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

@hoplogic/hopjit

v0.1.2

Published

HopJIT execution engine for HopSpec v3 — structured execution runtime for LLM agents (CC / Codex reuse-mode drivers)

Readme

HopJIT

HopJIT 是 HopSpec v3 的执行运行时——一套面向 LLM Agent 的结构化执行引擎。你用 HopSpec markdown 声明任务结构(步骤类型、数据流、循环/分支/并行、人机介入点),HopJIT 负责执行状态管理、变量存储、retry/adaptive 修复、None 传播等流控。

📖 新用户从这里开始USAGE.md — 从安装到在 Claude Code 里跑通第一个 spec 的完整上手指南。

两种驱动模式:

  • 复用模式(reuse):外层 LLM(如 Claude Code)当推理引擎,HopJIT 只做纯流控——不需要 API key。配套 hopspec skill 驱动。
  • 独立模式(standalone):HopJIT 内部 StepDispatcher 直调 LLM API 执行——需 @anthropic-ai/sdk + ANTHROPIC_API_KEY

包名、命令名、文件

一句话理清三层:装 @hoplogic/hopjit → 得到 命令 hopjit → 它执行包内的 dist/cli.js

# 全局 CLI
npm install -g @hoplogic/hopjit

# 或项目内
npm install @hoplogic/hopjit

# 开发期(克隆本仓库)
npm install && npm run build && npm link

装好后 hopjit --help 可用(bin 命令名是 hopjit,与包名 scope 无关)。

CLI 用法

hopjit validate <spec.md>        # 校验 spec 合法性(放行前闸门,验证规则)
hopjit list <dir>                # 列出目录下可执行 spec
hopjit run <spec.md> [--params '<json>']   # 启动执行(复用模式由 skill 驱动,见下)
hopjit status --state-dir <dir> [--instance <id>]   # 查执行进度
hopjit resume --state-dir <dir> [--instance <id>]   # 从中断恢复
hopjit install-skill [--dir <目标>] [--carrier cc|codex]   # 安装驱动 skill(见下)

其余子命令(init / submit_and_fetch_next / join_parallel / fanout-plan / fanout-next / debug_step / vars)由驱动层(skill / dispatcher)调用,一般不手动跑。

Quickstart(校验你自己的 spec):

hopjit validate my-spec.md

spec 范本见项目仓库 examples/(未随 npm 包发布——多为引擎自测范本)。

复用模式:安装驱动 skill

复用模式下外层 LLM(Claude Code / Codex)通过 skill 驱动引擎。一条命令安装(自动把包内 driver/ 源展开到正确布局,免手动 cp):

# Claude Code(默认,装到 .claude/skills/)
hopjit install-skill

# Codex(装到指定目录,用 AGENTS.md 载体)
hopjit install-skill --carrier codex --dir .

# 覆盖已存在的(改过 skill 想重置时)
hopjit install-skill --force

install-skill 展开的布局(CC):

.claude/skills/
├── hopspec/
│   ├── SKILL.md          # 主 skill(源 driver/hopspec-skill.md 改名)
│   └── references/       # 载体中立共享(cli-discovery / driver-subagent / …)
└── hopskill-build/
    ├── SKILL.md
    └── references/

skill 启动时自举探测 hopjit 位置(全局命令 → 项目 node_modules → 包内 dist → 开发期 fallback),无需硬编码路径——见 references/cli-discovery.md

之后在 Claude Code 里:

/hopspec run <spec.md>          # 驱动执行一个 spec
/hopspec list [dir]             # 列出可执行 spec
/hopskill-build                 # 把 prose skill 翻译成 hopskill

Codex 载体见 driver/codex/AGENTS.md——同构 CC,只换四处载体原语(触发 / 起 subagent / 问人 / act 工具)。

依赖说明

  • 运行时依赖commander(CLI)+ @anthropic-ai/sdk(仅独立模式的 StepDispatcher 用;复用模式不触发)。
  • 复用模式(skill 驱动)不需要 API key——推理由外层 LLM 承担。

文档

  • 项目仓库 examples/ — 端到端 spec 范本(data-quality / doc-review / parallel-* / fact-check 等;未随 npm 包发布)。
  • HopSpec v3 语法与执行语义见项目概念层文档(HopSpec V3 核心规范 / 配套 HopJIT 运行时能力)。

License

MIT