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/a2uicatalog/a2ui/a2ui-catalognpx skills add a2uicatalog/a2ui --skill a2ui-cataloggit clone --depth 1 https://github.com/a2uicatalog/a2uiWrote 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/a2uicatalog/a2ui/a2ui-catalog)<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>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 | $0.00111 | $0.00942 |
| Opus 5 | $0.00056 | $0.00471 |
| Sonnet 5 | $0.00022 | $0.00188 |
| Haiku 4.5 | $0.00011 | $0.00094 |
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.
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
textorbuttonatom. Every block names a real, typed atom from the vocabulary — checkget_catalogfirst. - 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_catalogsfirst; 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_onin the catalog entry before assuming portability.
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.
- 6d ago First seen · 72 lines · 111 tokens per session scan A 25ee2214a628
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.
Other skills, from other repositories
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
wukongim-cloud-analysis
Diagnose one exact live WuKongIM cloud Simulation Run or chat-lifecycle Cloud Lease through the repository Analysis MCP. Use when the user or a local Analysis Session asks Codex to inspect a run's cluster state, Prometheus signals, application logs, diagnostics, Controller task audits, profiles, or redacted config…
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.