agentmods.dev

tui

tui is a skill for Claude Code from MadAppGang/magus. It costs 52 tokens per session (5,199 once invoked), scanned A, original, MIT.

A toolkit for building and checking colourful terminal user interfaces with OpenTUI, using Bun and TypeScript. It supports React-style JSX or OpenTUI's core building blocks, plus Yoga for arranging screen elements.

In plain words
What is it for?
Use it to build, review or debug Bun/TypeScript terminal apps with dense dashboards, graphs, badges, colour meters and other visual elements.
Why use it?
It helps avoid plain, hard-to-read terminal output and catches visual problems by building a colour screenshot for review. It also provides guidance for choosing meters, charts, sparklines and other compact displays.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the bunjs plugin — 9 skills, 9 commands shipped together

not rated 9repo changed today A scan 52 tokens original MIT

Good fit Use it to build, review or debug Bun/TypeScript terminal apps with dense dashboards, graphs, badges, colour meters and other visual elements.

Compare 6 skills from other repositories ↓
View source ↗ MadAppGang/magus
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add MadAppGang/magus
Claude Code
/plugin install bunjs

Made for: Claude Code.

Or install bunjs, the plugin that ships this one along with the rest of its 9 skills, 9 commands.

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 tui

README.md
[![agentmods](https://agentmods.dev/badge/skills/madappgang/magus/tui.svg)](https://agentmods.dev/skills/madappgang/magus/tui)
Your own site
<a href="https://agentmods.dev/skills/madappgang/magus/tui"><img src="https://agentmods.dev/badge/skills/madappgang/magus/tui.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,199 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 $0.00052 $0.05199
Opus 5 $0.00026 $0.02599
Sonnet 5 $0.00010 $0.01040
Haiku 4.5 $0.00005 $0.00520

Measured today against content hash 2eb3fdfd8a2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tui 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 today.

The scan reads SKILL.md. This mod also ships 10 executable files (assets/runtime/opentui-env.d.ts, assets/runtime/shutdown.test.ts, assets/runtime/shutdown.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/bunjs/skills/tui/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenTUI TUI

Build Bun/TypeScript terminal UIs that look like btop, gonzo, posting and lazygit — colourful, dense, graph-and-badge-heavy — not like cat output. OpenTUI hands you a real layout engine (Yoga flexbox) and a React renderer, and no meter, chart, badge or colour maths, so under-baked is the default outcome — which the contract below and the shipped assets/ prevent. You cannot judge a look from source: build → screenshot in colour → look → fix.

The aesthetic this skill is for

The bar is more colour, more graphs, less text; the failure mode is not ugliness but under-baking — printing CPU 78% where the row could carry a meter, a percentage and a sparkline. Reach for the rich form mechanically.

You have… Default to… Not…
a bounded value (a percentage — pct is 0–100, never 0–1) a gradient meter — one colour per cell across the fill a bare number, or a flat one-colour bar
a time series / recent history a sparkline (▁▂▃▄▅▆▇█) the latest number alone
a category distribution a bar chart or stacked bar, coloured per category a list of name: count lines
counts over time × category a heat row per category, brightness = magnitude a table of numbers
a discrete status / level / method a badge — dark ink on a saturated fill plain coloured text alone
genuine free narrative (logs, detail) text — and only inside a log or detail panel text as the main surface

Three rules keep it from tipping into noise. Colour is semantic, never decorative — one colour means one thing app-wide; red as "error" here and "selected" there kills glanceability. Make gradients smooth — one blended colour per column at the widget's real width, never four ░▒▓█ glyphs sharing one. Dim the chrome, saturate the signal.

Negative control: if your first screenshot shows a single-colour bar or bare numbers, you failed — as is a non-log panel over about half prose or numerals. Then run that count a second time over the WHOLE frame, not per panel (graphics body rows vs text rows across the capture): every panel can pass the table while the screen still reads as prose — one build's first wide capture was 28 of 38 rows text, every panel compliant. Under half, add a graphics panel.

Read the full file on GitHub · 208 lines

Files

What ships with it

60 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.

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. today Changed · +1 lines 2eb3fdfd8a2e
  2. 8d ago First seen · 207 lines · 52 tokens per session scan A 6acc0f325808

Subscribe to this mod's changes

tui is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 5,199 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.

Frontend
Related

Other skills, from other repositories

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 50 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

prototype-web

A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.

nexu-io/html-anything · 24 tokens

menu-transitions-rtl

Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…

asmyshlyaev177/react-horizontal-scrolling-menu · 137 tokens