00000 | $0.01156 |
| Opus 5 | $0.00000 | $0.00578 |
| Sonnet 5 | $0.00000 | $0.00231 |
| Haiku 4.5 | $0.00000 | $0.00116 |
Grade A, and why
multivendor-device-query 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multivendor Device Query
Query network devices on platforms NetClaw's Cisco- and Juniper-specific servers cannot reach — MikroTik RouterOS, VyOS, SONiC, Nokia SR Linux, Extreme, Huawei, Dell, Ubiquiti EdgeOS, and roughly eighty more.
MCP server: multivendor-cli-mcp (results identify themselves as multivendor-cli)
Decide which server to use FIRST
This skill is wrong for most Cisco and Juniper work. Check here before using it:
| Your device | Use |
|---|---|
| Cisco IOS / IOS-XE / NX-OS / IOS-XR | pyats-* skills — ~2000 Genie parsers, state diffing |
| Juniper Junos | junos-network skill — PyEZ/NETCONF |
| Streaming telemetry, any vendor | gnmi-telemetry skill |
| No direct reachability | radkit-remote-access skill |
| Anything else | this skill |
| "Compare X across Cisco and Arista and Nokia" | this skill (read-only) |
That last row is the exception worth understanding. NAPALM returns one shape across vendors, so this is the only server that can answer a genuinely cross-vendor question. It answers those read-only, even on Cisco and Juniper.
Configuration writes on Cisco and Juniper are refused, naming the correct server. That is deliberate, not a limitation: one write path per platform is what makes "verify the change" mean something. Reads may overlap between servers; writes may not.
Tools
| Tool | Purpose |
|---|---|
server_info |
Server identity, read-only vs write mode, which platforms have destructive-syntax modelling |
check_command_policy |
Would this command be permitted? Answers without touching a device |
list_devices |
Inventory, with the source that answered and why |
check_device_readiness |
Is this device resolvable, authenticable, and mine to act on? Contacts nothing |
Workflow
list_devices— confirm the device is in inventory and seeowning_server. If that ispyatsorjunos-mcp, stop and use that server for single-device work.check_device_readiness— verify credentials resolve and check what this server may do. Run this before anything else on a new device: it separates not in inventory from credentials missing from owned by another server, which need three different fixes.check_command_policy— before an unusual command, confirm it passes policy.
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 · 97 lines · 0 tokens per session scan A 1cf7fd509a5a
multivendor-device-query is a skill published in the GitHub repository automateyournetwork/netclaw (657 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,156 tokens. 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 2026-09-03.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.