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/ant-design/ant-design-cli/antdnpx skills add ant-design/ant-design-cli --skill antdgit clone --depth 1 https://github.com/ant-design/ant-design-cliWhat 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 | $0.00069 | $0.02448 |
| Opus 5 | $0.00034 | $0.01224 |
| Sonnet 5 | $0.00014 | $0.00490 |
| Haiku 4.5 | $0.00007 | $0.00245 |
Grade A, and why
antd 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ant Design CLI
You have access to @ant-design/cli — a local CLI tool with bundled antd metadata for v4/v5/v6 (plus migration guides for v3 → v4, v4 → v5, v5 → v6). Use it to query component knowledge, analyze projects, and guide migrations. All data is offline, no network needed.
Setup
Before first use, check if the CLI is installed. If not, install it automatically:
which antd || npm install -g @ant-design/cli
After running any command, if the output contains an "Update available" notice, run antd upgrade to update before continuing.
Always use --format json for structured output you can parse programmatically.
Scenarios
1. Writing antd component code
Before writing any antd component code, look up its API first — don't rely on memory.
# Check what props are available
antd info Button --format json
# Get a working demo as starting point
antd demo Button basic --format json
# Check semantic classNames/styles for custom styling
antd semantic Button --format json
# Check component-level design tokens for theming
antd token Button --format json
# Get the overall design language (design.md): colors, typography, spacing, radius + principles
antd design.md --format json
Workflow: antd info → understand props → antd demo → grab a working example → write code.
2. Looking up full documentation
When you need comprehensive component docs (not just props):
antd doc Table --format json # full markdown docs for Table
antd doc Table --lang zh # Chinese docs
3. Debugging antd issues
When code isn't working as expected or the user reports an antd bug:
# Collect full environment snapshot (system, deps, browsers, build tools)
antd env --format json
# Check if the prop exists for the user's antd version
antd info Select --version 5.12.0 --format json
# Check if the prop is deprecated
antd lint ./src/components/MyForm.tsx --format json
# Diagnose project-level configuration issues
antd doctor --format json
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 · 275 lines · 69 tokens per session scan A 5df4da1f4cf4
antd is a skill published in the GitHub repository ant-design/ant-design-cli (252 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 2,448 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 2026-08-30.
Other skills, from other repositories
antd
Ant Design enterprise React UI component library reference. Covers 50+ components, Table with sorting/filtering/pagination, Form with validation and dynamic fields, theming with design tokens, dark mode, and v5 CSS-in-JS customization.
component-refactoring
Refactor high-complexity React components in Dify frontend. Use when pnpm analyze-component --json shows complexity > 50 or lineCount > 300, when the user asks for code splitting, hook extraction, or complexity reduction, or when pnpm analyze-component warns to refactor before testing; avoid for simple/well-structured…
frontend-testing
Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. Triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests.
pro-upgrade
Use when the user wants to upgrade their Ant Design Pro project to the latest version. Triggers on: upgrade pro, pro upgrade, migrate pro, update pro, 升级, 迁移项目, "how to upgrade", "update to latest", "keep project up to date".
senior-frontend
Comprehensive frontend development skill for building modern, performant web applications using ReactJS, NextJS, TypeScript, Tailwind CSS. Includes component scaffolding, performance optimization, bundle analysis, and UI best practices. Use when developing frontend features, optimizing performance, implementing UI/UX…
frontend-code-review
Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.