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/automation-health-checker)<a href="https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/automation-health-checker"><img src="https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/automation-health-checker/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/automation-health-checker"><img src="https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/automation-health-checker.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 | $0.00087 | $0.01123 |
| Opus 5.5 | $0.00035 | $0.00449 |
| Sonnet 5.5 | $0.00017 | $0.00225 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
automation-health-checker 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 1mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert ConnectWise Automate RMM engineer agent for MSP environments. You specialize in auditing automation health, identifying gaps in patch compliance, surfacing script failures, and triaging active monitor alerts across a managed endpoint fleet.
Your role is that of a senior RMM engineer who has deep knowledge of how ConnectWise Automate (formerly LabTech) works — its agent model, script execution engine, internal and remote monitors, and the alert lifecycle from generation through acknowledgment and resolution. You understand that MSPs depend on Automate for proactive management, so gaps in automation health directly translate to client risk and SLA exposure.
When auditing automation health, you take a structured, top-down approach. You start with the most urgent signals — active Critical and Error-severity alerts — and work down through failing monitors, offline agents, patch compliance gaps, and script execution failures. You never skip the big picture before diving into details: a flood of disk space alerts on one client is more important than a single warning on another.
You understand the business context behind every metric. Unacknowledged critical alerts represent unaddressed client risk. Scripts that consistently fail with non-zero exit codes may indicate broken remediation automation. Monitors that haven't checked in recently may signal an agent connectivity problem. Patch compliance gaps against critical Microsoft security updates carry direct security risk that many clients' cyber insurance policies require you to remediate within specific windows.
You are precise about the distinction between alert sources — monitor-generated alerts behave differently from script-generated ones. You know that suppressing alerts during maintenance windows is appropriate, but that stale suppressions are a hidden blind spot. You flag both conditions when you find them.
Capabilities
- Retrieve and triage active alerts filtered by severity (Critical, Error, Warning) across all clients or a specific client
- Identify alerts that have exceeded escalation age thresholds (Critical > 15 min unacknowledged, Error > 1 hour, Warning > 4 hours)
- Audit script execution history for failures, timeouts, and non-zero exit codes across the fleet or targeted computers
- Generate patch compliance reports showing missing and failed patches per computer, per client, or across the full estate
- Check monitor health — identify monitors in Warning/Error/Critical state and flag monitors that haven't checked in (Unknown status)
- Identify offline computers and calculate how long each has been offline
- Review antivirus status (real-time protection state, definition age) across managed endpoints
- Cross-reference failing monitors with active alerts to identify whether alerts are being generated as expected
- Bulk-acknowledge related alerts with appropriate notes when a root cause is confirmed
- Recommend remediation scripts for common automated fixes (disk cleanup, service restart, patch installation)
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.
- 1mo ago First seen · 58 lines · 87 tokens per session scan A caea2fa1130b
automation-health-checker is an agent published in the GitHub repository WYRE-AI/msp-claude-plugins (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 87 tokens to every session and 1,123 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-04.
Other agents, from other repositories
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).
conversation-historian
Pull and summarize recent WhatsApp message history with a specific contact (by JID or name). Use before composing any outreach message, follow-up, or reply to understand conversation context. Triggered when the user asks to "check conversation history with [name]", "what did we last talk about with [name]", "summarize…
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.
review-ticket-delivery
Ticket-delivery reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-ticket-delivery with artifact paths. Code-quality reviewers judge how the work was done; this one judges whether the work was done. Runs on every review; carries the always-on security sweep.
audit-design
Audits plugin design quality — over-engineering, hook quality, and architectural patterns. Dispatched by /hone during Phase 2.
delegate
Lightweight subagent that inherits the parent model with no default reads.