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 meraki-switch-opsgit 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/meraki-switch-ops)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/meraki-switch-ops"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/meraki-switch-ops/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/meraki-switch-ops"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/meraki-switch-ops.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 | $0.00062 | $0.01406 |
| Opus 5 | $0.00031 | $0.00703 |
| Sonnet 5 | $0.00012 | $0.00281 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
meraki-switch-ops 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meraki Switch Operations (read-only)
MCP Server
- Server: Cisco's official Meraki MCP — developer.cisco.com
- Endpoint:
https://mcp.meraki.com/mcp(remote HTTP, no local install) - Self-host fallback: CiscoDevNet/cisco-meraki-mcp-official (Apache-2.0)
- Requires:
MERAKI_DASHBOARD_API_KEY— use a read-only dashboard key - Tools: exactly two —
semantic_search(discover) andexecute_api(invoke)
Read-only, structurally
All 431 mutating Meraki operations (174 POST, 186 PUT, 71 DELETE) are absent from the
capability catalogue. Only non-deprecated GETs are built in, so updateNetwork,
rebootDevice, blinkDeviceLeds and friends return Capability not found.
Do not attempt writes and do not offer them. There is no ServiceNow CR path here because there is nothing to gate — a change must be made in the Meraki dashboard directly.
How to call it
Two capability IDs may be called directly; everything else must be discovered:
execute_api→getOrganizations— find accessible org IDsexecute_api→getOrganizationNetworks— find network IDs in the chosen orgsemantic_search→ describe the intent in words → returns rankedcapability_idsexecute_api→ the chosencapability_id+ its required parameters
Discover, do not guess. An earlier version of this skill hardcoded 80 method names and
54 of them did not exist in the Meraki API at all — they failed regardless of server.
semantic_search is the guard against that: it can only return IDs that exist.
Reading results honestly
- One page only.
execute_apireturns a single page. Request a bounded page size when supported, and never present a page as the complete dataset. - Empty is not absent.
n=0means this network reported none, never none exist. Live proof from a real sandbox org:getOrganizationDevicesreturns 0 devices while the same org has a fully configured network with 15 SSIDs. - Three distinct errors, three different fixes:
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 · 111 lines · 62 tokens per session scan A db865dcce962
meraki-switch-ops is a skill published in the GitHub repository automateyournetwork/netclaw (655 stars, last pushed 4d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,406 once invoked, about $0.0003 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 2026-09-03.
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.
preset-health
Nested swiss-knife reference for saved-preset health checks. Read this when the human asks whether saved presets still work, which preset is expired or misconfigured, why system(action="presets") shows a bad connectivity status, or for a safe procedure to enumerate saved presets, classify each failure (expired key…