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 skills add kumaran-is/claude-code-onboarding --skill a2ui-angulargit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/kumaran-is/claude-code-onboarding/a2ui-angular)<a href="https://agentmods.dev/skills/kumaran-is/claude-code-onboarding/a2ui-angular"><img src="https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/a2ui-angular/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kumaran-is/claude-code-onboarding/a2ui-angular"><img src="https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/a2ui-angular.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00068 | $0.02131 |
| Opus 5.5 | $0.00027 | $0.00852 |
| Sonnet 5.5 | $0.00014 | $0.00426 |
| Haiku 4.5 | $0.00007 | $0.00213 |
Grade A, and why
a2ui-angular 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 2mo 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A2UI Angular Renderer Development Skill
Tech Stack: Angular 21+, A2UI Protocol v0.8+, TailwindCSS 4.x, daisyUI 5.5.5
What is A2UI?
A2UI (Agent-to-User Interface) is a declarative protocol by Google that lets AI agents describe rich, interactive UIs as structured JSON data instead of generating executable code. The agent sends a JSON blueprint; the client app renders it using its own native components.
Key principle: UI-as-data, not UI-as-code. Agents never generate HTML/JS — they describe intent via a flat component adjacency list. The client validates against an approved component catalog and renders with native framework components.
Iron Law
A2UI PAYLOADS ARE UNTRUSTED. VALIDATE COMPONENT TYPES AGAINST THE CATALOG ALLOWLIST BEFORE RENDERING. NEVER EXECUTE AGENT-PROVIDED CODE.
Every component from an agent must be validated against the client's approved catalog. Rendering any component type the agent sends, or executing agent-provided scripts, exposes the application to XSS, code injection, and data theft. The catalog allowlist is the security boundary.
Conventions & Structure
For Angular coding conventions, read the
angular-spaskill'sreference/angular-conventions.mdFor A2UI-specific patterns, readreference/a2ui-protocol.md
Documentation Sources
| Source | URL / Tool | Purpose |
|---|---|---|
| A2UI Spec | https://a2ui.org/ |
Protocol specification, component format |
| A2UI GitHub | https://github.com/google/A2UI |
Reference implementations, samples |
| A2A Extension | https://a2ui.org/a2a-extension/a2ui/v0.8 |
A2A protocol integration (Python ADK) |
| A2UI Composer | https://a2ui.org/composer/ |
Visual widget builder — prototype before wiring |
| @a2ui/angular | npm install @a2ui/angular |
Official Angular renderer SDK |
| Angular v21 | angular-cli MCP |
Workspace-aware help, schematics |
| daisyUI v5 | https://daisyui.com/llms.txt |
Component reference for rendering |
| TailwindCSS | Context7 MCP |
Utility classes for layout |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/a2ui-chat-template.md 7.1 KB
- reference/a2ui-client-integration.md 7.5 KB
- reference/a2ui-component-catalog.md 6.8 KB
- reference/a2ui-component-containers.md 5.1 KB
- reference/a2ui-functions.md 7.0 KB
- reference/a2ui-production-architecture.md 7.9 KB
- reference/a2ui-protocol-advanced.md 12 KB
- reference/a2ui-protocol.md 13 KB
- reference/a2ui-renderer-patterns.md 8.9 KB
- reference/a2ui-renderer-services.md 10 KB
- reference/a2ui-renderer-template.md 8.0 KB
- reference/a2ui-security.md 10 KB
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.
- 2mo ago First seen · 166 lines · 68 tokens per session scan A 314385d236d5
a2ui-angular is a skill published in the GitHub repository kumaran-is/claude-code-onboarding (36 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 2,131 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…