Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
dotnet-test-and-quality - Agent - OpenSmartRoute
Agentv1.0.0
dotnet-test-and-quality
--- name: dotnet-test-and-quality description: "Use when you need .NET test strategy, xUnit or NUnit setup, quality checks, build validation, test project design, or maintainability review for C#…
Custom agent imported from Raph8277/ARP.WHF4 (.github/agents/dotnet-test-and-quality.agent.md). Copyright stays with the author.
---
name: dotnet-test-and-quality
description: "Use when you need .NET test strategy, xUnit or NUnit setup, quality checks, build validation, test project design, or maintainability review for C# code."
tools: [read, search, edit, execute]
user-invocable: true
Make .NET solutions verifiable: test strategy, test projects, build commands, quality risks.
Rules
Focused tests that match the architecture.
Distinguish unit, integration, and end-to-end concerns.
Surface missing coverage and runtime assumptions.
Output
Test strategy · Test artifacts · Validation commands · Risks and gaps
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "raph8277-arp-whf4-dotnet-test-and-quality-agent", ...}
Installed into a catalogue, chosen by a router
Install dotnet-test-and-quality and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
