openui-blocks

openui-blocks is a skill for Claude Code, Codex from poco-ai/Agentero. It costs 58 tokens per session (761 once invoked), scanned A, original, MIT.

A format for adding small, read-only visual blocks to chat replies. OpenUI Lang can describe cards, figures, tables, charts, outlines, lists, steps, and callouts using approved components and document references.

In plain words
What is it for?
Use it when a paper-like card, table, chart, figure reference, or step list would help explain an answer. It is not for forms, buttons, or stateful widgets.
Why use it?
It can present compact structured information more clearly than prose while avoiding interactive controls or hidden actions.

Skill for Claude CodeCodex

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

Good fit Use it when a paper-like card, table, chart, figure reference, or step list would help explain an answer. It is not for forms, buttons, or stateful widgets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/poco-ai/agentero/openui-blocks
About the project

Agentero is a local research workspace that connects papers, structured reading material, Markdown notes, and AI agents in one place. Researchers use it to read and annotate PDFs, extract formulas and figures, organize literature, and collaborate with agents on research tasks while keeping context locally. Its catalogue skills and instruction support agent-assisted research workflows in Agentero.

poco-ai/Agentero · 2,442 stars · on GitHub · agentero.app

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.

Any agent
npx skills add poco-ai/Agentero --skill openui-blocks
Clone the repo
git clone --depth 1 https://github.com/poco-ai/Agentero

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 openui-blocks

README.md
[![agentmods](https://agentmods.dev/badge/skills/poco-ai/agentero/openui-blocks/github.svg)](https://agentmods.dev/skills/poco-ai/agentero/openui-blocks)
Your own site
<a href="https://agentmods.dev/skills/poco-ai/agentero/openui-blocks"><img src="https://agentmods.dev/badge/skills/poco-ai/agentero/openui-blocks/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.

agentmods 80×15 button for openui-blocks

Your own site · 80×15
<a href="https://agentmods.dev/skills/poco-ai/agentero/openui-blocks"><img src="https://agentmods.dev/badge/skills/poco-ai/agentero/openui-blocks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 761 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00058 $0.00761
Opus 5.5 $0.00023 $0.00304
Sonnet 5.5 $0.00012 $0.00152
Haiku 4.5 $0.00006 $0.00076

Measured 3d ago against content hash 611926d361c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openui-blocks 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 3d 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.

scripts/templates/openui-blocks.SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenUI Blocks

Reply with at most one fenced openui-lang block when a compact visual answer clearly helps. Keep the normal prose answer outside the fence. Prefer Markdown when it is enough, especially for a single table.

Rules

  • Fence info string: openui-lang. The root must be root = Stack([...]).
  • Arguments are positional; strings use double quotes; arrays use [...].
  • Use only the components listed below. Do not invent props or components.
  • source / path must be a Vault-relative file path or citation target: papers/<id>/<id>.pdf#page=<N>, #figure=<N>, #formula=<N>, #section=<x.y> (numbers are placeholders; only use anchors that exist). Numbered equations use #formula=N, never #equation=. Never put a human-readable label such as "Table 3, Section 4.2" there; use label, caption or detail for display text. Unrecognized targets stay as text.
  • Never invent a numbered PDF anchor. #figure=N, #table=N, #formula=N, #algorithm=N and #section=... must exist in the paper's layout: check agentero layout list <paper> --kind <kind> --json, or read {paper}/source/layout-index.json when the CLI is unavailable. Formulas may also live as \tag{N} in {paper}/source/layout.json. Only a matching numbered id, title/caption, or \tag{N} counts; an unnumbered region of that kind is not a citation. If the number is not there, use a verified #page=N or omit source; a PDF existing is not the same as the anchor existing.
  • Outline section level is 1-based (1 = top, 2 = subsection); Tree depth is 0-based. Never use level: 0.
  • Read-only v1: no state, bindings, queries, mutations, actions, HTML, scripts, or nested code fences.
  • Keep data small: at most 8 table columns / 60 rows, 24 chart points, 12 steps, 40 list items, 20 timeline items, 60 tree items, 20 tags or sources.
  • If the app rejects the block, it shows the source and a short reason. Fall back to Markdown rather than retrying the same invalid program.
  • One block per reply. Do not put a block inside a sentence.

Read the full file on GitHub · 61 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. 3d ago Changed · +12 lines 611926d361c3
  2. 4d ago First seen · 49 lines · 58 tokens per session scan A b1d19d05759b

Subscribe to this mod's changes

openui-blocks is a skill published in the GitHub repository poco-ai/Agentero (2,442 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 761 once invoked, about $0.0002 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 2026-11-08.

Related

openui-blocks compared with skills from other repositories

openui-blocks next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
openui-blockspoco-ai/AgenteroSkill2.4ktodayMITA58Claude Code, Codex
research-idea-generatorfindscripter/everything-skillsSkill11todaynoneA119Claude Code
prosebeita6969/ScienceClawSkill1.0k3d agoMITA36Claude Code, Codex
academic-literature-searchbeita6969/ScienceClawSkill1.0k3d agoMITA4Claude Code, Codex
data-viz-plotsbeita6969/ScienceClawSkill1.0k3d agoMITA34Claude Code, Codex
arxiv-databasebeita6969/ScienceClawSkill1.0k3d agoMITA63Claude Code, Codex
knowledge-synthesisbeita6969/ScienceClawSkill1.0k3d agoMITA7Claude Code, Codex