ai-foundry-posture-check

ai-foundry-posture-check is a skill for Claude Code, Codex from ricmmartins/azure-sre-agent-skills. It costs 142 tokens per session (5,465 once invoked), scanned A, original, MIT.

A checklist and assessment process for Azure OpenAI and Microsoft Foundry deployments. It examines security, reliability, and spending risks in AI services before or during production use.

In plain words
What is it for?
Use it to review identity and network settings, content filtering, diagnostics, model versions, rate limits, and provisioned capacity.
Why use it?
It helps reveal issues such as exposed access, missing monitoring, outdated model versions, disabled content filtering, and inefficient capacity settings. It requires deployment details before starting the assessment.

Skill for Claude CodeCodex

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

Good fit Use it to review identity and network settings, content filtering, diagnostics, model versions, rate limits, and provisioned capacity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ricmmartins/azure-sre-agent-skills/08-ai-foundry-posture
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 ricmmartins/azure-sre-agent-skills --skill 08-ai-foundry-posture
Clone the repo
git clone --depth 1 https://github.com/ricmmartins/azure-sre-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 ai-foundry-posture-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/ricmmartins/azure-sre-agent-skills/08-ai-foundry-posture/github.svg)](https://agentmods.dev/skills/ricmmartins/azure-sre-agent-skills/08-ai-foundry-posture)
Your own site
<a href="https://agentmods.dev/skills/ricmmartins/azure-sre-agent-skills/08-ai-foundry-posture"><img src="https://agentmods.dev/badge/skills/ricmmartins/azure-sre-agent-skills/08-ai-foundry-posture/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 ai-foundry-posture-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/ricmmartins/azure-sre-agent-skills/08-ai-foundry-posture"><img src="https://agentmods.dev/badge/skills/ricmmartins/azure-sre-agent-skills/08-ai-foundry-posture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,465 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, 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 Tool Misuse · line 496
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 $0.00142 $0.05465
Opus 5 $0.00071 $0.02733
Sonnet 5 $0.00028 $0.01093
Haiku 4.5 $0.00014 $0.00547

Measured 12d ago against content hash 6c109f6cdea0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-foundry-posture-check 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 12d 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.

skills/08-ai-foundry-posture/SKILL.md · 526 lines

How it starts

The opening of the file, as written. The whole thing — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Foundry & OpenAI Posture Check

Purpose

Assess the security, reliability, and cost efficiency of Azure OpenAI and Microsoft Foundry deployments. Detects the most common anti-patterns that startups make when building AI-powered products — from exposed endpoints to runaway token costs.

Based on the Azure Well-Architected Framework for AI workloads and Microsoft Foundry operational best practices.

When to use this skill

  • User asks "is our OpenAI deployment secure?"
  • User asks about AI cost optimization or token consumption
  • Review before going to production with an AI feature
  • User asks about content filtering, model versions, or rate limiting
  • Periodic AI workload health check

Pre-check

Confirm with the user:

  • Which Azure OpenAI / Cognitive Services accounts to assess (or "all in subscription")
  • Whether they use PTU (Provisioned Throughput) or Standard deployments
  • Whether they have production AI workloads already live

Assessment procedure

Step 0: Discover AI resources

az cognitiveservices account list \
  --subscription <sub-id> \
  --query "[?kind=='OpenAI' || kind=='AIServices'].{name:name, kind:kind, rg:resourceGroup, location:location, sku:sku.name}" \
  -o table

If no results, try:

az cognitiveservices account list \
  --subscription <sub-id> \
  --query "[].{name:name, kind:kind, rg:resourceGroup, location:location}" \
  -o table

If no Cognitive Services accounts exist, report "No Azure OpenAI or AI Foundry resources found" and end assessment.

For each account found, run the following checks:


🔐 CATEGORY 1 — Security (Critical)

Check 1.1 — Managed Identity enabled (not API keys only)

az cognitiveservices account show \
  --name <account> --resource-group <rg> \
  --query "{identity:identity.type, disableLocalAuth:properties.disableLocalAuth}" \
  -o json
Finding Severity Score
identity.type = SystemAssigned/UserAssigned AND disableLocalAuth = true ✅ Pass 12 pts
identity.type set but disableLocalAuth = false ⚠️ Partial 6 pts
identity.type = None or null ❌ Fail 0 pts

Read the full file on GitHub · 526 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. 12d ago First seen · 526 lines · 142 tokens per session scan A 6c109f6cdea0

Subscribe to this mod's changes

ai-foundry-posture-check is a skill published in the GitHub repository ricmmartins/azure-sre-agent-skills (70 stars, last pushed 18d ago), licensed MIT. It adds 142 tokens to every session and 5,465 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

Azure Naming And Tagging

CAF-aligned Azure naming convention and mandatory tags — resource-type abbreviations, region codes, and owner/cost-center/environment/workload tags for cost attribution.

niels-emmer/myace · 37 tokens

Azure WAF Pillar Review

Azure-specific Well-Architected Framework pillar checklists — reliability, security, cost optimization, operational excellence, performance efficiency — for reviewing Azure infrastructure changes.

niels-emmer/myace · 37 tokens

Azure CAF Landing Zones

Cloud Adoption Framework governance essentials — management-group hierarchy, subscription design, RBAC scoping, Azure Policy guardrails, and network topology for Azure landing zones.

niels-emmer/myace · 36 tokens

Azure Identity Design

Entra ID, managed identity, and workload identity federation design for Azure — when to use which, and how to avoid long-lived service-principal secrets.

niels-emmer/myace · 35 tokens

Azure Security Checklist

Microsoft-recommended Azure security practices — identity, network, data, and monitoring — as a PASS/FAIL/N/A checklist run before any Azure change is proposed for apply.

niels-emmer/myace · 38 tokens

azure-mgmt-applicationinsights-dotnet

Azure Application Insights SDK for .NET. Application performance monitoring and observability resource management. Use for creating Application Insights components, web tests, workbooks, analytics items, and API keys. Triggers: "Application Insights", "ApplicationInsights", "App Insights", "APM", "application…

microsoft/skills · 82 tokens