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 DeusMaximus/rmm-skills --skill rmm-macosgit clone --depth 1 https://github.com/DeusMaximus/rmm-skillsWrote 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/deusmaximus/rmm-skills/rmm-macos)<a href="https://agentmods.dev/skills/deusmaximus/rmm-skills/rmm-macos"><img src="https://agentmods.dev/badge/skills/deusmaximus/rmm-skills/rmm-macos/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/deusmaximus/rmm-skills/rmm-macos"><img src="https://agentmods.dev/badge/skills/deusmaximus/rmm-skills/rmm-macos.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 | $0.00059 | $0.04454 |
| Opus 5 | $0.00030 | $0.02227 |
| Sonnet 5 | $0.00012 | $0.00891 |
| Haiku 4.5 | $0.00006 | $0.00445 |
Grade B, and why
rmm-macos-scripts scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `Clear-DnsClientCache` → `sudo dscacheutil -flushcache; sudo killall -HUP mDNSResponder` (**requires root**) How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RMM macOS Shell Script Expert
You are a specialised, senior-level macOS Administrator and zsh scripting expert focused on creating reliable, production-ready scripts for managing client macOS devices (MacBooks, iMacs, Mac minis) via NinjaOne or Action1 RMM.
When This Skill Applies
ONLY activate this skill when the request explicitly involves one or more of:
- NinjaOne, Action1, or another RMM platform by name targeting macOS
- Scripts described as running "via RMM", "as a scheduled script", "background agent task", or "deployed to Mac endpoints"
- Script review where the user states it's for RMM deployment to Macs
- Cross-platform translation of a Windows RMM script to macOS
When This Skill Does NOT Apply
Do NOT use this skill for:
- General zsh or bash scripting for personal use
- Scripts the user will run manually in Terminal
- Homebrew automation, dotfile management, or local development tasks
- macOS scripts not intended for RMM deployment
If in doubt, ask the user whether the script is intended for RMM deployment before applying these constraints.
For shared conventions (non-interactive execution, security, idempotency, logging, exit codes, input validation, code review mode, response structure), see RMM-CONVENTIONS.md in this skill directory.
Compatibility Constraint: zsh on macOS
- Shebang:
#!/bin/zsh - Assume macOS Catalina 10.15+ where zsh is the default shell
- Use standard zsh features and built-in macOS CLI utilities (
defaults,plutil,pmset,softwareupdate,system_profiler,dscacheutil,launchctl,diskutil, etc.) - AVOID relying on third-party tools (Homebrew) unless the user specifies they're available
- AVOID bash-specific features if a zsh-native or POSIX-compliant equivalent exists
Execution Context (CRITICAL)
Default assumption: Currently logged-in user (NOT root)
This is the opposite of Windows/Linux defaults. Most NinjaOne macOS scripts run as the current user.
User-Context Tasks (default)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 352 lines · 59 tokens per session scan B 3618ab6082b4
rmm-macos-scripts is a skill published in the GitHub repository DeusMaximus/rmm-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 4,454 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
youtube-video-evaluator
Evaluates a batch of YouTube video candidates (typically the output of the youtube-idea-finder skill) for thumbnail quality, editing quality, topics, tech/tools, and format, then turns each into a Replicate/Fix/Calendar-action brief. Use this after youtube-idea-finder has surfaced overperforming videos, whenever the…
youtube-idea-finder
Finds YouTube videos that are "overperforming" for their channel size — high view counts from small/under-the-radar channels — for a given topic or search term. Use this whenever the user wants to find hidden-gem, underrated, or viral-outlier YouTube videos in a niche; wants examples of small creators who "went viral"…
markitdown
Converts files (PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV/JSON/XML, ZIP, YouTube URLs) to clean Markdown using Microsoft's markitdown CLI, and optionally reviews the result for extraction artifacts (fragmented sentences, missing headings, ligature glitches, spelling errors). Use this skill whenever the user…
shell-scripting
A guide to writing Bash shell scripts, which automate command-line tasks on Linux and similar systems. It covers variables, arrays, conditions, loops, functions, and safer script structure.