mdm-device-management

mdm-device-management is a skill for Claude Code, Codex from BagelHole/DevOps-Security-Agent-Skills. It costs 48 tokens per session (6,074 once invoked), scanned A, original, MIT.

A guide to managing company laptops, phones, and tablets with mobile device management (MDM) tools. It covers enrolling macOS, Windows, iOS, and Android devices, applying security rules, and deploying software.

In plain words
What is it for?
Use it to plan device enrollment, enforce encryption and other policies, deploy applications, separate company data from personal data, and remotely wipe devices.
Why use it?
It replaces manual device setup and scattered security checks with a repeatable way to manage a growing or remote team. It also helps with offboarding, compliance evidence, and lost-device response.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan device enrollment, enforce encryption and other policies, deploy applications, separate company data from personal data, and remotely wipe devices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bagelhole/devops-security-agent-skills/mdm-device-management
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.

Any agent
npx skills add BagelHole/DevOps-Security-Agent-Skills --skill mdm-device-management
Clone the repo
git clone --depth 1 https://github.com/BagelHole/DevOps-Security-Agent-Skills

Made for: Claude Code, Codex.

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 mdm-device-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/mdm-device-management/github.svg)](https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/mdm-device-management)
Your own site
<a href="https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/mdm-device-management"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/mdm-device-management/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 mdm-device-management

Your own site · 80×15
<a href="https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/mdm-device-management"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/mdm-device-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,074 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 26 findings, up to medium

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 →

  • medium Rogue Agent · line 258
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 260
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 296
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 664
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 258
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Privilege Escalation · line 303
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 304
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 305
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 409
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 410
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 411
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 507
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 508
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 509
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 510
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Rogue Agent · line 409
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 410
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 411
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 507
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 508
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00048 $0.06074
Opus 5 $0.00024 $0.03037
Sonnet 5 $0.00010 $0.01215
Haiku 4.5 $0.00005 $0.00607

Measured 5d ago against content hash a3883c47b1ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mdm-device-management scanned grade A with 2 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 5d 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 rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo /usr/libexec/ApplicationFirewall/socketfilterfw --setglobalstate on

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

brew "wget"
infrastructure/it/mdm-device-management/SKILL.md · 772 lines

How it starts

The opening of the file, as written. The whole thing — 772 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mobile Device Management (MDM) for Startups & Small Teams

A practical guide to enrolling, securing, and managing company devices across macOS, Windows, iOS, and Android — from zero-touch onboarding to remote wipe.


1. When to Use MDM

MDM becomes essential when any of the following apply:

  • Team size crosses ~10 people — manual laptop setup no longer scales.
  • Compliance requirements — SOC 2, HIPAA, ISO 27001, or customer security questionnaires demand proof that endpoints are encrypted and patched.
  • Remote / hybrid workforce — you cannot walk over to someone's desk to fix a configuration or verify disk encryption.
  • Contractor or BYOD devices — you need a way to separate corporate data from personal data and revoke access on offboarding.
  • Insurance or investor due diligence — cyber-insurance carriers and VCs increasingly ask for evidence of endpoint management.

If you are still under 10 people and everyone is in-office, a simple checklist plus a configuration management tool (Ansible) may suffice — but plan for MDM early so enrollment is painless when you scale.


2. MDM Platform Comparison

Platform Best For Pricing Model Open Source Key Strength
Jamf Pro macOS / iOS fleets Per-device/yr No Deepest Apple integration, DEP/ADE native
Microsoft Intune Windows + M365 shops Bundled w/ M365 E3/E5 No Seamless Azure AD + Autopilot
Kandji macOS-first startups Per-device/yr No Pre-built compliance templates, fast setup
Mosyle Education & SMB Apple Per-device/yr No Apple School/Business Manager integration
Fleet Cross-platform, eng-led Free (OSS) / paid cloud Yes osquery-powered, GitOps-friendly, API-first
SimpleMDM Small Apple-only teams Per-device/mo No Simple UI, quick onboarding

Decision heuristic

if (team < 50 AND engineering-led AND multi-OS):
    consider Fleet (open-source, osquery-native)
elif (team is macOS-dominant AND compliance-heavy):
    consider Kandji or Jamf
elif (team is Windows-dominant AND already on M365):
    consider Intune (likely already licensed)
else:
    evaluate Fleet or Kandji based on OS mix

Read the full file on GitHub · 772 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. 5d ago First seen · 772 lines · 48 tokens per session scan A a3883c47b1ea

Subscribe to this mod's changes

mdm-device-management is a skill published in the GitHub repository BagelHole/DevOps-Security-Agent-Skills (1,067 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 6,074 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

implementing-aws-config-rules-for-compliance

Implementing AWS Config rules for continuous compliance monitoring of AWS resources, deploying managed and custom rules aligned to CIS and PCI DSS frameworks, configuring automatic remediation with SSM Automation, and aggregating compliance data across accounts.

adriannoes/awesome-agentic-ai · 53 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

holoscan-setup

Guides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.

NVIDIA/skills · 36 tokens

jetson-video-recipe

Use when turning a Jetson encoder use case into one validated surface-neutral recipe with native and PyNvVideoCodec projections for codec, preset, rate control, bitrate, latency, format, and profile.

NVIDIA/skills · 46 tokens

doca-flow-dpa-provider

Use this skill when the user is doing hands-on DOCA Flow DPA Provider work — exporting a doca-flow pipe or external resource (index-selector/memory) into BlueField DPA address space so a DPACC-built kernel can read counters, mutate hash-pipe entries, and update/read memory or index-selector resources inline with Flow.…

NVIDIA/skills · 244 tokens

doca-flow-tune

Use this skill when the user is tuning a live or captured doca-flow pipeline with docaflowtune — snapshotting pipe / counter / KPI state, picking a tuning axis (rule placement, resource hints / table sizing, HW-offload mode) and a matching measurement (rule-install rate, lookup latency, hardware-counter delta)…

NVIDIA/skills · 230 tokens