Borrowing it
Nothing to install: this file belongs to antdigital-ai/agentic-ui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/antdigital-ai/agentic-ui/main/.cursor/skills/agentic-ui-usage/SKILL.mdgit clone --depth 1 https://github.com/antdigital-ai/agentic-uiWrote 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/antdigital-ai/agentic-ui/agentic-ui-usage)<a href="https://agentmods.dev/skills/antdigital-ai/agentic-ui/agentic-ui-usage"><img src="https://agentmods.dev/badge/skills/antdigital-ai/agentic-ui/agentic-ui-usage/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.
<a href="https://agentmods.dev/skills/antdigital-ai/agentic-ui/agentic-ui-usage"><img src="https://agentmods.dev/badge/skills/antdigital-ai/agentic-ui/agentic-ui-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.01083 |
| Opus 5.5 | $0.00039 | $0.00433 |
| Sonnet 5.5 | $0.00019 | $0.00217 |
| Haiku 4.5 | $0.00010 | $0.00108 |
Grade A, and why
agentic-ui-usage 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 2mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic UI 组件库使用指南
面向在业务项目中使用 @ant-design/agentic-ui 的开发者:安装、引入、常见场景与 API 查阅方式。
安装与依赖
pnpm add @ant-design/agentic-ui
# 或 npm / yarn
- Peer:
react、react-dom>= 16.9.0(项目需已安装)。 - 运行时依赖:包内已含
antd、@ant-design/cssinjs等,无需单独安装。 - 使用前确保项目已正确引入 Ant Design 样式或 CSS-in-JS 方案(与 antd 5 一致)。
引入方式
// 按需引入常用组件
import {
AgenticLayout,
ChatLayout,
History,
Workspace,
Bubble,
AIBubble,
UserBubble,
MarkdownInputField,
MarkdownEditor,
ThoughtChainList,
ToolUseBar,
TaskList,
AgentRunBar,
WelcomeMessage,
ChatBootPage,
} from '@ant-design/agentic-ui';
// 类型
import type { HistoryItemProps, BubbleListProps } from '@ant-design/agentic-ui';
- 组件与类型均从
@ant-design/agentic-ui单入口导出,无需从子路径导入。 - 若打包器支持 Tree Shaking,未用到的组件会被剔除。
典型使用场景
1. 智能体聊天整体布局
左栏历史 + 中间聊天 + 右侧工作区:
<AgenticLayout
left={<History dataSource={sessions} onSelect={...} />}
center={
<ChatLayout
header={...}
content={<Bubble.List messages={messages} />}
footer={<MarkdownInputField onSubmit={...} />}
/>
}
right={<Workspace tabs={[...]} />}
header={{ leftCollapsed, rightCollapsed, onLeftCollapse, onRightCollapse }}
/>
2. 仅聊天区域(无三栏)
<ChatLayout
content={<Bubble.List messages={messages} />}
footer={<MarkdownInputField onSubmit={...} />}
/>
3. 消息列表与气泡
- 使用
Bubble.List+AIBubble/UserBubble或直接传入messages与渲染约定。 - 流式、思维链、工具调用等由气泡与 ThoughtChainList、ToolUseBar 等配合展示。
4. 编辑器与输入
- 只读/展示:
MarkdownEditor只读模式或直接渲染 Markdown。 - 可编辑:
MarkdownEditor受控 +value/onChange。 - 输入框:
MarkdownInputField支持附件、语音、发送等,通过onSubmit等回调与后端对接。
5. 国际化
- 通过 Ant Design 的
ConfigProvider传入locale,与 antd 一致。 - 组件库内置中英文等 locale,可合并或覆盖:
import { locale } from '@ant-design/agentic-ui'(具体以文档为准),再传给ConfigProvider。
API 与文档查阅
- 组件 API:仓库内
docs/components/下各组件文档(如agentic-layout.md、bubble.md),含 Props、受控/非受控说明。 - Demo:
docs/demos-pages/与站点 Demo 页(如 layout、chat、editor、markdown-input-field、workspace、history 等)对应实际用法。 - 类型:从
@ant-design/agentic-ui导出,用 TypeScript 时可查看.d.ts或 IDE 提示。
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.
- 2mo ago First seen · 108 lines · 97 tokens per session scan A ac6715fc1c9c
agentic-ui-usage is a skill published in the GitHub repository antdigital-ai/agentic-ui (237 stars, last pushed 24d ago), licensed MIT. It adds 97 tokens to every session and 1,083 once invoked, about $0.0004 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 2026-08-30.
agentic-ui-usage compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentic-ui-usageantdigital-ai/agentic-ui | Skill | 237 | 24d ago | MIT | A | 97 | Cursor |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| tamagui-v6-configtamagui/tamagui | Skill | 14k | today | MIT | A | 0 | Claude Code, Codex |
| tamagui-theme-generatortamagui/tamagui | Skill | 14k | today | MIT | A | 48 | Claude Code, Codex |
| frontend-ui-dark-tsmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 48 | Claude Code |
| cobejsMengTo/Skills | Skill | 7.3k | yesterday | MIT | A | 31 | Claude Code, Codex |
| vercel-composition-patternscalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 58 | Claude Code, Codex |