ag-ui: Skill for Claude Code

.github/skills/agui-dotnet-unit-tests/SKILL.md

agui-dotnet-unit-tests is a skill for Claude Code, Codex from ag-ui-protocol/ag-ui. It costs 154 tokens per session (1,550 once invoked), scanned A, original, MIT.

A testing skill for writing unit tests for the AG-UI .NET SDK. Unit tests check small parts of a program automatically, while compatibility tests compare behavior with data from another implementation.

In plain words
What is it for?
Use it to test new SDK types and methods, event serialization round-trips, protobuf conversion, client and server behavior, transport negotiation, and SSE formatting.
Why use it?
It helps tests catch serialization and naming mistakes without relying on fragile full-text comparisons, and keeps the SDK compatible with existing TypeScript fixtures.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

This is ag-ui-protocol/ag-ui's own configuration. It tells Claude Code and Codex how to work on ag-ui itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ag-ui configures →

About the project

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.

ag-ui-protocol/ag-ui · 15,752 stars · on GitHub · ag-ui.com

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ag-ui-protocol/ag-ui/main/.github/skills/agui-dotnet-unit-tests/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ag-ui-protocol/ag-ui

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agui-dotnet-unit-tests

README.md
[![agentmods](https://agentmods.dev/badge/skills/ag-ui-protocol/ag-ui/agui-dotnet-unit-tests.svg)](https://agentmods.dev/skills/ag-ui-protocol/ag-ui/agui-dotnet-unit-tests)
Your own site
<a href="https://agentmods.dev/skills/ag-ui-protocol/ag-ui/agui-dotnet-unit-tests"><img src="https://agentmods.dev/badge/skills/ag-ui-protocol/ag-ui/agui-dotnet-unit-tests.svg" alt="Measured on agentmods" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,550 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00154 $0.01550
Opus 5 $0.00077 $0.00775
Sonnet 5 $0.00031 $0.00310
Haiku 4.5 $0.00015 $0.00155

Measured 8d ago against content hash bcef4be6d456, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agui-dotnet-unit-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.

.github/skills/agui-dotnet-unit-tests/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AG-UI .NET Unit Tests

Conventions for the tests/*.UnitTests projects. Mined from sdks/dotnet/AGENTS.md and existing tests. An agent gets these wrong by default: asserting on deserialized objects (misses naming bugs), comparing full JSON strings (fragile), using reflection, or skipping the FixtureLoader compatibility pattern.

All commands run from sdks/dotnet/.

Unit-test projects

Project Focus
tests/AGUI.Abstractions.UnitTests/ Event serialization round-trips; backward compat vs TypeScript fixtures (Compatibility/)
tests/AGUI.Protobuf.UnitTests/ Protobuf codec round-trips; JsonElement↔protobuf Value conversion
tests/AGUI.Client.UnitTests/ Client builders, content-negotiation handler, transport, protocol rules
tests/AGUI.Server.UnitTests/ ChatResponseUpdate → AG-UI event conversion
tests/AGUI.Formatting.UnitTests/ SSE event-stream formatter (read/write, media type)

Run one project: dotnet test tests/AGUI.Abstractions.UnitTests/

Conventions

  • Test files live directly under the project root (not mirrored into Events/ subfolders). Compatibility tests go in the Compatibility/ subfolder.
  • Test class name: {TypeUnderTest}Test (RunStartedEventTest, ToolCallBuilderTest). Compatibility class: {Category}CompatibilityTest (RunEventsCompatibilityTest).
  • public sealed class, one class per file, file name matches type.
  • [Fact] for single cases, [Theory] + [InlineData] for parameterized cases.
  • Serialize via the source-generated context: AGUIJsonSerializerContext.Default.{Type} — never JsonSerializer.Serialize<object>(...) or hand-rolled options.

Pattern 1 — Event serialization round-trip (Abstractions)

Serialize via the source-gen context, parse with JsonDocument, assert each camelCase property name AND the type discriminator. This is what catches [JsonPropertyName] bugs.

[Fact]
public void Serialization_RoundTrips()
{
    var evt = new RunStartedEvent { ThreadId = "t1", RunId = "r1", Timestamp = 1234567890 };

    var json = JsonSerializer.Serialize(evt, AGUIJsonSerializerContext.Default.RunStartedEvent);
    using var doc = JsonDocument.Parse(json);

    Assert.Equal("RUN_STARTED", doc.RootElement.GetProperty("type").GetString());
    Assert.Equal("t1", doc.RootElement.GetProperty("threadId").GetString());
    Assert.Equal("r1", doc.RootElement.GetProperty("runId").GetString());
    Assert.Equal(1234567890, doc.RootElement.GetProperty("timestamp").GetInt64());
}

Read the full file on GitHub · 137 lines

Changes

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.

  1. 8d ago First seen · 137 lines · 154 tokens per session scan A bcef4be6d456

Subscribe to this mod's changes

agui-dotnet-unit-tests is a skill published in the GitHub repository ag-ui-protocol/ag-ui (15,752 stars, last pushed yesterday), licensed MIT. It adds 154 tokens to every session and 1,550 once invoked, about $0.0008 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.