GitHub自治团队

autonomous-github-team

by captainsvbot

>

3.9k编码与调试未扫描2026年3月23日

安装

claude skill add --url github.com/openclaw/skills/tree/main/skills/captainsvbot/autonomous-github-team

文档

🤖 Autonomous GitHub Team Skill

⚠️ Security Warning — Read Before Installing

This skill clones and executes bash scripts from a remote repository. Before running:

  1. Audit the scripts first — review every agent file in the agents/ directory
  2. Use a least-privilege PAT — dedicated token scoped to a single test repo, not your main account
  3. Never run on a production repo until you've tested in an isolated fork
  4. Never commit tokens — keep config.env private and out of version control
  5. Require human review before merging any PRs the agents create

What It Does

41 AI agents that autonomously monitor a GitHub repository, detect bugs, create fixes, open PRs, and release to production automatically.

Required Environment Variables

bash
GH_TOKEN        # GitHub PAT — needs: contents:w, pr:w, issues:w
TARGET_REPO     # The repository to operate on (format: owner/repo)

Primary credential: GH_TOKEN — treat this as a high-privilege secret.

Setup

bash
# 1. Clone the repo (pinned to v1.0.0 tag)
git clone --branch v1.0.0 https://github.com/captainsvbot/AutonomousGitHubTeam.git
cd autonomous-github-team

# 2. Configure — edit config.env
cp config.example.env config.env
nano config.env   # set GH_TOKEN and TARGET_REPO

# 3. Audit the agents first (important!)
# Review agents/*.sh before running anything

# 4. Run
bash agents/orchestrator.sh

Security Requirements for the GitHub Token

The skill needs a token that can:

  • Read and write to repository contents
  • Create and manage pull requests
  • Read and write issues

Create a dedicated token for this skill:

  1. GitHub → Settings → Developer Settings → Personal Access Tokens → Fine-grained tokens
  2. Scope to only the specific repository you want the team to operate on
  3. Grant only: contents: read and write, pull requests: read and write, issues: read and write
  4. Never use your main account token with broad org access

Available Agents

bash
bash agents/orchestrator.sh          # Full pipeline (detect → fix → release)
bash agents/security-agent.sh        # Vulnerability scanning
bash agents/fixer-agent.sh          # Apply fixes, open PRs
bash agents/git-guardian-agent.sh     # Merge PRs (requires human review before main merges)
bash agents/backup-agent.sh          # Backup repo via GitHub API
bash agents/rollback-agent.sh         # Auto-revert broken commits
bash agents/team-bravo.sh            # Activity monitor (read-only check)

Gitflow

code
feature/fix → develop → main

Every run syncs main → develop first. The Git Guardian does not auto-merge to main — all merges to main require human approval.

Before Running on a Production Repo

  • Clone and review all agents/*.sh files
  • Test in an isolated fork first
  • Set up branch protection on main (require PR reviews)
  • Use a dedicated, scope-limited PAT
  • Keep config.env out of version control

Security Checklist Before Publishing Changes

bash
# Scan for accidentally committed secrets
grep -rni "gho_\|token\|secret\|api_key\|password" .

If you modify this repo, always scan before pushing publicly.

相关 Skills

前端设计

by anthropics

Universal
热门

面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。

想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。

编码与调试
未扫描111.8k

网页构建器

by anthropics

Universal
热门

面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。

在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。

编码与调试
未扫描111.8k

网页应用测试

by anthropics

Universal
热门

用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。

借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。

编码与调试
未扫描111.8k

相关 MCP 服务

GitHub

编辑精选

by GitHub

热门

GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。

这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。

编码与调试
83.1k

by Context7

热门

Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。

它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。

编码与调试
51.8k

by tldraw

热门

tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。

这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。

编码与调试
46.2k

评论