npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

ralphy-spec

v0.3.6

Published

One-command setup for Ralph loop + OpenSpec workflows across Cursor, OpenCode, and Claude Code.

Readme

ralphy-spec

English | 简体中文 | 한국어 | 日本語

规范驱动的 AI 开发 + 迭代执行。 结合 OpenSpec 和 Ralph 循环,实现可预测的 AI 辅助编码。

官网: https://ralphy-spec.org 文档: https://ralphy-spec.org/zh/docs/ 更新日志: https://ralphy-spec.org/zh/changelog/ · GitHub

快速开始

npx ralphy-spec init

CLI 基础用法:

ralphy-spec run --dry-run
ralphy-spec run
ralphy-spec status
ralphy-spec budget --json

然后使用你的 AI 工具对应的命令:

Cursor

| 命令 | 功能 | |------|------| | /ralphy-plan | 从需求创建规范 | | /ralphy-implement | 迭代循环构建 | | /ralphy-validate | 验证验收标准 | | /ralphy-archive | 完成并归档 |

Claude Code

| 命令 | 功能 | |------|------| | /ralphy-plan | 从需求创建规范 | | /ralphy-implement | 迭代循环构建 | | /ralphy-validate | 验证验收标准 | | /ralphy-archive | 完成并归档 |

OpenCode

使用自然语言配合 AGENTS.md:

  • "Follow AGENTS.md to plan [功能]"
  • "Follow AGENTS.md to implement [变更]"
  • "Follow AGENTS.md to validate"
  • "Follow AGENTS.md to archive [变更]"

配合 Ralph 循环运行器:

npm install -g @th0rgal/ralph-wiggum
ralph "Follow AGENTS.md to implement add-api. Output <promise>TASK_COMPLETE</promise> when done." --max-iterations 20

工作流示例

# 1. 规划:从你的想法创建规范
You: /ralphy-plan 添加 JWT 用户认证

# 2. 实现:AI 迭代构建
You: /ralphy-implement add-user-auth

# 3. 验证:确保测试通过
You: /ralphy-validate

# 4. 归档:完成变更
You: /ralphy-archive add-user-auth

创建的文件

.cursor/prompts/          # 或 .claude/commands/
├── ralphy-plan.md
├── ralphy-implement.md
├── ralphy-validate.md
└── ralphy-archive.md

AGENTS.md                 # OpenCode 使用

openspec/
├── specs/                # 真实来源
├── changes/              # 进行中的工作
├── archive/              # 已完成
└── project.md            # 上下文

ralphy-spec/              # 本地状态 + 可读产物(IDE 友好)
├── state.db              # SQLite 运行/任务日志
├── STATUS.md             # 实时状态(`ralphy-spec status` 优先读取)
├── TASKS.md              # 任务看板
├── BUDGET.md             # 花费/预算
├── runs/                 # 不可变运行日志(`runs/<runId>.md`)
├── logs/                 # 后端原始输出(尽力写入)
├── worktrees/            # Git worktree(启用 worktree 模式时)
└── tasks/                # 单任务产物(CONTEXT / REPAIR / NOTES)
    └── <taskId>/
        ├── CONTEXT.md
        ├── REPAIR.md
        └── NOTES.md

注意:如果检测到旧的 .ralphy/,会自动迁移到 ralphy-spec/ 并提示。

工作原理

Ralph Wiggum 循环: AI 重复接收相同提示直到任务完成。每次迭代,它都能看到文件中的之前工作并自我纠正。

OpenSpec: 先有规范后有代码。结构化的规范和验收标准确保 AI 知道要构建什么。

为什么结合使用:

| 问题 | 解决方案 | |------|----------| | 聊天中的模糊需求 | 规范锁定意图 | | AI 中途停止 | 循环重试直到完成 | | 无法验证 | 测试验证输出 | | 工具特定设置 | 一条命令搞定所有 |

安装选项

# npx(推荐)
npx ralphy-spec init

# 全局安装
npm install -g ralphy-spec
ralphy-spec init

# 指定工具
ralphy-spec init --tools cursor,claude-code,opencode

致谢

基于以下项目:

许可证

BSD-3-Clause