foundry-runtime-audit

A method for checking whether a codebase really uses an Azure AI Foundry project or runtime, rather than calling Azure OpenAI directly. Azure AI Foundry is Microsoft's platform for organizing AI projects and runtimes.

In plain words
What is it for?
It is for auditing C# and Python repositories, distinguishing Foundry-style clients from direct Azure OpenAI clients, and checking migration compatibility.
Why use it?
It replaces assumptions based on names or documentation with evidence from package references, client construction, endpoints, and—when needed—Git history.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/alonf/mcppythondemo/foundry-runtime-audit
Any agent
npx skills add alonf/MCPPythonDemo --skill foundry-runtime-audit
Clone the repo
git clone --depth 1 https://github.com/alonf/MCPPythonDemo

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00403
Opus 5 $0.00000 $0.00201
Sonnet 5 $0.00000 $0.00081
Haiku 4.5 $0.00000 $0.00040

Measured yesterday against content hash a42232a0fda3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

foundry-runtime-audit 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 yesterday.

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.

.squad/skills/foundry-runtime-audit/SKILL.md · 43 lines

What it actually says

Foundry Runtime Audit

Purpose

Determine whether a codebase is truly using an Azure AI Foundry project/runtime abstraction or merely calling Azure OpenAI directly.

When to use

  • A repo claims “Foundry” usage, but behavior is unclear
  • Migration parity depends on matching auth/client/runtime semantics
  • You need evidence from real code, not naming or branch assumptions

Procedure

  1. Inspect package references

    • C#: check .csproj for Azure.AI.Projects or project-runtime packages
    • Python: check pyproject.toml / requirements for Foundry/project SDKs
  2. Inspect runtime construction

    • Direct Azure OpenAI usually looks like:
      • C#: new AzureOpenAIClient(endpoint, credential).GetChatClient(deployment)
      • Python: AzureOpenAI(azure_endpoint=..., api_version=...)
    • Foundry-project usage should create a project/client/runtime object, not just endpoint + deployment
  3. Check endpoint shape

    • *.cognitiveservices.azure.com usually indicates direct Azure OpenAI resource usage
    • Project-style config should expose explicit project/runtime concepts
  4. Search the full repo history if needed

    • Search for Foundry, AIProject, Azure.AI.Projects, project-runtime types
    • Do not infer architecture from README wording alone
  5. Run the real entrypoint

    • Confirm what the live path actually tries to construct
    • Even if startup fails, early initialization often proves whether the path is direct Azure OpenAI or project-backed

Output template

  • Current runtime type: direct Azure OpenAI / Foundry project runtime
  • Evidence: package refs, constructor calls, endpoint form, live run notes
  • Parity invariant: what downstream ports must match
  • Gap call: whether the gap is in the port, or already in the source system
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. yesterday First seen · 43 lines · 0 tokens per session scan A a42232a0fda3

Subscribe to this mod's changes

foundry-runtime-audit is a skill published in the GitHub repository alonf/MCPPythonDemo (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 403 tokens. 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens