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

agent-runner-mcp

v0.1.1

Published

MCP server exposing the three-platform sandboxed runner protocol: run tasks in an evidence-protected sandbox, read the EXIT protocol, and get an autopsy report. Zero runtime dependencies. Every claim carries an experiment number.

Readme

agent-runner-mcp

一个把三平台沙箱 runner 协议暴露给任何 MCP 客户端(Claude Code、Codex 等)的 MCP server:在证据保护的沙箱里跑任务、读 EXIT 协议、拿尸检报告。零依赖——MCP 协议层手写。每个能力声明带实验编号。

English: README.md

license ci

为什么存在 / Why this exists

Agent 框架各自为政,但"在沙箱里可靠地执行任务并留下证据"是共性刚需。本 server 把 dsh-witness 的 runner 协议(lock=pid:startSec、EXIT:、尸检分类学)包装成 MCP 工具——Claude Code 实测 ✓ Connected,Codex 等 MCP 客户端同协议可接。

工具 / Tools

| 工具 | 语义 | |---|---| | task_run | 沙箱执行命令(Windows ACL / Linux bwrap / macOS sandbox-exec 按平台自动选),返回任务目录 | | task_wait | 等终态(EXIT: 写入)| | task_output | 按字节偏移增量读 out.log | | task_autopsy | 生成尸检报告(autopsy-spec 格式:manner/evidence/verdict/D-01~D-09)| | task_kill | 按 lock pid 击杀(崩溃实验)| | task_adopt | 三证据收养判定(lock 解析 + 进程存活 + exit 协议)|

快速开始 / Quick start

# 安装(git 源)
dsh plugin --profile <name> add "github:Wang-Lin-Chang/agent-runner-mcp#v0.1.1"

# 注册到 Claude Code
claude mcp add agent-runner -- node dist/server.js

# 或直接跑测试(15 断言协议实测)
npm test

验收证据 / Acceptance evidence

  • EXP-1:MCP 协议层实测 15/15(握手 / 六工具 / EXIT:0→D-01 / 崩溃→D-08 / EXIT:1→D-02)
  • EXP-2:Claude Code 2.1.92 真实客户端 ✓ Connected(initialize + tools/list 握手)
  • EXP-3:Windows ACL 持久性判决(观测产物与证据区分离)
  • EXP-4:死亡语义矩阵对齐 autopsy-spec 分类学

诚实边界 / Honest boundaries

  • Claude Code 会话内工具调用需登录态——本机未登录,协议握手实测、会话调用未实测不声称。
  • 本 server 是 runner 协议层:完整 registry 级收养/事件溯源/缓存见 dsh-witness。
  • Windows CI 管理员环境下 ACL 沙箱失效 → runner fail-closed(EXIT:-998)为协议正确回应;沙箱能力验收在非管理员环境实测。
  • 离线适用面:架构无网络依赖(本地进程 + 文件协议);数天级断网长跑未实测。

License

Apache-2.0