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/delexw/claude-code-misc/inktuinpx skills add delexw/claude-code-misc --skill inktuigit clone --depth 1 https://github.com/delexw/claude-code-miscWrote 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/delexw/claude-code-misc/inktui)<a href="https://agentmods.dev/skills/delexw/claude-code-misc/inktui"><img src="https://agentmods.dev/badge/skills/delexw/claude-code-misc/inktui.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 | $0.00161 | $0.01473 |
| Opus 5 | $0.00081 | $0.00737 |
| Sonnet 5 | $0.00032 | $0.00295 |
| Haiku 4.5 | $0.00016 | $0.00147 |
Grade A, and why
inktui 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ink — React for CLIs
Ink is a React renderer for terminal applications. It uses Yoga (flexbox) for layout and renders to stdout. Every element is a flex container — think <div style="display: flex"> for the terminal.
Quick Start
# Scaffold a new project
npx create-ink-app my-cli # JavaScript
npx create-ink-app --typescript my-cli # TypeScript
Or add to an existing project:
npm install ink react
npm install @inkjs/ui # Optional: pre-built UI components
Core Architecture
Ink apps are React component trees rendered via render(). The process stays alive while there's work in the event loop. Exit via Ctrl+C, useApp().exit(), or instance.unmount().
import React, {useState} from 'react';
import {render, Text, Box} from 'ink';
function App() {
const [count, setCount] = useState(0);
return (
<Box flexDirection="column">
<Text>Count: {count}</Text>
<Text color="green">Press q to quit</Text>
</Box>
);
}
render(<App />);
Reference Files
Read these for detailed API documentation and examples:
- references/components.md — All Ink core components (
Box,Text,Newline,Spacer,Static,Transform) with full props - references/hooks.md — All hooks (
useInput,useApp,useFocus,useFocusManager,useStdin,useStdout,useStderr,useWindowSize,useBoxMetrics,useCursor,usePaste) - references/ink-ui.md — All
@inkjs/uicomponents (TextInput,Select,MultiSelect,Spinner,ProgressBar,Alert,Badge,StatusMessage,ConfirmInput,EmailInput,PasswordInput,OrderedList,UnorderedList) with props and theming - references/patterns.md — Common patterns: multi-step wizards, loading states, tables, command routing, testing, fullscreen apps, and real-world examples
Key Concepts
Layout is Flexbox
Every element is a flex container. Use <Box> for layout with standard flex props: flexDirection, justifyContent, alignItems, gap, padding, margin, etc. Percentage widths/heights are supported.
What ships with it
4 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.
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.
- 3d ago First seen · 150 lines · 161 tokens per session scan A 727dd591041b
inktui is a skill published in the GitHub repository delexw/claude-code-misc (1 stars, last pushed 5mo ago), licensed MIT. It adds 161 tokens to every session and 1,473 once invoked, about $0.0008 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
accesslint-audit
Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers di.
intlayer-react
Integrates Intlayer internationalization with React component. Use when the user asks to "setup React i18n", create a new translated component, use the "useIntlayer" hook, or configure providers.
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
当用户需要对PDF文件进行任何操作时,请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片,以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF,请使用此技能。.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
current-slide
Resolve which slide, page, and (optionally) selected element the user is currently viewing in the open-slide dev server. Consult this whenever the user references "this page", "this slide", "this element", "the slide I'm on", "the current page", or any deictic reference to slide content without naming it. Re-read…