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 BagelHole/DevOps-Security-Agent-Skills --skill arm-templatesgit clone --depth 1 https://github.com/BagelHole/DevOps-Security-Agent-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/bagelhole/devops-security-agent-skills/arm-templates)<a href="https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/arm-templates"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/arm-templates/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/bagelhole/devops-security-agent-skills/arm-templates"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/arm-templates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 Supply Chain · line 26 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Tool Misuse · line 26 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Privilege Escalation · line 183 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Privilege Escalation · line 26 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.
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 | $0.00030 | $0.02959 |
| Opus 5 | $0.00015 | $0.01479 |
| Sonnet 5 | $0.00006 | $0.00592 |
| Haiku 4.5 | $0.00003 | $0.00296 |
Grade A, and why
arm-templates 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 7d 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 — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARM Templates & Bicep
Deploy Azure infrastructure with ARM templates and Bicep. Bicep is the recommended domain-specific language that compiles to ARM JSON, offering cleaner syntax, modules, and first-class tooling support.
When to Use
- You need Azure-native Infrastructure as Code without third-party tooling.
- Your organization standardizes on Azure and wants tight portal integration.
- You need What-If analysis before deploying changes.
- You are migrating existing ARM JSON templates to Bicep for maintainability.
- You need deployment scopes at resource group, subscription, management group, or tenant level.
Prerequisites
# Install Azure CLI
curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash
# Install Bicep CLI (bundled with Azure CLI 2.20+)
az bicep install
az bicep upgrade
# Verify installation
az bicep version
# Login and set subscription
az login
az account set --subscription "my-subscription-id"
Bicep Fundamentals
Resource Group Deployment with Virtual Network
// main.bicep
@description('Azure region for all resources')
param location string = resourceGroup().location
@description('Environment name used for resource naming')
@allowed(['dev', 'staging', 'prod'])
param environment string = 'dev'
@description('Base name for all resources')
param baseName string
var vnetName = '${baseName}-${environment}-vnet'
var nsgName = '${baseName}-${environment}-nsg'
resource nsg 'Microsoft.Network/networkSecurityGroups@2023-05-01' = {
name: nsgName
location: location
properties: {
securityRules: [
{
name: 'AllowHTTPS'
properties: {
priority: 100
direction: 'Inbound'
access: 'Allow'
protocol: 'Tcp'
sourcePortRange: '*'
destinationPortRange: '443'
sourceAddressPrefix: '*'
destinationAddressPrefix: '*'
}
}
{
name: 'DenyAllInbound'
properties: {
priority: 4096
direction: 'Inbound'
access: 'Deny'
protocol: '*'
sourcePortRange: '*'
destinationPortRange: '*'
sourceAddressPrefix: '*'
destinationAddressPrefix: '*'
}
}
]
}
}
resource vnet 'Microsoft.Network/virtualNetworks@2023-05-01' = {
name: vnetName
location: location
properties: {
addressSpace: {
addressPrefixes: [
'10.0.0.0/16'
]
}
subnets: [
{
name: 'web-subnet'
properties: {
addressPrefix: '10.0.1.0/24'
networkSecurityGroup: {
id: nsg.id
}
}
}
{
name: 'app-subnet'
properties: {
addressPrefix: '10.0.2.0/24'
}
}
{
name: 'data-subnet'
properties: {
addressPrefix: '10.0.3.0/24'
privateEndpointNetworkPolicies: 'Enabled'
}
}
]
}
}
output vnetId string = vnet.id
output webSubnetId string = vnet.properties.subnets[0].id
output appSubnetId string = vnet.properties.subnets[1].id
What ships with it
1 file 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.
- 7d ago First seen · 474 lines · 30 tokens per session scan F 635628b9a988
arm-templates is a skill published in the GitHub repository BagelHole/DevOps-Security-Agent-Skills (1,071 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 2,959 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 2026-09-03.
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.
ec2
AWS EC2 virtual machine management — instances, security groups, key pairs, AMIs, EBS volumes, Auto Scaling Groups, Spot Instances, Session Manager, placement groups, and instance lifecycle automation. Trigger on ANY of these, even when EC2 isn't named explicitly: - Launching or provisioning: "spin up a server"…
cloudformation
AWS CloudFormation infrastructure as code for stack management. Use when writing templates, deploying stacks, managing drift, troubleshooting deployments, or organizing infrastructure with nested stacks.
cloudwatch
AWS CloudWatch monitoring for logs, metrics, alarms, and dashboards. Use when setting up monitoring, creating alarms, querying logs with Insights, configuring metric filters, building dashboards, or troubleshooting application issues.
ecs
AWS ECS container orchestration for running Docker containers. Use when deploying containerized applications, configuring task definitions, setting up services, managing clusters, or troubleshooting container issues.
eks
AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services.