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.
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/ag-ui-protocol/ag-ui/agui-dotnet-sample-stepnpx skills add ag-ui-protocol/ag-ui --skill agui-dotnet-sample-stepgit 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-sample-step)<a href="https://agentmods.dev/skills/ag-ui-protocol/ag-ui/agui-dotnet-sample-step"><img src="https://agentmods.dev/badge/skills/ag-ui-protocol/ag-ui/agui-dotnet-sample-step.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00168 | $0.01600 |
| Opus 5 | $0.00084 | $0.00800 |
| Sonnet 5 | $0.00034 | $0.00320 |
| Haiku 4.5 | $0.00017 | $0.00160 |
Grade A, and why
agui-dotnet-sample-step 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 6d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AG-UI .NET — Add a GettingStarted Sample Step
The samples/GettingStarted/Step01..StepNN pairs are the primary consumer-facing
deliverable: each Step is a self-contained Server + Client that demonstrates one
feature, written to look like the code we want users to write. Adding a Step is a
recurring, multi-artifact task. This skill covers the sample anatomy and wiring; it
routes the integration-test mechanics to agui-dotnet-integration-tests and the doc
sync to agui-dotnet-agents-sync.
Run all commands from sdks/dotnet/. Confirm the next free number and the current naming
by listing samples/GettingStarted/Step* first — never assume the range.
Anatomy of a Step
A Step is a folder samples/GettingStarted/StepNN_<Name>/ with two projects:
-
StepNN_<Name>.Server— an ASP.NET host (Microsoft.NET.Sdk.Web,net10.0).Program.cscallsbuilder.Services.AddAGUI(), registers anIChatClient, and ends withapp.MapAGUI("/"). TheIChatClientis the whole point: the SDK turns anyIChatClientinto an AG-UI endpoint, so the sample logic is just MEAI.- References
src/AGUI.Abstractions+samples/AGUI.Samples.Shared(the ASP.NET glue). It does not reference ansrc/server package directly. InternalsVisibleTothe integration-test project so its replay test can reach the server'sProgramand anyFakeChatClient.- Provide a deterministic
FakeChatClientfallback (fixed clocks, canned tool results) used when no real LLM is configured. Replayable determinism is what lets the integration test record once and replay forever.
- References
-
StepNN_<Name>.Client— a console app (Microsoft.NET.Sdk,OutputType Exe,net10.0).Program.csbuilds the client and hands it to a sharedSampleClient:using HttpClient httpClient = new() { BaseAddress = new Uri(baseUrl) }; var aguiClient = new AGUIChatClient(new(httpClient, baseUrl)); await SampleClient.RunAsync(aguiClient, Console.Out);
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.
- 6d ago First seen · 109 lines · 168 tokens per session scan A 8d91080bda2c
agui-dotnet-sample-step is a skill published in the GitHub repository ag-ui-protocol/ag-ui (15,739 stars, last pushed yesterday), licensed MIT. It adds 168 tokens to every session and 1,600 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.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.