65/100 (Medium)

OpenClaw： suspicious
VirusTotal： benign
StaticScan： clean

OpenClaw： suspicious

The skill's instructions are coherent with a long-running project harness, but the SKILL.md expects shell tools and running arbitrary project init scripts (which may install software or run network op...

[内容已截断]

VirusTotal： benign VT 报告

静态扫描： clean

No suspicious patterns detected.

README 未提供

{
    "latestVersion": {
        "_creationTime": 1773814548915,
        "_id": "k973gs0d8pjmq00pv07dw2ab99834g5f",
        "changelog": "# Changelog — long-running-harness\n\n所有格式基于 [Keep a Changelog](https:\/\/keepachangelog.com\/zh-CN\/1.1.0\/)，\n版本号遵循 [语义化版本](https:\/\/semver.org\/lang\/zh-CN\/)。\n\n---\n\n## [0.1.0] — 2026-03-18\n\n### 新增\n- 初始版本发布\n- 基于方法论：[Effective Harnesses for Long-Running Agents](https:\/\/www.anthropic.com\/engineering\/effective-harnesses-for-long-running-agents)（Anthropic Engineering Blog, Justin Young, 2025-11-26）\n- **SKILL.md** 核心技能文件\n  - 5 条核心原则：持久化优于记忆、结构化优于自由文本、验证优于声明、增量优于大步、标准化优于临时\n  - 三阶段项目生命周期：初始化 → 增量开发 → 进度报告\n  - 标准化启动\/结束例程（每次会话强制执行）\n  - 子Agent调度模板（sessions_spawn，task 自包含设计）\n  - Cron Job 定时巡检配置示例\n  - 故障模式预防表（6 种常见 Agent 失败模式及对策）\n  - 通用领域扩展支持：软件开发、研究、写作、数据分析（通过 category 区分）\n- **功能列表模板** `references\/feature-list-template.md`\n  - features.json 标准格式：id \/ name \/ description \/ category \/ priority \/ passes \/ tests \/ notes\n  - 8 种 category 前缀规范：feat- \/ infra- \/ docs- \/ perf- \/ fix- \/ research- \/ writing- \/ analysis-\n  - Agent 只能修改 passes 和 notes 字段的约束说明\n- **初始化脚本模板** `references\/init-template.md`\n  - Web 应用模板（Node.js \/ Python 通用）\n  - Python 项目模板（含 venv 管理）\n  - 含冒烟测试步骤，确保每次启动快速验证环境\n- **进度日志模板** `references\/progress-log-template.md`\n  - progress.md 标准格式与会话记录规范\n  - 状态标记体系：✅ 完成 \/ ⏳ 部分完成 \/ ❌ 失败\n  - 书写规范：不修改历史条目、记录 Git commits hash",
        "changelogSource": "user",
        "createdAt": 1773814548915,
        "version": "1.0.0"
    },
    "owner": {
        "_creationTime": 0,
        "_id": "publishers:missing",
        "displayName": "Aowind",
        "handle": "aowind",
        "image": "https:\/\/avatars.githubusercontent.com\/u\/26450413?v=4",
        "kind": "user",
        "linkedUserId": "kn789707vk375dmrgyd8cy9drx8322cn"
    },
    "ownerHandle": "aowind",
    "skill": {
        "_creationTime": 1773814548915,
        "_id": "kd7dwm9jzxcm5a5a9rk4n0at6n8351m2",
        "badges": [],
        "createdAt": 1773814548915,
        "displayName": "long-running-harness",
        "latestVersionId": "k973gs0d8pjmq00pv07dw2ab99834g5f",
        "ownerUserId": "kn789707vk375dmrgyd8cy9drx8322cn",
        "slug": "long-running-harness",
        "stats": {
            "comments": 0,
            "downloads": 50,
            "installsAllTime": 0,
            "installsCurrent": 0,
            "stars": 1,
            "versions": 1
        },
        "summary": "长时程 Agent 项目工作流框架（基于 Anthropic \"Effective Harnesses for Long-Running Agents\"）。 用于创建、管理和调度跨多个上下文窗口的长期项目任务。 Use when: 启动新项目、初始化项目工作流、管理项目任务列表、调度子Agent增量开发、 恢复项...",
        "tags": {
            "latest": "k973gs0d8pjmq00pv07dw2ab99834g5f"
        },
        "updatedAt": 1774336907650
    }
}