AI Agents for Beginners is a course that teaches the fundamentals of building AI agents through a sequence of lessons. People learning generative AI and agent development use it to study topics and frameworks including AutoGen and Semantic Kernel. The catalogue entries provide skills, instructions, and an agent related to the course.
Borrowing it
Nothing to install: this file belongs to microsoft/ai-agents-for-beginners. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/ai-agents-for-beginners/main/.agents/skills/testing-course-samples/SKILL.mdgit clone --depth 1 https://github.com/microsoft/ai-agents-for-beginnersWrote 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/ai-agents-for-beginners/testing-course-samples)<a href="https://agentmods.dev/skills/microsoft/ai-agents-for-beginners/testing-course-samples"><img src="https://agentmods.dev/badge/skills/microsoft/ai-agents-for-beginners/testing-course-samples/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/ai-agents-for-beginners/testing-course-samples"><img src="https://agentmods.dev/badge/skills/microsoft/ai-agents-for-beginners/testing-course-samples.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- 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 | $0.00086 | $0.01116 |
| Opus 5.5 | $0.00034 | $0.00446 |
| Sonnet 5.5 | $0.00017 | $0.00223 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
testing-course-samples 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing the Course Samples
Validate that the lesson notebooks and code samples run against a live
Microsoft Foundry / Azure OpenAI setup. The repo ships a runner at
scripts/validate-notebooks.ps1 that
executes every Python notebook headlessly and prints a PASS/FAIL matrix.
When to use
- "Validate all the notebooks / samples against my Azure subscription."
- "Smoke-test the course after upgrading packages or changing models."
- "Which lessons still pass / fail live?"
Do not use this for the AI Smoke Test GitHub Action (that validates deployed
hosted agents — see tests/README.md). This skill
runs the notebooks locally.
Prerequisites (check first)
- Python 3.12+ with course deps:
python -m pip install -r requirements.txtplus the executor:python -m pip install nbconvert ipykernel. .envat the repo root (copy from.env.example) with at least:AZURE_AI_PROJECT_ENDPOINT— Foundry project endpoint (https://<account>.services.ai.azure.com/api/projects/<project>)AZURE_AI_MODEL_DEPLOYMENT_NAME— a non-deprecated deployment (e.g.gpt-5-mini)AZURE_OPENAI_ENDPOINT(https://<account>.openai.azure.com) andAZURE_OPENAI_DEPLOYMENTfor lessons that call Azure OpenAI directly (Lesson 06, 02-azure-openai, 14 handoff/human-loop).
az logincompleted — samples authenticate withAzureCliCredential(Entra ID, keyless).- Verify the model deployment exists:
az cognitiveservices account deployment list -g <rg> -n <account> -o table.
Running the validation
# All Python notebooks (skips .NET, .venv, site-packages, translations, skill assets)
pwsh scripts/validate-notebooks.ps1
# A single lesson, with a longer per-cell timeout
pwsh scripts/validate-notebooks.ps1 -Filter '08-*' -Timeout 600
# Just list what would run (no execution)
pwsh scripts/validate-notebooks.ps1 -List
# Explicit interpreter (if `python` is not on PATH, e.g. Windows Store alias)
pwsh scripts/validate-notebooks.ps1 -Python "C:/path/to/python.exe"
The script writes executed copies, per-notebook logs, and results.json to
$env:TEMP\aiab-nbval and exits with the number of failures.
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 First seen · 80 lines · 86 tokens per session scan A 838ef21b9163
testing-course-samples is a skill published in the GitHub repository microsoft/ai-agents-for-beginners (77,700 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 1,116 once invoked, about $0.0003 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
nexent-daily-test
A procedure for running Nexent daily, full-layer tests on a self-hosted Ubuntu machine. Nexent is tested across separate layers such as unit, service, AI runtime, and browser journeys, with results and evidence kept locally.
tfp-verification
Generate a deterministic report for disposable executor acceptance tests.
agent-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agent-production-validator
Agent skill for production-validator - invoke with $agent-production-validator.
agent-implementer-sparc-coder
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder.