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 jnPiyush/AgentX --skill azure-foundrygit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/azure-foundry)<a href="https://agentmods.dev/skills/jnpiyush/agentx/azure-foundry"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/azure-foundry/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/jnpiyush/agentx/azure-foundry"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/azure-foundry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00106 | $0.01104 |
| Opus 5.5 | $0.00042 | $0.00442 |
| Sonnet 5.5 | $0.00021 | $0.00221 |
| Haiku 4.5 | $0.00011 | $0.00110 |
Grade A, and why
azure-foundry 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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure AI Foundry
Companion Extension: For detailed operational playbooks (create agents, deploy containers, invoke endpoints, trace with App Insights, troubleshoot), install Azure MCP Extension (
ms-azuretools.vscode-azure-mcp-server). In VS Code it also wires in the Azure Skills plugin frommicrosoft/azure-skillsplus Foundry MCP. Frontier recommends it when Azure files are detected and the installer can add it automatically for Azure-oriented workspaces.
When to Use This Skill
- Designing agent architecture on Azure Foundry or Azure AI Agent Service
- Selecting models via GitHub Models or Azure AI model catalog (cost/quality tradeoffs)
- Planning evaluation strategy with Foundry evals (RAGAS, LLM-as-judge)
- Defining guardrails, safety instructions, and content filtering policies
- Choosing deployment patterns (managed endpoint vs AKS vs serverless)
Agent Lifecycle
Design -> Build -> Evaluate -> Deploy -> Monitor -> Iterate
- Design - Define agent capabilities, tool schemas, system prompts
- Build - Implement with Azure AI Agent Service or Semantic Kernel
- Evaluate - Run evals (RAGAS, custom rubrics, LLM-as-judge)
- Deploy - Azure AI Foundry managed endpoints or AKS
- Monitor - Application Insights + OpenTelemetry tracing
- Iterate - Feedback loops, prompt refinement, model updates
Tracing Pattern
All agent calls MUST include OpenTelemetry spans:
agent.plan- Planning/reasoning stepagent.tool_call- Tool invocation with input/outputagent.llm_call- LLM API call with model, tokens, latencyagent.response- Final response with quality metrics
Export to Application Insights via APPLICATIONINSIGHTS_CONNECTION_STRING.
Tool Definition
Tools use JSON Schema for parameters. Every tool MUST have:
name- Unique, descriptive identifierdescription- What it does (used by LLM for selection)parameters- JSON Schema with required fields marked
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.
- 1mo ago Changed f55940778fda
- 1mo ago First seen · 126 lines · 106 tokens per session scan A 005c87113cbc
azure-foundry is a skill published in the GitHub repository jnPiyush/AgentX (17 stars, last pushed 2d ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,104 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…