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-raw-cligit 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-raw-cli)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/multivendor-raw-cli"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/multivendor-raw-cli/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-raw-cli"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/multivendor-raw-cli.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 | $0.00642 |
| Opus 5 | $0.00000 | $0.00321 |
| Sonnet 5 | $0.00000 | $0.00128 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
multivendor-raw-cli 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multivendor Raw CLI
Run a command on a device whose platform has no dedicated NetClaw server, and get its real output.
MCP server: multivendor-cli-mcp · Tools: run_command, check_reachability
Check routing first
Refuses raw execution on Cisco and Juniper, naming pyats / junos-mcp. Those servers are richer for
their own platforms. Use list_devices and look at owning_server before reaching for this.
Start with check_reachability
On any newly added device, run it first. It separates three failures that look identical in a generic error message and need three different fixes:
| Status | Means | Fix |
|---|---|---|
unreachable |
TCP/port problem | network, or the device is down |
auth_failed |
credentials resolved but rejected | check Vault path or env vars |
platform_mismatch |
inventory platform ≠ reality, or no driver | correct the inventory |
not_found |
device in no inventory source | add it |
Command policy
Filtering is server-side and runs before connecting — a denied command never opens a session. In
read-only mode the first verb must be show/display/get/… Ordering: chaining is rejected first,
then per-platform destructive verbs, then the allowlist.
CLI wrappers are unwrapped and their inner command judged. On FRR the only read path is
vtysh -c "show ip route", whose first token is vtysh — so the wrapper is stripped and
show ip route is what gets evaluated. This means vtysh -c "configure terminal" is correctly
denied: allowlisting vtysh itself would have turned the wrapper into a config escape.
Platform strings
Aliases are normalised, so nokia_srl, srl and nokia_srlinux all resolve to the same policy — and
to the SR Linux-specific denylist rather than only the universal baseline.
Verified live against Nokia SR Linux (native CLI) and FRR (shell-hosted).
Caveat: CLI reach is not full vendor support
netmiko also drives Fortinet, Palo Alto PAN-OS and Check Point, so this server gives CLI-level reach to them today. That is not equivalent to their dedicated API integrations:
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 · 55 lines · 0 tokens per session scan A 96b3277b93c3
multivendor-raw-cli 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 642 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-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
competition-firmware-layout
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init…
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
holohub-debug-build-run
Use when a concrete ./holohub command fails, hangs, regresses, or returns wrong output and needs reproducible diagnosis and verification.