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 agentsgit 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/agents)<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/agents"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/agents.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 185 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00035 | $0.02591 |
| Opus 5 | $0.00017 | $0.01295 |
| Sonnet 5 | $0.00007 | $0.00518 |
| Haiku 4.5 | $0.00003 | $0.00259 |
Grade A, and why
Atera Agents 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 8d 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atera Agent Management
Overview
Atera agents are lightweight software installed on managed endpoints that provide remote monitoring and management capabilities. Agents report system information, health metrics, and enable remote execution of scripts and commands.
Anti-triggers
- Atera's own "devices" — an Atera device is an agentless HTTP,
SNMP, or TCP monitor with no agent behind it; use
atera-devices. Atera is the odd one out: inncentral-devices,ninjaone-devices, anddatto-rmm-devices"device" means the managed endpoint, which here is an agent. - Claude subagents — "agent" here is an Atera endpoint sensor, never
an AI subagent definition under
agents/*.md. Inhalopsa-agentsit is a human technician, and inliongard-overviewit is one inspection runner per customer site. - Running a script on an endpoint managed by another RMM — "run
PowerShell on this machine" matches every RMM in this marketplace
equally, and none of them reach Atera's agents. Confirm which RMM the
endpoint is enrolled in, then use
syncro-assets,superops-runbooks,immybot-script-execution,ncentral-monitoring-tasks,connectwise-automate-scripts, ordatto-rmm-jobs. - The alert an agent raised — agent records carry health and
inventory, not monitoring output; use
atera-alerts.
Agent Information Fields
Core Fields
| Field | Type | Description |
|---|---|---|
AgentID |
int | Unique agent identifier |
AgentName |
string | Agent display name |
MachineID |
int | Machine reference ID |
CustomerID |
int | Associated customer ID |
CustomerName |
string | Customer display name |
Online |
boolean | Current online status |
LastSeenDate |
datetime | Last communication timestamp |
System Information
| Field | Type | Description |
|---|---|---|
MachineName |
string | Computer hostname |
DomainName |
string | AD domain (if joined) |
OS |
string | Operating system name |
OSVersion |
string | OS version/build |
OSType |
string | Windows, Mac, Linux |
OSSerialNumber |
string | OS serial number |
Processor |
string | CPU model |
Memory |
long | Total RAM in bytes |
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.
- 8d ago First seen · 343 lines · 35 tokens per session scan A aa281f23e801
Atera Agents is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 5d ago), licensed Apache-2.0. It adds 35 tokens to every session and 2,591 once invoked, about $0.0002 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
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
content-card-news
A planning tool for four-card social media carousels on Instagram, Threads, and Kakao Channel, combining card copy, design guidance, image prompts, captions, and hashtags.
design-copywriting
A copywriting workflow for marketing and product pages that uses a brand voice and returns structured text for page sections.
cs-voc-triage
A customer-feedback analysis tool that combines reviews and support contacts from multiple channels. VOC means “voice of the customer”: the comments, questions, complaints, and praise customers leave about a business.
data-realestate
A lookup tool for reported South Korean property transactions using Ministry of Land data. It covers sales and rental deals for apartments, officetels, multi-family homes, houses, and commercial or office properties.