AG-UI is an event-based protocol that lets AI agent backends communicate with user-facing applications. It standardizes agent events and inputs while supporting transports such as server-sent events, WebSockets, and webhooks. The catalogue add-ons help developers build integrations and applications around the protocol.
Borrowing it
Nothing to install: this file belongs to ag-ui-protocol/ag-ui. 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/ag-ui-protocol/ag-ui/main/.github/skills/agui-dotnet-integration-tests/SKILL.mdgit clone --depth 1 https://github.com/ag-ui-protocol/ag-uiWrote 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/ag-ui-protocol/ag-ui/agui-dotnet-integration-tests)<a href="https://agentmods.dev/skills/ag-ui-protocol/ag-ui/agui-dotnet-integration-tests"><img src="https://agentmods.dev/badge/skills/ag-ui-protocol/ag-ui/agui-dotnet-integration-tests.svg" alt="Measured on agentmods" 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 | $0.00176 | $0.04025 |
| Opus 5 | $0.00088 | $0.02013 |
| Sonnet 5 | $0.00035 | $0.00805 |
| Haiku 4.5 | $0.00018 | $0.00402 |
Grade A, and why
agui-dotnet-integration-tests 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 8d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AG-UI .NET Integration Tests
End-to-end tests for the AG-UI .NET SDK that post RunAgentInput, stream events over the wire (SSE or protobuf), and assert behavior through the AGUIChatClient (IChatClient) abstraction.
Orientation
The canonical project layout, endpoint pattern, and naming live in
sdks/dotnet/AGENTS.md (project layout + endpoint pattern) and
sdks/dotnet/docs/architecture.md (the server/client pipeline). Read those first;
this skill covers only the integration-test mechanics on top of them.
One durable gotcha: the test project folder and csproj are named
tests/AGUI.Hosting.AspNetCore.IntegrationTests/ (kept after the server package was
renamed to AGUI.Server), but all types live in namespace AGUI.Server.IntegrationTests.
The ASP.NET hosting glue (AddAGUI, the negotiating endpoint, AGUIResults) lives in
samples/AGUI.Samples.Shared, and the protobuf formatter comes from AGUI.Protobuf.
Project Layout
tests/AGUI.Hosting.AspNetCore.IntegrationTests/ # namespace AGUI.Server.IntegrationTests
├── Infrastructure/
│ ├── IntegrationTestBase.cs # Two-tier base: generic <TEntryPoint> + non-generic (uses Program). Emit helpers, CollectUpdates, CreateClient(handler[, TransportFormat]), VerifyCaptures (8 capture points), recording load/save, id scrubbing.
│ ├── TransportFormat.cs # enum { Json, Protobuf } — selects the wire encoding the test client negotiates
│ ├── DelegatingStreamingChatClient.cs # Func-based IChatClient for inline server behavior
│ ├── CapturingChatClient.cs # IChatClient decorator that records server-side calls (ServerCallCapture)
│ ├── CapturingAGUITransport.cs # IAGUITransport decorator that records client-side turns (TurnCapture)
│ ├── ServerCallCapture.cs # RunAgentInput + ChatMessage[] + ChatOptions + ChatResponseUpdate[] per server call
│ ├── TurnCapture.cs # RunAgentInput + BaseEvent[] per client-side turn
│ ├── ChatResponseUpdateCaptureConverter.cs # JsonConverter that renders ChatResponseUpdate (+RawRepresentation) for snapshots
│ ├── AGUIEndpointExtensions.cs # Test-local MapAGUI: ToChatRequestContext + AsAGUIEventStreamAsync, returns AGUIResults.Events (negotiating)
│ ├── AGUIServerSentEventsResult.cs # Legacy SSE-only IResult (still present; the live endpoint uses AGUIResults instead)
│ ├── AGUICapabilitiesEndpointRouteBuilderExtensions.cs # Test-only AgentCapabilities publisher (the SDK ships no capabilities endpoint; the spec doesn't define one)
