dev-agent-orchestration — dev-agent-orchestration setup guide dev-agent-orchestration setup guide, how to use Claude Agent SDK V2, RAG-based development workflows, autonomous development agent systems, dev-agent-orchestration vs traditional development methods, installing dev-agent-orchestration, what is dev-agent-orchestration, dev-agent-orchestration tutorial, dev-agent-orchestration best practices

v1.0.0
GitHub

About this Skill

Ideal for AI Agents requiring streamlined development cycles, such as those built with Claude Agent SDK V2 and RAG dev-agent-orchestration is an autonomous development agent system based on Claude Agent SDK V2 and RAG, executing entire development cycles through 7 specialized agents.

Features

Utilizes unstable_v2_createSession() for session creation and session.stream() for execution
Employs hooks for monitoring and supports different execution methods per phase
Executes DESIGN phase with session.stream() and Agent Teams environment activation
Performs CODE phase with unstable_v2_prompt() using Promise.all for concurrent execution
Runs TEST/VERIFY phase with sequential unstable_v2_prompt() execution
Configures with settingSources and permissionMode options for customized operation

# Core Topics

uygnoey uygnoey
[0]
[0]
Updated: 3/4/2026

Quality Score

Top 5%
36
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add uygnoey/autonomous-dev-agent-ts/dev-agent-orchestration

Agent Capability Analysis

The dev-agent-orchestration MCP Server by uygnoey is an open-source Community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for dev-agent-orchestration setup guide, how to use Claude Agent SDK V2, RAG-based development workflows.

Ideal Agent Persona

Ideal for AI Agents requiring streamlined development cycles, such as those built with Claude Agent SDK V2 and RAG

Core Value

Empowers agents to automate design, code, test, and verification phases using unstable_v2_createSession and session.stream, while leveraging hooks for monitoring and Promise.all for concurrent execution, all within a permission-bypassed environment

Capabilities Granted for dev-agent-orchestration MCP Server

Automating development workflows with Claude Agent SDK V2 Session API
Streamlining design phases with session.stream and Agent Teams environment
Concurrently executing code generation tasks using unstable_v2_prompt and Promise.all

! Prerequisites & Limits

  • Requires Claude Agent SDK V2 and RAG setup
  • Needs permissionMode set to 'bypassPermissions' for autonomous operation
  • Dependent on specific environment variables like CLAUDE_CODE_EXPERIMENTAL_AGENT
Project
SKILL.md
1.1 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

에이전트 오케스트레이션

adev의 2계층은 Claude Agent SDK V2 Session API를 사용하여 에이전트를 실행한다.

핵심 패턴

unstable_v2_createSession()으로 세션 생성 → session.stream()으로 실행 + hooks로 모니터링.

Phase별 실행 방식이 다르다:

  • DESIGN: session.stream() 1개 + Agent Teams env 활성화 (팀 토론)
  • CODE: unstable_v2_prompt() ×N 동시 (Promise.all)
  • TEST/VERIFY: unstable_v2_prompt() 순차

필수 옵션

typescript
1{ 2 settingSources: [], // 파일시스템 설정 의존 없음 3 permissionMode: 'bypassPermissions', // 자율 운영 4 env: { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }, // DESIGN에서만 5 allowedTools: ['Read', 'Write', 'Edit', 'Bash', 'Glob', 'Grep'], 6}

Hook 기반 모니터링

typescript
1const hooks = { 2 preToolUse: async (event) => { /* 도구 호출 전 검증 */ }, 3 postToolUse: async (event) => { /* 도구 호출 후 기록 */ }, 4 teammateIdle: async (event) => { /* 팀원 유휴 감지 */ }, 5};

상세 패턴: references/v2-session-pattern.md 알려진 이슈: references/known-issues.md

Related Skills

Looking for an alternative to dev-agent-orchestration or building a Community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

testing

Logo of lobehub
lobehub

Testing is a process for verifying AI agent functionality using commands like bunx vitest run and optimizing workflows with targeted test runs.

73.3k
0
Communication

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication