pro-upgrade

pro-upgrade is a skill for Claude Code from ant-design/ant-design-pro. It costs 63 tokens per session (1,573 once invoked), scanned C, original, MIT.

An upgrade guide for projects built with Ant Design Pro, a React-based application template for business software. It compares the project with the latest official template and merges framework updates while preserving application code.

In plain words
What is it for?
Use it to check project changes, fetch the latest template, separate framework files from business files, and merge an upgrade safely.
Why use it?
It gives a defined process for updating an older Pro project without accidentally replacing the code written for the specific application.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to check project changes, fetch the latest template, separate framework files from business files, and merge an upgrade safely.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ant-design/ant-design-pro/pro-upgrade
About the project

Ant Design Pro is a React boilerplate for building enterprise applications with Ant Design, providing reusable page blocks and common application templates. Developers use it as a starting point for admin panels, dashboards, and other business software. Catalogue entries provide instructions and skills for working with the project.

ant-design/ant-design-pro · 38,753 stars · on GitHub · pro.ant.design

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 ant-design/ant-design-pro --skill pro-upgrade
Clone the repo
git clone --depth 1 https://github.com/ant-design/ant-design-pro

Made for: Claude Code.

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 pro-upgrade

README.md
[![agentmods](https://agentmods.dev/badge/skills/ant-design/ant-design-pro/pro-upgrade/github.svg)](https://agentmods.dev/skills/ant-design/ant-design-pro/pro-upgrade)
Your own site
<a href="https://agentmods.dev/skills/ant-design/ant-design-pro/pro-upgrade"><img src="https://agentmods.dev/badge/skills/ant-design/ant-design-pro/pro-upgrade/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 pro-upgrade

Your own site · 80×15
<a href="https://agentmods.dev/skills/ant-design/ant-design-pro/pro-upgrade"><img src="https://agentmods.dev/badge/skills/ant-design/ant-design-pro/pro-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,573 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 12 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 15
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 39
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 144
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 15
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 15
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 39
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 144
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium MCP Rug Pull · line 14
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 114
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 115
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 121
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 137
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00063 $0.01573
Opus 5 $0.00032 $0.00787
Sonnet 5 $0.00013 $0.00315
Haiku 4.5 $0.00006 $0.00157

Measured 9d ago against content hash 569bd8d8539c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

pro-upgrade scanned grade C with 1 finding 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 9d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Bash(rm -rf /tmp/ant-design-pro-upgrade*)
.claude/skills/pro-upgrade/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ant Design Pro Upgrade Skill

You are an Ant Design Pro upgrade assistant. Your task is to help users upgrade their Pro-based project to the latest version by comparing it against the official template and intelligently merging changes.

Preflight

Before starting, confirm:

  1. The user has committed or stashed all changes (git status should be clean or they confirm it's OK to proceed).
  2. If not clean, remind them to commit or stash their changes first (e.g., "Please commit or stash your changes — the upgrade process will modify multiple files.") and wait for them to confirm.

Upgrade Flow

Step 1 — Fetch the latest template

rm -rf /tmp/ant-design-pro-upgrade
git clone --depth=1 https://github.com/ant-design/ant-design-pro.git /tmp/ant-design-pro-upgrade

Read the template's package.json to confirm its version.

Step 2 — Classify files

Separate the user's project files into framework files (Pro-owned, rarely customized) and business files (user-written, must be preserved).

Framework files — diff these against the template:

Path Notes
package.json dependencies, scripts, devDependencies only
config/config.ts framework config
config/routes.ts structure only — preserve user-added routes
config/defaultSettings.ts layout/theme defaults
config/proxy.ts structure only — preserve user targets
src/app.tsx runtime config
src/access.ts permission definitions
src/global.tsx global side effects
src/loading.tsx loading component
src/requestErrorConfig.ts request interceptor
src/typings.d.ts global type declarations
tsconfig.json TypeScript config
biome.json or biome.jsonc linter config
.husky/ git hooks
commitlint.config.* commit lint config
src/services/ant-design-pro/ auto-generated — do NOT manually edit; regenerate with npm run openapi

Business files — preserve these, only adjust imports/APIs if needed:

Read the full file on GitHub · 166 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. 9d ago First seen · 166 lines · 63 tokens per session scan C 569bd8d8539c

Subscribe to this mod's changes

pro-upgrade is a skill published in the GitHub repository ant-design/ant-design-pro (38,753 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 1,573 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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.

bytesagain/ai-skills · 50 tokens

owl-admin-frontend-assets

A development guide for the browser-side files and published assets used by Owl Admin, a Laravel-based administration system. It covers admin views, themes, layouts, React work, and asset publishing.

slowlyo/owl-admin · 80 tokens

antd

Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or analyzing antd usage in a project. Triggers on antd-related code, imports from 'antd', or explicit antd questions.

ant-design/ant-design-cli · 69 tokens

frontend-technical-spec

Defines React environment, component architecture, state/data flow, build verification, and frontend non-functional criteria from repository evidence. Use when configuring or designing a React frontend, its build, or its runtime boundaries.

shinpr/ai-coding-project-boilerplate · 45 tokens

frontend-typescript-rules

Applies React/TypeScript type safety, component design, and state management rules. Use when implementing React components.

shinpr/ai-coding-project-boilerplate · 29 tokens

next-upgrade

Upgrade Next.js to the latest version following official migration guides and codemods.

agustinusnathaniel/nextarter-tailwind · 19 tokens