│ ├── Program.cs # Minimal host: AddAGUI() + register ProtobufEventStreamFormatter + DelegatingStreamingChatClient + MapAGUI("/agui")
│ └── VerifyConfig.cs # ModuleInitializer for Verify settings (DontScrubDateTimes, DiffRunner disabled)
├── RunLifecycleIntegrationTest.cs # Run lifecycle events [Theory Json/Protobuf]
├── TextStreamingIntegrationTest.cs # Text streaming + multi-turn [Theory Json/Protobuf]
├── ToolCallIntegrationTest.cs # Tool call events [Theory + one Json-only ToolCallResult fact]
├── ClientToolIntegrationTest.cs # Client (frontend) tools [Theory Json/Protobuf]
├── MixedToolInvocationIntegrationTest.cs # Mixed server+client tool batches (approval-flow) [Json-only, has Verify baselines]
├── FrontendToolReinvocationTest.cs # Frontend tool re-invocation [Json-only]
├── StateManagementIntegrationTest.cs # State snapshot/delta [Theory Json/Protobuf]
├── ReasoningIntegrationTest.cs # Thinking/reasoning events [Json-only]
├── ActivityIntegrationTest.cs # Activity snapshot/delta [Json-only]
├── CustomAndRawEventIntegrationTest.cs # Custom/raw events [Theory Json/Protobuf]
├── RawRepresentationFactoryIntegrationTest.cs # Custom RawRepresentation factory [Theory Json/Protobuf]
├── CapabilitiesEndpointIntegrationTest.cs # Capabilities endpoint (exercises the test-local helper) [Json-only]
├── TransportEquivalenceIntegrationTest.cs # Asserts Json and Protobuf decode to identical ChatResponseUpdate sequences
├── AGUIResultsTest.cs # Accept-header negotiation (proto vs SSE vs 406) for AGUIResults.Events
├── Samples/GettingStarted/
│ ├── StepNN_XyzTest.cs # Replay/snapshot test per sample (Step01..Step12)
│ ├── fixtures/{Sample}/*.recording.json # Recorded List<List<ChatResponseUpdate>> (one list per turn)
│ └── baselines/{Sample}/*.verified.json # Verify snapshots, one file per capture point (see below)
└── AGUI.Hosting.AspNetCore.IntegrationTests.csproj # references AGUI.Client, AGUI.Protobuf, AGUI.Samples.Shared + every Step01..Step12 Client/Server
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.
- 8d ago First seen · 247 lines · 176 tokens per session scan A 9f451c953767
agui-dotnet-integration-tests is a skill published in the GitHub repository ag-ui-protocol/ag-ui (15,752 stars, last pushed yesterday), licensed MIT. It adds 176 tokens to every session and 4,025 once invoked, about $0.0009 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
test-automation
Execute Vitest and Playwright test suites with result collection and failure analysis.
qa-testing
Generate and execute API and E2E tests with quality gate assessment.
test-engineer
Automated E2E testing with Playwright including the auto-fix loop — generate test cases from the UI, run them, fix failures and re-run until passing, then produce a human-readable report. Test until it passes, not just test and report. Drives /toh-test; use whenever tests must be written, run, or made green.
testing-strategy
Comprehensive testing skill covering unit, integration, and e2e testing with TDD. Use when writing tests, improving coverage, or setting up testing infrastructure. Keywords: test, TDD, unit test, integration, e2e, coverage, mock, jest, vitest.
test-automation
Plan, write, and review automated tests following KATA (Komponent Action Test Architecture) on Playwright + TypeScript, or explain existing automated tests in a sealed read-only mode. Use when writing E2E or API/integration tests, creating Page or Api components, designing ATCs, parameterizing test data, registering…
dpf-verify-on-live-install
Use when asked to functionally verify that a DPF feature works on the live install by driving the happy path on the running portal.