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-dojo/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-dojo)<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>- 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 | $0.00142 | $0.01855 |
| Opus 5 | $0.00071 | $0.00928 |
| Sonnet 5 | $0.00028 | $0.00371 |
| Haiku 4.5 | $0.00014 | $0.00186 |
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.
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-dotnet → HttpAgent per feature |
| Menu / feature list | apps/dojo/src/menu.ts |
integration id, name, enabled features |
| Env config | apps/dojo/src/env.ts |
aguiDotnetUrl ← AGUI_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. prepforag-ui-dotnetrunsdotnet restore && dotnet buildonAGUIDojoServer/AGUIDojoServer.csprojinsdks/dotnet/samples/AGUIClientServer.runforag-ui-dotnetrunsdotnet run --project AGUIDojoServer/AGUIDojoServer.csproj --urls "http://localhost:8023" --no-build— prep first or there's no build to run.
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 · 120 lines · 142 tokens per session scan A 053600902b59
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.
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.