ag-ui: Skill for Claude Code

.github/skills/agui-dojo/SKILL.md

agui-dojo is a skill for Claude Code, Codex from ag-ui-protocol/ag-ui. It costs 142 tokens per session (1,855 once invoked), scanned A, original, MIT.

A guide for running the AG-UI Dojo, a local demo website that showcases how AI-agent interfaces work, together with its .NET integration. It describes the frontend, backend, agent registry, configuration, and end-to-end tests.

In plain words
What is it for?
Use it to start the Dojo frontend and .NET backend, register or change the AG-UI .NET demo integration, update its feature menu or configuration, and run browser end-to-end tests.
Why use it?
It removes the setup and wiring work needed to see AG-UI .NET features in the demo viewer. Developers can find the relevant files, service addresses, and test commands in one place.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node apps/dojo/scripts/prep-dojo-everything.js --only dojo,ag-ui-dotnet.

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-dojo/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-dojo

README.md
[![agentmods](https://agentmods.dev/badge/skills/ag-ui-protocol/ag-ui/agui-dojo.svg)](https://agentmods.dev/skills/ag-ui-protocol/ag-ui/agui-dojo)
Your own site
<a href="https://agentmods.dev/skills/ag-ui-protocol/ag-ui/agui-dojo"><img src="https://agentmods.dev/badge/skills/ag-ui-protocol/ag-ui/agui-dojo.svg" alt="Measured on agentmods" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,855 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 $0.00142 $0.01855
Opus 5 $0.00071 $0.00928
Sonnet 5 $0.00028 $0.00371
Haiku 4.5 $0.00014 $0.00186

Measured 8d ago against content hash 053600902b59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agui-dojo 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-dojo/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AG-UI Dojo (.NET integration)

The Dojo is a Next.js "demo viewer" (apps/dojo) that showcases AG-UI protocol features (agentic chat, generative UI, human-in-the-loop, shared state, etc.) against many framework integrations. The AG-UI .NET SDK is one integration, id ag-ui-dotnet.

Where the pieces live

Piece Path Role
Dojo app (frontend) apps/dojo Next.js viewer, runs on port 9999
.NET backend sdks/dotnet/samples/AGUIClientServer/AGUIDojoServer/ ASP.NET host exposing AG-UI endpoints, port 8023
Agent registry apps/dojo/src/agents.ts ag-ui-dotnetHttpAgent per feature
Menu / feature list apps/dojo/src/menu.ts integration id, name, enabled features
Env config apps/dojo/src/env.ts aguiDotnetUrlAGUI_DOTNET_URL (default http://localhost:8023)
Generated source viewer data apps/dojo/src/files.json generated, committed
Content generator apps/dojo/scripts/generate-content-json.ts builds files.json from menu.ts
Prep / run orchestrators apps/dojo/scripts/{prep,run}-dojo-everything.js install/build + start services
.NET e2e suite apps/dojo/e2e/tests/agUiDotnetTests/*.spec.ts Playwright tests
CI .github/workflows/dojo-e2e.yml suite ag-ui-dotnet (triggers on sdks/dotnet/**)

Run the dojo + .NET backend locally

From the repo root (the scripts shell out to git rev-parse):

pnpm install --no-frozen-lockfile

# 1) Prep: builds the .NET backend AND the dojo (use the stable ids)
node apps/dojo/scripts/prep-dojo-everything.js --only dojo,ag-ui-dotnet

# 2) Run: starts the dojo (9999) + AGUIDojoServer (8023) together, with LLMock env injected
node apps/dojo/scripts/run-dojo-everything.js --only dojo,ag-ui-dotnet
  • Browse http://localhost:9999/ag-ui-dotnet/feature/agentic_chat.
  • prep for ag-ui-dotnet runs dotnet restore && dotnet build on AGUIDojoServer/AGUIDojoServer.csproj in sdks/dotnet/samples/AGUIClientServer.
  • run for ag-ui-dotnet runs dotnet run --project AGUIDojoServer/AGUIDojoServer.csproj --urls "http://localhost:8023" --no-buildprep first or there's no build to run.

Read the full file on GitHub · 120 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 · 120 lines · 142 tokens per session scan A 053600902b59

Subscribe to this mod's changes

agui-dojo is a skill published in the GitHub repository ag-ui-protocol/ag-ui (15,752 stars, last pushed yesterday), licensed MIT. It adds 142 tokens to every session and 1,855 once invoked, about $0.0007 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.