What is foundry-ads-session?

A guided architecture-planning conversation for Microsoft Foundry, Microsoft's platform for building and running AI applications and agents. It gathers requirements across AI and machine-learning use cases and helps produce a Foundry-based design.

Use it to plan enterprise chat systems, AI agents, multi-agent workflows, retrieval-augmented generation, fine-tuning, batch inference, or real-time scoring.

It helps turn a broad AI idea into a documented solution with suitable models, agents, data retrieval, evaluation, deployment, and governance choices.

How HaoZhang615/ads-copilot configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to HaoZhang615/ads-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/HaoZhang615/ads-copilot/main/.github/skills/foundry-ads-session/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/HaoZhang615/ads-copilot

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/haozhang615/ads-copilot/foundry-ads-session.svg)](https://agentmods.dev/skills/haozhang615/ads-copilot/foundry-ads-session)

Your own site

<a href="https://agentmods.dev/skills/haozhang615/ads-copilot/foundry-ads-session"><img src="https://agentmods.dev/badge/skills/haozhang615/ads-copilot/foundry-ads-session.svg" alt="Measured on agentmods" height="20"></a>

Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,887 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00148	$0.02887
Opus 5	$0.00074	$0.01443
Sonnet 5	$0.00030	$0.00577
Haiku 4.5	$0.00015	$0.00289

Measured 8d ago against content hash b2d7d1718bfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

foundry-ads-session 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 8d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (foundry-ads-session/scripts/generate_architecture.py, scripts/generate_architecture.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.github/skills/foundry-ads-session/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft Foundry ADS Session

This skill provides domain-specific knowledge for Microsoft Foundry (Microsoft Foundry) to be used within an Architecture Design Session. The ADS methodology (persona, pacing, session structure, decision narration, trade-off framework, self-critique) is defined in the runtime system prompt. This skill supplies the Foundry-specific questions, patterns, components, and references that the methodology operates on.

Domain: Microsoft Foundry

This skill covers the Microsoft Foundry unified AI platform including:

Resource Model: Foundry resource (Microsoft.CognitiveServices/account kind=AIServices) + project subresource; Classic Hub (Microsoft.MachineLearningServices/workspaces kind=Hub) + Project (legacy, still supported as Foundry Classic)
SDK / API: azure-ai-projects v1.0.0 (GA Jul 2025, Foundry Classic) and v2.0.0b4+ (Preview Feb 2026, new Foundry portal); azure-ai-inference, azure-ai-evaluation, azure-ai-agents; OpenAI-compatible client via get_openai_client()
Agent Service: Multi-agent framework (MAF), hosted agents (LangGraph, custom frameworks), standard vs basic agent setup; Foundry MCP Server (mcp.ai.azure.com)
Model Deployment: GlobalStandard, GlobalProvisionedManaged, GlobalBatch, DataZoneStandard, DataZoneProvisionedManaged, DataZoneBatch, Standard, ProvisionedManaged, DeveloperTier; MaaS (serverless) vs MaaP (managed online endpoint)
Networking: Public, Private Link (privatelink.cognitiveservices.azure.com), Managed VNet with outbound rules; agent subnet injection (RFC-1918 /24)
Identity & Security: Managed Identity (system/user-assigned), Entra ID, DefaultAzureCredential; RBAC roles (Azure AI User, Azure AI Project Manager, Contributor); CMK encryption; Content Safety; Key Vault
Observability: Azure Monitor, Application Insights, OpenTelemetry tracing via azure-ai-projects; token usage metrics, latency, evaluation scores
Enterprise Patterns: Landing zone integration, hub-spoke networking, multi-region design, dev/test/prod, governance, cost management, chargeback

Read the full file on GitHub · 180 lines

Files

What ships with it

21 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.

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.

8d ago First seen · 180 lines · 148 tokens per session scan A b2d7d1718bfc

Subscribe to this mod's changes

foundry-ads-session is a skill published in the GitHub repository HaoZhang615/ads-copilot (2 stars, last pushed 6mo ago), licensed MIT. It adds 148 tokens to every session and 2,887 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 2026-08-31.

Building agents Planning architecture azure copilot databricks fastapi mermaid

code-to-diagram

Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a…

zebbern/claude-code-guide · 74 tokens

init-workspace-documentation

Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.

griddynamics/rosetta · 10 tokens

drawio

WORKFLOW SKILL — Generate Azure architecture diagrams in .drawio via simonkurtz-MSFT MCP server (full Azure icon set, batch creation, transactional mode). Covers architecture, dependency, runtime-flow, and as-built diagrams. WHEN: 'draw.io diagram', 'Azure architecture diagram', 'as-built diagram', 'runtime flow…

jonathan-vella/apex-accelerator · 99 tokens

azure-bicep-patterns

UTILITY SKILL — Reusable Azure Bicep patterns: hub-spoke, private endpoints, diagnostics, AVM composition. WHEN: "hub-spoke Bicep", "private endpoint module", "diagnostic settings", "AVM Bicep composition". USE FOR: Bicep template design, hub-spoke networking, private endpoint patterns, AVM modules. DO NOT USE FOR…

jonathan-vella/apex-accelerator · 114 tokens

copilot-customization

Authoritative reference for VS Code Copilot customization mechanisms: instructions, prompt files, custom agents, agent skills, MCP servers, hooks, and plugins. Use when deciding which customization type to use, creating new .instructions.md/.prompt.md/.agent.md/SKILL.md/mcp.json files from scratch, or debugging why a…

jonathan-vella/apex-accelerator · 90 tokens

deploy-model

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai…

jonathan-vella/apex-accelerator · 129 tokens

ads-copilot: Skill for Claude Code