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 nso-device-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/nso-device-ops)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/nso-device-ops"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/nso-device-ops.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01545 |
| Opus 5 | $0.00028 | $0.00772 |
| Sonnet 5 | $0.00011 | $0.00309 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
nso-device-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 4d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSO Device Operations
MCP Server
- Command:
cisco-nso-mcp-server(pip-installed, stdio transport) - Requires:
NSO_ADDRESS,NSO_USERNAME,NSO_PASSWORDenvironment variables - Optional:
NSO_SCHEME(default: http),NSO_PORT(default: 8080),NSO_VERIFY,NSO_TIMEOUT - API: RESTCONF (RFC 8040)
Available Tools
| Tool | Parameters | What It Does |
|---|---|---|
get_device_config |
device_name |
Get the full configuration for a device from NSO's CDB |
get_device_state |
device_name |
Get operational state data for a device (interfaces, counters, status) |
check_device_sync |
device_name |
Check if NSO's copy of the device config is in sync with the actual device |
sync_from_device |
device_name |
Pull the current config from the device into NSO's CDB (sync-from) |
get_device_platform |
device_name |
Get platform info: model, OS version, serial number, hardware details |
get_device_ned_ids |
none | List all Network Element Driver (NED) IDs — shows what device types NSO can manage |
get_device_groups |
none | List all device groups defined in NSO |
MCP Resource
| Resource URI | What It Returns |
|---|---|
https://resources.cisco-nso-mcp.io/environment |
NSO environment summary: device count, OS distribution, unique models, device series, group membership |
Workflow: Device Configuration Audit
When a user asks "show me R1's config from NSO" or "what does NSO have for the core routers":
- Get device groups:
get_device_groupsto see how devices are organized - Get config:
get_device_configfor each target device - Present: Format the configuration in a readable way
- Cross-reference: Compare with pyATS live config if discrepancies suspected
Workflow: Sync Check and Remediation
When a user asks "are my devices in sync?" or "is NSO up to date?":
- Check sync:
check_device_syncfor the target device(s) - If out of sync: Report which devices are out of sync and why
- Remediate: Use
sync_from_deviceto pull current config from the device into NSO - Verify: Run
check_device_syncagain to confirm sync is restored - Record in GAIT: Log the sync operation for audit trail
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.
- 4d ago First seen · 123 lines · 57 tokens per session scan A 3ca8fd9176fa
nso-device-ops is a skill published in the GitHub repository automateyournetwork/netclaw (650 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 1,545 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
mcp-config-sync
Provider-neutral entry point for discovering, planning and synchronizing MCP configuration between user-selected providers and app classes. The user selects truth, targets and scope; no provider is an implicit hub.
ha-integration-solution
Plans and orchestrates a complete Home Assistant Python custom-integration backend from a result-oriented device/cloud/API requirement, driven by a chosen quality-scale target tier (Bronze–Platinum), so the user never picks individual skills. Decomposes the requirement into a minimal dependency-ordered plan for the…
ha-esphome-solution
Plans and orchestrates a complete ESPHome device or fleet result from a requirement, so the user never has to pick which ESPHome skill produces what. Decomposes it into the minimal dependency-ordered set of artifacts across the ha-esphome- family — repository layout and packages, the device file, sensors and buses…
ha-automation-solution
Plans and orchestrates a complete Home Assistant YAML solution from a result-oriented requirement, so the user never has to pick which authoring skill to use. Decomposes the requirement into the minimal combination of artifacts across the ha-automation skill family, presents a dependency-ordered artifact plan for…
mpm-config
Manage Claude MPM configuration.
ryu-local-model
Search, download, and serve a local GGUF model on a Ryu node via Core's models and engines REST surface. Covers catalog search and device-fit, installing a specific quantization, activating a model, and listing engines (the engine is derived from the model format). Use when a user wants to get a local model running on…