Azure Skills Plugin is an agent plugin that packages Azure-specific guidance with MCP server configurations for carrying out Azure work. Coding agents use it to plan, deploy, troubleshoot, monitor, govern, and optimize Azure applications and services. The catalogue entries are the plugin's skills, instructions, and execution integrations.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/azure-skillsnpx agentmods add skills/microsoft/azure-skills/microsoft-foundryWrote 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/microsoft/azure-skills/microsoft-foundry)<a href="https://agentmods.dev/skills/microsoft/azure-skills/microsoft-foundry"><img src="https://agentmods.dev/badge/skills/microsoft/azure-skills/microsoft-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/microsoft/azure-skills/microsoft-foundry"><img src="https://agentmods.dev/badge/skills/microsoft/azure-skills/microsoft-foundry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk 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 | $0.00226 | $0.06347 |
| Opus 5.5 | $0.00090 | $0.02539 |
| Sonnet 5.5 | $0.00045 | $0.01269 |
| Haiku 4.5 | $0.00023 | $0.00635 |
Grade A, and why
microsoft-foundry scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Applies to **any** call against a Foundry project or its parent Foundry account — Foundry MCP tools, `azd`, `az` CLI, `curl`, REST, or SDK. This is a copy
94% identical to microsoft-foundry — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Foundry Skill
This skill helps developers work with Microsoft Foundry resources, covering model discovery and deployment, complete dev lifecycle of AI agent, evaluation workflows, and troubleshooting.
Pre-Execution Requirements
Follow each applicable subsection below before starting its corresponding action or workflow.
Dependency Check and Setup
MANDATORY: As the first step after this skill loads, run the dependency check and setup script below from this skill's root and wait for it to finish before continuing. The script checks first and installs only missing dependencies; it does not reinstall dependencies that are already available.
You MUST complete this check before reading or entering any sub-skill, workflow, or workflow-specific reference.
./scripts/check-and-setup-dependencies.sh # macOS / Linux
./scripts/check-and-setup-dependencies.ps1 # Windows (pwsh)
Strictly follow the script output for subsequent actions.
Workflow Guidance
MANDATORY: Before executing ANY workflow-specific steps, you MUST read the corresponding sub-skill document. Do not call workflow-specific MCP tools for a workflow without reading its skill document. This applies even if you already know the MCP tool parameters — the skill document contains required workflow steps, pre-checks, and validation logic that must be followed. This rule applies on every new user message that triggers a different workflow, even if the skill is already loaded.
Foundry MCP
MANDATORY: Before using Foundry MCP operations, call the Azure MCP foundry tool and inspect the available Foundry MCP tools and related parameters. Treat this as the discovery/help step for MCP-based workflows.
azd
MANDATORY: Before executing ANY azd command, you MUST read azd-guidance and strictly follow the shared rules defined in it, especially the AZURE_DEV_USER_AGENT setting rules.
Sub-Skills
This skill includes specialized sub-skills for specific workflows. When a sub-skill matches the task, strictly follow its workflow:
What ships with it
60 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.
