peterfei/ai-agent-team
AI Agent Team-拥有24/7专业AI开发团队：产品经理、前端开发、后端开发、测试工程师、DevOps工程师、技术负责人。一键安装，支持中英文命令，大幅提升开发效率！
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit peterfei/ai-agent-team/.claude ./rig-ai-agent-team # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit peterfei/ai-agent-team/.claude/skills/backend-dev .claude/skills/backend-dev $ npx degit peterfei/ai-agent-team/.claude/skills/changelog-generator .claude/skills/changelog-generator $ npx degit peterfei/ai-agent-team/.claude/skills/devops-engineer .claude/skills/devops-engineer $ npx degit peterfei/ai-agent-team/.claude/skills/drawnote .claude/skills/drawnote $ npx degit peterfei/ai-agent-team/.claude/skills/frontend-dev .claude/skills/frontend-dev $ npx degit peterfei/ai-agent-team/.claude/skills/fullstack-engineer .claude/skills/fullstack-engineer $ npx degit peterfei/ai-agent-team/.claude/skills/product-manager .claude/skills/product-manager $ npx degit peterfei/ai-agent-team/.claude/skills/qa-engineer .claude/skills/qa-engineer $ npx degit peterfei/ai-agent-team/.claude/skills/softcopyright .claude/skills/softcopyright $ npx degit peterfei/ai-agent-team/.claude/skills/tech-leader .claude/skills/tech-leader $ npx degit peterfei/ai-agent-team/.claude/skills/thread-manager .claude/skills/thread-manager $ npx degit peterfei/ai-agent-team/.claude/skills/tidymydesktop .claude/skills/tidymydesktop
$ curl -fsSL --create-dirs -o .claude/agents/backend_dev.md https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/agents/backend_dev.md $ curl -fsSL --create-dirs -o .claude/agents/devops_engineer.md https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/agents/devops_engineer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend_dev.md https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/agents/frontend_dev.md $ curl -fsSL --create-dirs -o .claude/agents/fullstack_dev.md https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/agents/fullstack_dev.md $ curl -fsSL --create-dirs -o .claude/agents/product_manager.md https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/agents/product_manager.md $ curl -fsSL --create-dirs -o .claude/agents/qa_engineer.md https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/agents/qa_engineer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-leader.md https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/agents/tech-leader.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (12)
backend-dev-agentchangelog-generatordevops-engineer-agentdrawnote-skillfrontend-dev-agentfullstack-engineer-agentproduct-manager-agentqa-engineer-agentsoftcopyrighttech-leader-agentthread-managertidymydesktop
Subagents (7)
| backend_dev model: inherit | 专业后端开发工程师，负责API设计、数据库优化和服务器端逻辑开发 |
| devops_engineer model: inherit | 专业DevOps工程师，负责部署、基础设施和CI/CD流水线 |
| frontend_dev model: inherit | 专业前端开发工程师，负责UI实现、组件开发和用户体验优化 |
| fullstack_dev model: inherit | 专业全栈开发工程师，负责前后端一体化开发、API集成和端到端功能实现 |
| product_manager model: inherit | 专业产品经理，负责产品规划、需求分析和路线图制定 |
| qa_engineer model: inherit | 专业QA工程师，负责测试、质量保证和缺陷报告 |
| tech-leader model: inherit | 技术负责人，负责项目技术决策和团队协调 |
Slash commands (11)
/be-start/fe-start/fs-start/ops-start/pm-start/qa-start/start-task/t/thread/threads/tl-start
Similar rigs
bijutharakan/multi-agent-squad
Production-ready multi-agent orchestration framework for Claude Code. Features specialized AI agents, automated Git workflows, and comprehensive development automation.
Orchestrator 1.5k tok ·
Rohankundra2009/claude-agents-forge
Build and run production-ready Claude Code agents with full agent specs, including turn limits, permissions, memory, and tool orchestration.
Orchestrator 1.3k tok ·
Mationetap/claude-agents-forge
Production-hardened agent system for Claude Code — uses the full agent spec (maxTurns, permissionMode, disallowedTools, Task() orchestration, memory scopes, MCP integration)
Orchestrator 1.3k tok ·
erayendes/kortext
The project brain for AI-driven development: a brief becomes approved analysis documents, then your own agent CLI (Claude, Codex etc.) writes the code. Local-first, no API key of its own.
Orchestrator 1.1k tok ·