Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add antoinekh/nokia-sr-skills/plugin install nokia-sr-skillsWrote 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/antoinekh/nokia-sr-skills/nokia-sr)<a href="https://agentmods.dev/skills/antoinekh/nokia-sr-skills/nokia-sr"><img src="https://agentmods.dev/badge/skills/antoinekh/nokia-sr-skills/nokia-sr/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/antoinekh/nokia-sr-skills/nokia-sr"><img src="https://agentmods.dev/badge/skills/antoinekh/nokia-sr-skills/nokia-sr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00104 | $0.01189 |
| Opus 5 | $0.00052 | $0.00594 |
| Sonnet 5 | $0.00021 | $0.00238 |
| Haiku 4.5 | $0.00010 | $0.00119 |
Grade A, and why
nokia-sr 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 11d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nokia SR (SR OS & SR Linux) router skill
Helps you inspect and operate Nokia's two network operating systems:
- SR OS (SROS) - the classic 7750 SR / 7250 IXR / 7950 XRS TiMOS-based OS.
- SR Linux (SRL) - the newer Linux-based, fully YANG-modelled OS.
They share concepts (YANG-driven config, NETCONF/gNMI) but differ in CLI, config syntax, models, and tooling. Work in this order, loading the one reference you need.
Step 1: Which NOS is it?
If you don't already know, identify SR OS vs SR Linux first - it decides every later step (models, CLI, syntax). See references/global/detecting-nos.md.
If detection is inconclusive or you are not sure, stop and ask the user to confirm which NOS it is rather than guessing - picking the wrong NOS sends you to the wrong models, CLI, and syntax.
Step 2: Get the release, then the YANG models
Rule for any config / "how do I X" question (e.g. "how do I configure X on SR OS?"): do not answer from memory. First ask the user for the software version (or confirm it from the device/config), then verify the exact paths, keywords, and syntax against the YANG models for that version before giving an answer. Paths are case-sensitive and version-dependent, so an answer that is not checked against the pinned models is a guess.
YANG paths are case-sensitive and version-dependent, so pin the release first.
- SR OS version -
references/sros/version-detection.md - SR Linux version -
references/srlinux/version-detection.md
Then fetch the matching models on demand (the script is NOS-aware - first arg is the NOS, second is the version):
"${CLAUDE_PLUGIN_ROOT}/skills/nokia-sr/scripts/ensure-yang.sh" sros 25.10.R4
"${CLAUDE_PLUGIN_ROOT}/skills/nokia-sr/scripts/ensure-yang.sh" srlinux 25.10.3
"${CLAUDE_PLUGIN_ROOT}/skills/nokia-sr/scripts/ensure-yang.sh" sros latest # newest release
SR OS needs an explicit revision (25.10.R4, not bare 25.10); SR Linux needs the three-part version (25.10.3); latest resolves the newest release from GitHub. It prints the local YANG release directory (downloading from Nokia's GitHub only if not already cached). How it works and how to search the models: references/global/yang-models.md.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/global/detecting-nos.md 3.7 KB
- references/global/language-server.md 1.8 KB
- references/global/yang-models.md 4.4 KB
- references/global/yang-tooling.md 6.3 KB
- references/srlinux/config-format.md 2.5 KB
- references/srlinux/operate.md 3.8 KB
- references/srlinux/version-detection.md 1.8 KB
- references/sros/config-format.md 1.6 KB
- references/sros/operate.md 5.8 KB
- references/sros/version-detection.md 1.6 KB
- scripts/ensure-yang.sh 8.6 KB runs code
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.
- 11d ago First seen · 75 lines · 104 tokens per session scan A bbc92d106da0
nokia-sr is a skill published in the GitHub repository antoinekh/nokia-sr-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 104 tokens to every session and 1,189 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
cardputer-buddy
Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…
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…
google-cloud-filestore-autoscale
Inspects Google Cloud Filestore capacity and utilization, evaluates storage scaling rules, and performs capacity autoscaling (scale UP for low free space or scale DOWN for cost optimization). Use when monitoring Filestore instance headroom, resizing instance shares, configuring automated growth/shrink thresholds…
developer-device-platform-basics
Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.
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…