a2ui-catalog

a2ui-catalog is a skill for Claude Code, Codex from a2uicatalog/a2ui. It costs 111 tokens per session (942 once invoked), scanned A, original, MIT.

A guide for choosing interface building blocks from the A2UI Atomic Catalog, a library of typed UI components such as charts, gauges, dashboards, and steppers. It also explains the exact fields each component accepts.

In plain words
What is it for?
Use it when planning an A2UI interface, searching the catalog for a suitable component, or checking a component's required data before composing a UI payload.
Why use it?
It prevents choosing the wrong component or using field names that the renderer does not accept. This reduces failed or invalid UI payloads.

Skill for Claude CodeCodex

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

Install

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.

agentmods
npx agentmods add skills/a2uicatalog/a2ui/a2ui-catalog
Any agent
npx skills add a2uicatalog/a2ui --skill a2ui-catalog
Clone the repo
git clone --depth 1 https://github.com/a2uicatalog/a2ui

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 a2ui-catalog

README.md
[![agentmods](https://agentmods.dev/badge/skills/a2uicatalog/a2ui/a2ui-catalog.svg)](https://agentmods.dev/skills/a2uicatalog/a2ui/a2ui-catalog)
Your own site
<a href="https://agentmods.dev/skills/a2uicatalog/a2ui/a2ui-catalog"><img src="https://agentmods.dev/badge/skills/a2uicatalog/a2ui/a2ui-catalog.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00111 $0.00942
Opus 5 $0.00056 $0.00471
Sonnet 5 $0.00022 $0.00188
Haiku 4.5 $0.00011 $0.00094

Measured 6d ago against content hash 25ee2214a628, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

a2ui-catalog 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.

skills/a2ui-catalog/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Picking A2UI atoms

The catalog is deliberately not loaded all at once: 480 atoms is too much context for most tasks, and the wrong field name is a validation error, not a broken render — so this skill is about narrowing down to the right slice and reading its real contract, not guessing.

1. Narrow to a catalog slice

list_catalogs (MCP tool) or GET /catalogue/index.json (REST) returns every catalog with a one-line when-to-use, e.g. a2ui-atoms-v1 (the base vocabulary, always resolved), a2ui-learning-v1 (quizzes, flashcards, course UI), state/data-source extension catalogs. Pick the slice the task actually needs — do not pull the whole vocabulary into context for a one-chart request.

2. Read the real field contract

get_catalog(catalog) returns that slice's atoms with type + a one-line description — enough to confirm an atom EXISTS and roughly what it does, not enough to fill it in.

Before authoring any atom you haven't used before, call get_atom_schema(types) (MCP) or fetch /catalogue/atoms-json-schema.json (REST, strict per-atom JSON Schema — also useful as a response_format/grammar constraint so a model literally cannot emit an invalid atom). This is the step that prevents the single most common failure: guessing a prop name that doesn't exist, which either renders empty or gets silently normalised away.

required_catalogs(payload) is the reverse lookup — given a payload you already have, it returns exactly which catalog URIs it needs, deterministically (pure function of the atoms used, not a guess).

3. Common mistakes this skill exists to prevent

  • Inventing a generic block type. There is no text or button atom. Every block names a real, typed atom from the vocabulary — check get_catalog first.
  • Guessing a field name instead of calling get_atom_schema. An unrecognised or malformed field doesn't error loudly; it's caught and the block renders as a visible "unknown atom" notice, or the field is just dropped. Silent-wrong is worse than a hard error, so don't skip this step.
  • Loading the full 480-atom vocabulary for a small task. Pick the catalog slice via list_catalogs first; it costs nothing and keeps the working context small.
  • Assuming every atom renders everywhere. Per-surface support (web, Google Meet stage, Apps Script, Google Chat, MCP Apps, email, PDF) is declared PER ATOM. An atom that can't work on a target surface says so rather than degrading silently — check works_on / degraded_on / incompatible_on in the catalog entry before assuming portability.

Read the full file on GitHub · 72 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. 6d ago First seen · 72 lines · 111 tokens per session scan A 25ee2214a628

Subscribe to this mod's changes

a2ui-catalog is a skill published in the GitHub repository a2uicatalog/a2ui (3 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 942 once invoked, about $0.0006 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.

Related

Other skills, from other repositories