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 dotnet-presentations/ai-workshop --skill workshop-testinggit clone --depth 1 https://github.com/dotnet-presentations/ai-workshopWrote 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/dotnet-presentations/ai-workshop/workshop-testing)<a href="https://agentmods.dev/skills/dotnet-presentations/ai-workshop/workshop-testing"><img src="https://agentmods.dev/badge/skills/dotnet-presentations/ai-workshop/workshop-testing/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/dotnet-presentations/ai-workshop/workshop-testing"><img src="https://agentmods.dev/badge/skills/dotnet-presentations/ai-workshop/workshop-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 54 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Privilege Escalation · line 61 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00095 | $0.02032 |
| Opus 5.5 | $0.00038 | $0.00813 |
| Sonnet 5.5 | $0.00019 | $0.00406 |
| Haiku 4.5 | $0.00010 | $0.00203 |
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 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 — 96 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 10.0.9+
dotnet new install Microsoft.Extensions.AI.Templates
dotnet new mcpserver -h # built into .NET 10.0.9+ SDK
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.
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.
- 1mo ago Changed e103dc12628b
- 1mo ago Changed · +2 lines bf4cc15ea4b5
- 1mo ago Changed · +4 lines 291266ffb526
- 1mo 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 (60 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 2,032 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
aspire-integration-testing
Write integration tests using .NET Aspire's testing facilities with xUnit. Covers test fixtures, distributed application setup, endpoint discovery, and patterns for testing ASP.NET Core apps with real dependencies.
flutter-mcp-toolkit-control
Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.
flutter-mcp-e2e-harness
Use this skill when writing or running repeatable E2E scenarios for Flutter apps as checked-in Dart with the fluttermcpharness package (packages/harness) — build/launch the app, attach to its VM service, drive widgets (snapshot/tap/enter text) and assert without MCP; also covers the repo showcase launcher (make…
flutter-mcp-cli-runtime-validation
Run Flutter MCP runtime validation from CLI in two steps (launch app, then run validate-runtime), including toolkit-extension gating, screenshot/layout capture, app error collection, optional reload verification, and retry handling for transient first-connect failures.
ui-aqa-flow
Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.