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/jaichangpark/workshop-harness/a2ui-workshop-buildernpx skills add JAICHANGPARK/workshop-harness --skill a2ui-workshop-buildergit clone --depth 1 https://github.com/JAICHANGPARK/workshop-harnessWrote 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/jaichangpark/workshop-harness/a2ui-workshop-builder)<a href="https://agentmods.dev/skills/jaichangpark/workshop-harness/a2ui-workshop-builder"><img src="https://agentmods.dev/badge/skills/jaichangpark/workshop-harness/a2ui-workshop-builder.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 | $0.00061 | $0.01595 |
| Opus 5 | $0.00030 | $0.00797 |
| Sonnet 5 | $0.00012 | $0.00319 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
a2ui-workshop-builder 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 5d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A2UI & Flutter GenUI Workshop Builder Skill
Purpose
Automates the creation of cutting-edge hands-on workshops focused on A2UI (Agent-to-User Interface) and Generative UI (GenUI) in Flutter. Teaches developers how to replace static, hardcoded application screens and monolithic markdown text responses with agent-driven, dynamically orchestrated native UI widgets.
Protocol & SDK Standards:
- A2UI Protocol (
a2ui.org): Open-source, framework-agnostic protocol where AI agents emit declarative JSON structures representing UI components.- Flutter GenUI SDK (
genui): Official Google Flutter framework providingWidgetCatalog,SurfaceController, andGenUISurfaceto render A2UI payloads natively.
Core GenUI & A2UI Architectural Concepts
flowchart LR
User["User Query<br>'Book a hotel in Tokyo'"] --> Agent["AI Agent (Gemini)<br>with A2UI System Prompt"]
Agent -->|"A2UI Declarative JSON Stream"| Controller["SurfaceController /<br>GenUI Orchestrator"]
Catalog["App WidgetCatalog<br>(HotelCard, DatePicker, Slider)"] --> Controller
Controller -->|"Native Widget Tree"| Screen["Dynamic Interactive Screen<br>(Rendered in Flutter)"]
Screen -->|"User Action (Button Tap)"| Agent
1. The A2UI Protocol Layer (a2ui.org)
- Agents generate structured UI specifications (e.g., component type, layout arrangement, styling tokens, and bound parameters) instead of plain text.
- Security-by-design: Agents cannot execute arbitrary JavaScript or unapproved bytecode; they can only reference components pre-registered in the client's
WidgetCatalog.
2. WidgetCatalog & Component Registration
- The developer defines a catalog of allowed Flutter widgets.
- Each widget specifies its unique ID, JSON parameter schema, and a builder callback.
3. SurfaceController & Bi-Directional Action Loop
SurfaceControllerparses the agent's incoming stream and incrementally mounts widgets on the screen.- When an attendee clicks a generated button or submits a form, an action event payload is dispatched back to the agent as a tool response or follow-up prompt.
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.
- 5d ago First seen · 161 lines · 61 tokens per session scan A 10c68f2b1497
a2ui-workshop-builder is a skill published in the GitHub repository JAICHANGPARK/workshop-harness (5 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 1,595 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).