un-default

un-default

Enables scanning, fixing, and providing feedback on text for inclusive language, offering clearer alternatives and tunable rules.

Category
访问服务器

README

Un-Default

One thoughtful-language check for every way you build.

Formerly Anti-Default. Same tool — the name shifted so it reads as undoing defaults, not opposing people. Old URLs under darkai.ca/anti-default redirect here. npx anti-default still works as an alias for npx -y anti-default.

Un-Default reviews copy, docs, UI strings, and live pages for colonial defaults, gendered assumptions, ableist metaphors, and documented dogwhistles. It explains what it noticed and offers clearer alternatives.

No account. No AI required for matching. Open rules you can tune.

<p align="center"> <a href="https://darkai.ca/un-default/for-agents/"><strong>After Claude writes UI copy</strong></a> · <a href="https://darkai.ca/un-default"><strong>Try the web app</strong></a> · <a href="https://chromewebstore.google.com/detail/anti-default-%E2%80%94-inclusive/aajdplalleopollfjegljkajkdcihmhc"><strong>Add the Chrome extension</strong></a> · <a href="https://github.com/NomadBuilder/anti-default"><strong>Star on GitHub</strong></a> </p>


After Claude / Cursor writes UI copy

One command — skill + MCP + PR check. This is the habit that sticks:

npx -y anti-default init

Or install the Claude Code plugin from this repo’s marketplace:

claude plugin marketplace add NomadBuilder/anti-default
claude plugin install un-default@un-default

Paste-ready MCP JSON and Claude Project instructions:

https://darkai.ca/un-default/for-agents/

Directory checklist: docs/PUBLISH-DIRECTORIES.md

Paste MCP config (Cursor · Claude Desktop · Claude Code)

{
  "mcpServers": {
    "un-default": {
      "command": "npx",
      "args": ["-y", "anti-default", "mcp"]
    }
  }
}
Host Where it goes
Cursor .cursor/mcp.json (written by init) or Settings → MCP
Claude Desktop Settings → Developer → Edit Config → claude_desktop_config.json (merge, quit, relaunch)
Claude Code Plugin marketplace (above), or .mcp.json via init, or claude mcp add

Tools: un_default_scan · un_default_fix · un_default_feedback


Add it in under a minute

npx -y anti-default .

That is the whole local setup. It prints findings and exits non-zero on clear hits. Ambiguous or quoted matches stay advisory.

To pin it in a team project:

npm install --save-dev anti-default

Want the complete project setup?

npx -y anti-default init

init adds an ignore file, changed-files GitHub workflow, Cursor + Claude skills, .cursor/mcp.json + .mcp.json, Claude/Cursor after-edit hooks, CLAUDE.md instructions, and inclusive-check / inclusive-fix scripts. Existing files are never overwritten. Hooks surface hard findings back to the agent after Edit/Write so Claude keeps checking even when nobody remembers.

AI-copy habit (definition of done)

npx -y anti-default fix .          # safe 1:1 autofixes only
npx -y anti-default .              # remaining findings

Agents should not mark UI/docs work done until hard findings are cleared or explicitly marked fine in context. Soft/coded hits stay advisory.

# Preview autofixes without writing
npx -y anti-default fix . --dry-run

# Intentional language — suppress locally + share structured feedback
npx -y anti-default feedback --kind fine_in_context \
  --rule guys-generic --match "guys" --context "…snippet…" \
  --note "Quoted lyric" --open-issue

MCP server

npx -y anti-default mcp

See for-agents for host-specific paste steps.

Scan the way you work

# Paths
npx -y anti-default ./src ./docs README.md

# CI formats
npx -y anti-default . --format json  -o report.json
npx -y anti-default . --format sarif -o results.sarif

# Batch URLs — no Review UI
npx -y anti-default --urls https://example.com https://example.com/about
npx -y anti-default --urls-file urls.txt --format json

# Only files changed in this branch
npx -y anti-default . --changed-from origin/main

# Keep existing findings quiet; report only new ones
npx -y anti-default baseline .

Ignore what doesn’t matter

Commit a .undefaultignore so day-two noise doesn’t drown the team (example):

node_modules/
vendor/
*.min.js
rule:guys          # turn off one rule for this repo

GitHub Action

Keep inclusive language in the PR loop. This scans only changed files, fails on clear new findings, and leaves a checklist comment:

# .github/workflows/un-default.yml
name: Un-Default
on: [pull_request]
permissions:
  contents: read
  pull-requests: write
  security-events: write

jobs:
  scan:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
      - uses: NomadBuilder/anti-default@v1
        with:
          changed-from: ${{ github.event.pull_request.base.sha }}
          format: json
          comment-on-pr: "true"
          # telemetry: false   # opt out of anonymous action_run pings

Prefer SARIF for Code Scanning? Set format: sarif and output-file: un-default.sarif. Full inputs: action.yml.

Anonymous Action pings (no repo name or findings) feed public totals at darkai.ca/un-default/usage. Badge:

![Un-Default CI runs](https://darkai.ca/un-default/api/badge/action_run.svg)

Agent skill

npx -y anti-default init installs .cursor/skills/un-default/SKILL.md — the definition-of-done workflow for AI-generated copy: fix → scan → ask or feedback → re-scan.

Source: skills/un-default/SKILL.md · feedback model: feedback/README.md


Use it as a library

The npm package has no runtime dependencies and exposes the same analyzer used by the CLI and web app:

import { analyzeText, LANGUAGE_RULES } from "anti-default";

const result = analyzeText("Welcome, you guys.");
console.log(result.findings);

Chrome extension

Same rules as the app — on the page you’re already looking at.

Add to Chrome →

Runs offline from a bundled rule list. No tracking. No AI calls.
Dev / unpacked: npm run extension:pack → Load unpacked → extension/ · details in extension/README.md

Web app — try, learn, tune

darkai.ca/un-default

  • Review — paste, upload, or scan a URL; export Markdown, CSV, or a checklist
  • Swap — turn one phrase into clearer alternatives
  • Dogwhistles — learn what a phrase can signal and when context matters
  • Rules — tune the open rule catalog for your project
npm install && npm run dev   # localhost:3000

Why teams reach for it

  • Before publish — catch defaults in marketing, docs, and product copy
  • In the PR — Action + SARIF/JSON so machines and humans both get a signal
  • On the live page — extension for writers who never open a terminal
  • Without a lecture — suggestions are invitations; context always wins

Every suggestion cites the style guides and references behind it → /sources


Customize & self-host

  • Tune in the UI: /rules · edit code: src/lib/rules.ts
  • Practice corpus: npm run corpus
  • Static export: npm run build → out/
    Subpath (DarkAI): STATIC_EXPORT=true BASE_PATH=/un-default npm run build

Production lives at darkai.ca/un-default and is also vendored in DarkAI.

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选