Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计提醒

opentangl-pluginopentangl 插件

Agent Skill

opentangl-plugin 用于辅助安全审计、权限检查和凭据风险排查,适合在 OpenClaw 中需要复核安全边界、认证流程或敏感配置时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

4,339

周安装

179

GitHub Stars

公开资料未说明

下载量

1,418
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:opentangl-plugin(opentangl 插件)
来源仓库:https://github.com/8co/opentangl-plugin
安装命令:
openclaw skills install opentangl-plugin
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install opentangl-plugin

简介

opentangl-plugin 用于辅助安全审计、权限检查和凭据风险排查,适合在 OpenClaw 中需要复核安全边界、认证流程或敏感配置时使用。

  • 适用于开发团队进行代码安全审查、权限策略验证和敏感信息检测等场景。
  • 通过集成 OpenTangl 生命周期工具,支持任务队列查看、工作流程执行和合并管道管理。
  • 安装命令为 openclaw skills install opentangl-plugin,建议确认维护状态及是否会触发联网或文件读写。
  • 需结合来源仓库和原始 README 核验具体用法,注意权限范围和操作影响。

SKILL.md

OpenTangl Plugin for OpenClaw

This is an OpenClaw plugin (not a plain skill). It registers native tools into the OpenClaw agent runtime so you can operate OpenTangl entirely from chat.

Once installed, your agent gains 11 tools covering the full OpenTangl lifecycle: reading the queue, proposing tasks, running autopilot, executing workflows, auditing cross-repo wiring, and managing the merge pipeline.


Install

openclaw plugins install opentangl-plugin

Then restart your gateway:

openclaw gateway restart

Configure

Add to your OpenClaw config file:

{
  plugins: {
    entries: {
      opentangl: {
        enabled: true,
        config: {
          // Required: path to your OpenTangl workspace
          // (the directory containing projects.yaml and tasks/)
          workdir: "/path/to/your/opentangl-workspace",

          // Optional: override the CLI path if not in PATH
          // bin: "/usr/local/bin/opentangl",

          // Optional: timeout in ms (default 120000; increase for autopilot)
          // timeout: 300000,
        },
      },
    },
  },
}

To enable the mutating tools (they are off by default for safety):

{
  tools: {
    allow: [
      "opentangl_propose",
      "opentangl_autopilot",
      "opentangl_run_workflow",
      "opentangl_next",
      "opentangl_wire",
      "opentangl_merge",
      "opentangl_prune",
      "opentangl_resume",
    ],
  },
}

Prerequisites

  • OpenTangl installed and configured (projects.yaml + .env with API key)
  • node, git, gh in PATH
  • OPENAI_API_KEY or ANTHROPIC_API_KEY in the environment

What you get

Always-on tools (read-only)

ToolWhat it does
opentangl_queueTask queue with dependency status
opentangl_projectsRegistered projects and resolved paths
opentangl_list_executionsRecent workflow executions

Optional tools (enable via tools.allow)

ToolWhat it does
opentangl_proposeAnalyze codebase → propose tasks (preview or queue)
opentangl_autopilotFull autopilot: propose + write + verify + commit + PR
opentangl_run_workflowRun a workflow YAML (run or auto mode)
opentangl_nextExecute the next eligible queue task
opentangl_wireRead-only cross-repo wiring audit
opentangl_mergeMerge pipeline: CI wait, diff review, merge/escalate
opentangl_pruneRemove terminal tasks, commit cleaned queue
opentangl_resumeResume a failed workflow execution by ID

Example session

You:   What's in the task queue?
Agent: [opentangl_queue] → 3 pending, 1 running, 2 completed

You:   Propose some tasks for the api project
Agent: [opentangl_propose mode=preview projects=api] → shows proposed tasks

You:   Queue them
Agent: [opentangl_propose mode=queue projects=api] → appended 4 tasks

You:   Run the next one
Agent: [opentangl_next] → executes task, commits changes

You:   Run the merge pipeline
Agent: [opentangl_merge] → opens PRs, waits for CI, merges

Related

  • OpenTangl skill (opentangl) — onboarding guide for setting up OpenTangl from scratch
  • OpenTangl docs — https://opentangl.com

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

97.1%
按下载量换算1,377

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills