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 agentmods add skills/dotnet-presentations/ai-workshop/workshop-testingnpx skills add dotnet-presentations/ai-workshop --skill workshop-testinggit clone --depth 1 https://github.com/dotnet-presentations/ai-workshopWhat 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 | $0.00095 | $0.01892 |
| Opus 5 | $0.00048 | $0.00946 |
| Sonnet 5 | $0.00019 | $0.00378 |
| Haiku 4.5 | $0.00010 | $0.00189 |
Grade A, and why
workshop-testing 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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workshop Testing
Complete the workshop the way an attendee would — follow each Part N - */README.md literally, in a scratch directory — then reconcile what you produced against the committed snapshot and write a report.
Ground rules
- Follow the README, not this skill. The README is the artifact under test. If it is wrong or ambiguous, that is a finding, not something to silently work around.
- Always scaffold with
dotnet new. Never hand-author or copy a.csproj, and never use a committed snapshot as your working directory. The template workflow is part of what is being tested. - Work in
test-workspace/at the repo root (gitignored / delete when done). Never build inside the snapshot folders while testing. - Ask, don't guess. If a step needs a value you don't have (subscription, endpoint, model name), ask the user.
- Record every clarification you needed. Anything you had to infer is a documentation gap worth reporting.
Setup
.\.github\scripts\setup-workshop-credentials.ps1 -ApplyUserSecrets
dotnet --list-sdks # expect 10.0.x
dotnet new install Microsoft.Extensions.AI.Templates
dotnet new install Microsoft.McpServer.ProjectTemplates
docker --version # only needed for Parts 4 and 11
The script collects the WORKSHOP_* variables and, with -ApplyUserSecrets, writes the Foundry endpoint and key into the snapshot console projects (as AzureOpenAI:Endpoint / AzureOpenAI:Key), the local model settings into Part 9 if configured, and the composed ConnectionStrings:openai into the Part 11 AppHost. Add -Force if a key has been rotated since the last run.
Nothing in the workshop reads WORKSHOP_* directly. The console samples read user secrets (AzureOpenAI:Endpoint, AzureOpenAI:Key) and the Aspire app reads ConnectionStrings:openai. The script also configures a Part 4 app scaffolded at test-workspace/GenAiLab.
The samples hardcode the deployment names gpt-5-mini and text-embedding-3-small. If the test resource uses different names, that is a source edit in every part, not a config change.
What ships with it
1 file 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.
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.
- 2d ago First seen · 90 lines · 95 tokens per session scan A f728b0bf4f82
workshop-testing is a skill published in the GitHub repository dotnet-presentations/ai-workshop (54 stars, last pushed 7d ago), licensed MIT. It adds 95 tokens to every session and 1,892 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
github-actions-hardening
Security hardening reviewer for GitHub Actions workflow files (.github/workflows/.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill…
ngrx-signal-store
Build, review, and test NgRx SignalStore state management in Angular, using production patterns pinned to the official @ngrx/signals docs. Use this whenever Angular state management comes up: writing or reviewing a store, choosing between signalState and signalStore or between rxMethod and signalMethod, adding an…
github-actions-efficiency
Audit GitHub Actions workflow efficiency and recommend fixes to reduce CI minutes and costs.
github-actions-runtime-upgrade-conventions
Upgrade GitHub Actions to supported runtimes by selecting safe action versions, preserving workflow behavior, and validating post-upgrade execution.
csharp-docs
Ensure that C# types are documented with XML comments and follow best practices for documentation.
csharp-xunit
Get best practices for XUnit unit testing, including data-driven tests.