alert-triage

alert-triage is a command for Claude Code from WYRE-AI/msp-claude-plugins. It costs 19 tokens per session (680 once invoked), scanned A, original, Apache-2.0.

A command for reviewing open alerts in Auvik, a network-monitoring service used by managed service providers. It groups alerts by severity and type, then recommends which need action and which may be known noise.

In plain words
What is it for?
Use it to inspect open alerts, retrieve details for important ones, investigate related devices and tenants, and recommend dismissals or follow-up.
Why use it?
It turns a large alert queue into a ranked list, so network operators can focus on urgent problems instead of reviewing every alert equally.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the auvik plugin — 1 skill, 5 commands, 3 agents shipped together

Good fit Use it to inspect open alerts, retrieve details for important ones, investigate related devices and tenants, and recommend dismissals or follow-up.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/wyre-ai/msp-claude-plugins/alert-triage
Install

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.

Clone the repo
git clone --depth 1 https://github.com/WYRE-AI/msp-claude-plugins

Made for: Claude Code.

Or install auvik, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 3 agents.

Wrote 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.

agentmods badge for alert-triage

README.md
[![agentmods](https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/alert-triage/github.svg)](https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/alert-triage)
Your own site
<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/alert-triage"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/alert-triage/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.

agentmods 80×15 button for alert-triage

Your own site · 80×15
<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/alert-triage"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/alert-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 680 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00680
Opus 5 $0.00010 $0.00340
Sonnet 5 $0.00004 $0.00136
Haiku 4.5 $0.00002 $0.00068

Measured 9d ago against content hash 94a555cebf6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

alert-triage 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 9d 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.

msp-claude-plugins/auvik/auvik/commands/alert-triage.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auvik Alert Triage

Run the daily Auvik alert queue: pull what's open, rank it, recommend dismissals for confirmed noise, and surface the alerts that need human action. Designed for MSP NOC analysts working a multi-tenant queue.

Prerequisites

  • Tools: auvik_alerts_list, auvik_alerts_get, auvik_alerts_dismiss, auvik_devices_get, auvik_tenants_list

Steps

  1. List open alerts

    Call auvik_alerts_list with status=open (and tenant_id if scoped). Filter to severity >= the requested minimum (default warning). Paginate to completion.

  2. Bucket by severity

    Order: emergency, critical, warning, info. Within each bucket, group by alertName and entityType - duplicate alerts on the same device usually collapse to a single decision.

  3. Pull full details for the top of the queue

    For each of the top 20 alerts (or all emergency/critical alerts, whichever is larger), call auvik_alerts_get to retrieve the full record - description, detected time, dispatch reason, and the referenced entity ID.

  4. Resolve the entity for context

    For alerts referencing a device, call auvik_devices_get on the entity to retrieve deviceName, deviceType, and manageStatus. Unmanaged devices with critical alerts are usually false-positives from Auvik discovery, not real incidents.

  5. Classify each alert

    Into one of:

    • Action required - confirmed real condition on a managed device (down switch, saturated interface, failed config backup, etc.)
    • Investigate - the entity context is ambiguous - device recently changed, alert is new pattern, signal quality unclear
    • Dismiss (noise) - known false-positive pattern: link flap on user-port access switches, scheduled reboot windows, transient SNMP timeouts, alerts on manageStatus = unmanaged devices
  6. Recommend dismissals - do not dismiss automatically

    Surface the dismiss candidates as a list with one-line justifications and the auvik_alerts_dismiss call you would make. Wait for the user to confirm before dismissing. Dismissal acknowledges and hides - it does not fix - so a real condition that's still active will re-alert anyway.

Read the full file on GitHub · 65 lines

Changes

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.

  1. 9d ago First seen · 65 lines · 19 tokens per session scan A 94a555cebf6a

Subscribe to this mod's changes

alert-triage is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 6d ago), licensed Apache-2.0. It adds 19 tokens to every session and 680 once invoked, about $0.0001 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.