- .gitignore 0 B
- finetuning/references/agentic-rft.md 3.2 KB
- finetuning/references/dataset-formats.md 3.7 KB
- finetuning/references/deployment.md 3.4 KB
- finetuning/references/evaluation.md 5.8 KB
- finetuning/references/grader-design.md 3.4 KB
- finetuning/references/hyperparameters.md 3.2 KB
- finetuning/references/large-file-uploads.md 927 B
- finetuning/references/platform-gotchas.md 2.0 KB
- finetuning/references/reward-hacking.md 2.9 KB
- finetuning/references/training-curves.md 4.1 KB
- finetuning/references/training-types.md 3.1 KB
- finetuning/references/vision-fine-tuning.md 4.1 KB
- finetuning/scripts/calibrate_grader.py 9.3 KB runs code
- finetuning/scripts/check_training.py 7.8 KB runs code
- finetuning/scripts/cleanup.py 9.5 KB runs code
- finetuning/scripts/common.py 7.6 KB runs code
- finetuning/scripts/convert_dataset.py 11 KB runs code
- finetuning/scripts/deploy_model.py 9.4 KB runs code
- finetuning/scripts/evaluate_model.py 11 KB runs code
- finetuning/scripts/generate_distillation_data.py 10 KB runs code
- finetuning/scripts/monitor_training.py 5.7 KB runs code
- finetuning/scripts/score_dataset.py 7.7 KB runs code
- finetuning/scripts/submit_training.py 11 KB runs code
- finetuning/scripts/validate/__init__.py 305 B runs code
- finetuning/scripts/validate/data_stats.py 6.2 KB runs code
- finetuning/scripts/validate/validate_dpo.py 3.7 KB runs code
- finetuning/scripts/validate/validate_rft.py 8.6 KB runs code
- finetuning/scripts/validate/validate_sft.py 4.5 KB runs code
- finetuning/SKILL.md 5.4 KB
- finetuning/workflows/dataset-creation.md 3.1 KB
- finetuning/workflows/diagnose-poor-results.md 2.3 KB
- finetuning/workflows/full-pipeline.md 3.1 KB
- finetuning/workflows/iterative-training.md 3.1 KB
- finetuning/workflows/quickstart.md 4.5 KB
- foundry-agent/agent-optimizer/agent-optimizer.md 3.3 KB
- foundry-agent/agent-optimizer/references/azd-setup.md 1.2 KB
- foundry-agent/agent-optimizer/references/eval-yaml.md 3.2 KB
- foundry-agent/agent-optimizer/references/optimize-workflow.md 2.1 KB
- foundry-agent/agent-optimizer/references/python-patterns.md 4.0 KB
- foundry-agent/agent-optimizer/references/scaffold.md 3.3 KB
- foundry-agent/azd-guidance/azd-guidance.md 1.2 KB
- foundry-agent/azd-guidance/references/azd-ai-cli.md 9.4 KB
- foundry-agent/cicd/cicd.md 301 B
- foundry-agent/create/create-hosted.md 33 KB
- foundry-agent/create/create-managed-harness.md 6.6 KB
- foundry-agent/create/create-prompt.md 4.5 KB
- foundry-agent/create/quick-start-hosted.md 23 KB
- foundry-agent/create/references/enable-incoming-a2a.md 3.7 KB
- foundry-agent/create/references/foundry-model.md 1.6 KB
- foundry-agent/create/references/foundry-tool-catalog.md 43 KB
- foundry-agent/create/references/guardrails/guardrail-api-create.md 3.8 KB
- foundry-agent/create/references/guardrails/guardrail-attach.md 3.8 KB
- foundry-agent/create/references/guardrails/guardrail-manage.md 2.1 KB
- foundry-agent/create/references/langchain-langgraph-hosting.md 2.2 KB
- foundry-agent/create/references/local-run.md 10 KB
- foundry-agent/create/references/managed-harness-agent.md 3.1 KB
- foundry-agent/create/references/re-host.md 2.6 KB
- foundry-agent/create/references/sdk-operations.md 2.2 KB
- foundry-agent/create/references/skills/managed-harness-agent-skill-attach.md 1.3 KB
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.
- 6d ago Changed · +9 lines · +2 tokens per session dc8b45f94d82
- 8d ago Changed a157211705a8
- 18d ago Changed e92acb2507b6
- 26d ago Changed 6022ba3f34db
- 27d ago Changed 199914d82763
- 28d ago Changed c5e8efe9031c
- 29d ago Changed d14c074fec54
- 1mo ago Changed · +2 lines · +7 tokens per session 785cf19f8312
- 1mo ago Changed 70b745282e8d
- 1mo ago First seen · 292 lines · 217 tokens per session scan A 35e4488c4979
microsoft-foundry is a skill published in the GitHub repository microsoft/azure-skills (1,583 stars, last pushed yesterday), licensed MIT. It adds 226 tokens to every session and 6,347 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 94% identical to microsoft-foundry, differing in 0 lines, and is treated as a copy.
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…