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 WYRE-AI/msp-claude-plugins --skill warranty-trackinggit clone --depth 1 https://github.com/WYRE-AI/msp-claude-pluginsWrote 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/wyre-ai/msp-claude-plugins/warranty-tracking)<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/warranty-tracking"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/warranty-tracking/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/wyre-ai/msp-claude-plugins/warranty-tracking"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/warranty-tracking.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 | $0.00109 | $0.01877 |
| Opus 5 | $0.00055 | $0.00938 |
| Sonnet 5 | $0.00022 | $0.00375 |
| Haiku 4.5 | $0.00011 | $0.00188 |
Grade A, and why
Warranty Tracking 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warranty Tracking
Overview
Warranty status is the single-most load-bearing field in hardware asset management and the least consistently reliable one across RMM platforms. Some RMMs resolve warranty directly from the OEM (serial-number lookup against Dell/HP/Lenovo warranty APIs) and refresh it automatically. Others expose a warranty field that is purely a manually-entered value someone typed in once during onboarding and never touched again. Treating both as equally trustworthy produces confident-sounding reports built on stale data. This skill covers how to pull warranty data across whatever RMM(s) an org has connected, how to weigh its reliability, and how to fall back to documentation platforms (IT Glue, Hudu) when RMM data is missing or looks stale.
This is endpoint/hardware warranty specifically — physical device coverage
status. It is not network/cloud infrastructure health (see cloudops-pack)
and it is not a service-desk ticket about a broken device (see ops-pack);
a device can be fully healthy and in active use while still being three
weeks from warranty expiration, which is exactly the case this skill exists
to catch before it becomes a support problem.
Anti-triggers
- One platform's own warranty or lifecycle field — "what does Auvik
return for warranty," "read N-central's lifecycle record" is that
connector's API surface; use
auvik-devicesorncentral-devices. - ScalePad Lifecycle Manager's warranty product — LM holds its own
hardware lifecycle records and warranty pricing; use
scalepad-lifecycle-managerfor anything scoped to that tool. - Looking up one asset's record — use
itglue-configurationsorhudu-assets; this skill sweeps warranty state across a fleet.
Discovering available tools first
Never assume which RMM or documentation platform is connected:
- Call
conduit__search_toolswith a query like"device warranty","list devices", or"device lifecycle"to discover which RMM connector(s) are actually live for this org and their real tool names (e.g.datto-rmm__datto_list_devices,ninjaone__list_devices,ncentral__ncentral_get_device_lifecycle,kaseya-vsa__list_devices). - More than one RMM can be connected (a portfolio spanning multiple clients on different platforms, or a client mid-migration between RMMs). Cover all connected platforms; don't stop at the first.
- Separately discover documentation platforms (
itglue__search_configurations,hudu__*equivalents) as an optional fallback source, not a primary one — RMM inventory is the source of truth for "what devices exist"; documentation is the source of truth only when the RMM's own warranty field is empty or stale. - Only call concrete tools that discovery actually returned.
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 · 171 lines · 109 tokens per session scan A 27975b57f5a9
Warranty Tracking is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 8d ago), licensed Apache-2.0. It adds 109 tokens to every session and 1,877 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 2026-08-30.
Other skills, from other repositories
scan-my-machine
Scans the user's actual hardware and tells them exactly which local AI models they can run, by name, with expected speed. Use when the user asks "what models can my computer run", "can I run a local LLM", "how much VRAM do I have", "which model should I download", "is my Mac good enough for local AI", "scan my…
dell-idrac-bmc-ops
Bring a Dell PowerEdge BMC (iDRAC) onto the network headlessly, standardize its baseline settings, stage its firmware, and drive an unattended Proxmox/Linux install through it — including generation-specific Redfish/racadm gotchas, the identity-before-power-action rule, and the phantom-drive failure mode caused by…
pxe-netboot
Reliable remote OS install over PXE when a server's virtual-media/remote-KVM path is broken or unreliable — proxyDHCP + TFTP via dnsmasq, kernel/initrd served over plain HTTP, and a custom-built iPXE binary with an embedded autoexec script (because a distro-packaged one won't auto-chainload). Use when a legacy BMC's…
ha-addon-scaffold
Scaffold a production-ready Home Assistant add-on: config.yaml with UI options schema, multi-arch Dockerfile + build.yaml, s6-overlay services, Ingress web UI wiring, GHCR CI, DOCS/CHANGELOG, and an add-on repository.yaml. Use when creating a new Home Assistant add-on, adding an add-on to a repository, or setting up…
automatic-cybernetic-flow-design
Use when the user wants a cybernetic flow design document for an interactive system. Specifies sensors, actuators, feedback paths, delays, and oscillation risk, and writes the design to a named local file. Not for implementing or deploying the system.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…