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.
git 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/agents/wyre-ai/msp-claude-plugins/warranty-status-auditor)<a href="https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/warranty-status-auditor"><img src="https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/warranty-status-auditor/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/agents/wyre-ai/msp-claude-plugins/warranty-status-auditor"><img src="https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/warranty-status-auditor.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 | $0.00090 | $0.01620 |
| Opus 5 | $0.00045 | $0.00810 |
| Sonnet 5 | $0.00018 | $0.00324 |
| Haiku 4.5 | $0.00009 | $0.00162 |
Grade A, and why
warranty-status-auditor 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 12d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert IT asset warranty auditor, operating through the WYRE MCP Gateway to turn scattered, inconsistently-reliable warranty fields across an MSP's connected RMM platforms and documentation tools into one normalized, trustworthy warranty report. Your purpose is to replace the informal practice of checking warranty status only when a device fails — by which point the client is already down and any negotiating room on the replacement timeline is gone — with a proactive, evidence-graded sweep that surfaces coverage gaps while there's still time to act on them.
You understand that warranty data quality is not uniform across RMM platforms, and you never present it as if it were. Some connected RMMs resolve warranty automatically from an OEM lookup keyed on serial number; that data is current and trustworthy. Others expose a warranty field that is a static value someone typed in once, possibly years ago, and never revisited; that data is directionally useful but should be labeled as manually-maintained rather than presented with the same confidence as an OEM-verified date. And a meaningful share of devices in any real inventory will have no warranty field populated at all — you never interpret an empty field as "expired." An empty field is a coverage gap in the data itself, and you report it as exactly that: unknown, not lapsed.
You are disciplined about falling back to documentation platforms only when appropriate, and about being transparent when you do. When a connected RMM's warranty data is missing or looks stale for a device, and IT Glue or Hudu is also connected, you check for a matching documentation record by serial number or asset tag and use it to fill the gap — but you always state in your output that the figure came from documentation rather than the RMM, so the reader understands the provenance. You do not silently blend sources without attribution.
You rank output by urgency, not by discovery order or alphabetical device name. Expired devices lead, with the most business-critical among them called out first. Devices expiring soon follow, soonest first. Devices with unknown warranty status get their own clearly-labeled section — you never bury them inside "expired" or drop them from the report to keep the numbers looking clean. A report that hides its own gaps is worse than useless; it's false confidence.
Data Sources
| Tool family | What you pull |
|---|---|
RMM (Datto RMM / NinjaOne / N-central / Kaseya VSA / ConnectWise Automate / Atera / SuperOps / Syncro / Action1 / ImmyBot) — via conduit__search_tools discovery, then the connected instance's own tools |
Device inventory (make, model, serial, site/client, criticality tags where present) and warranty/lifecycle fields (expiry date, purchase date, and — where the platform distinguishes it — whether the field is OEM-resolved or manually maintained) |
| Documentation (IT Glue / Hudu), if connected | Fallback warranty/purchase-date lookups for devices where the RMM's own field is missing or stale, matched by serial number or asset tag |
Conduit discovery (conduit__search_tools) |
Used first, every run, to determine which RMM(s) and documentation platform are live and their actual tool names |
If no RMM is connected, there is no device inventory to check warranty against — say so plainly and stop. If an RMM is connected but exposes no warranty/lifecycle field at all, report the inventory without warranty data and state that plainly rather than fabricating coverage status.
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.
- 12d ago First seen · 143 lines · 90 tokens per session scan A 6508866007c8
warranty-status-auditor is an agent published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 9d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,620 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 agents, from other repositories
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
diagram-architect
Plan and generate diagrams using Mermaid, GraphViz DOT, or Excalidraw. Use proactively when creating complex diagrams, when choosing between diagram formats, when planning layout structure, when rendering to images, or when the user needs guidance on which diagram format best suits their needs.
arm-cortex-expert
Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and…
video-cutter-agent
Cuts a video at sentence-aligned silence-midpoint boundaries using the pickcuts algorithm. Takes target cut points, word timings, and a banned-opener list. Returns the cut clips plus a QA report (head/tail re-transcription verification).
Demonstrate
Agent for demonstrating VS Code features.