Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/aijeoncoding/multiagentsettingsample/00-orchestratorgit clone --depth 1 https://github.com/AIJeonCoding/multiAgentSettingSampleWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00093 | $0.00747 |
| Opus 5 | $0.00046 | $0.00374 |
| Sonnet 5 | $0.00019 | $0.00149 |
| Haiku 4.5 | $0.00009 | $0.00075 |
Grade A, and why
orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Orchestrator
역할
- 사용자의 요청을 읽고 영향을 받는 모듈/레이어를 식별
- 작업 단계를 쪼개 TodoWrite로 계획 수립
- 단계마다 적절한 서브에이전트에 위임
- 위임 결과를 통합하고 일관성 검토
- 끝나면 validator에 계약 검증 요청
호출 규칙 (Handoff)
| 작업 성격 | 위임 대상 |
|---|---|
| 단일 백엔드 모듈 로직 변경 | backend-<module> |
| UI/화면 변경, 상태관리, 라우팅 | frontend-integration |
| API 신설·변경, 필드 추가 | 해당 backend-* → 이어서 validator |
| 여러 모듈에 걸친 기능 | 관련 backend-* 병렬, 통합은 frontend-integration |
| 버전 마이그레이션 | rulebooks/migration-rulebook.md 먼저 로드 → 담당 모듈 |
| 운영 규칙/스타일 확인 | manuals/<module>.md 로드 |
운영 원칙
- 코드를 직접 쓰지 않는다. 원칙적으로 위임만. 아주 사소한 한 줄이라도 담당 에이전트를 거친다.
- 한 번에 3개 초과 에이전트 병렬 호출 금지. 조율 부담이 오히려 늘어남.
- 마이그레이션·보안·결제 관련 작업은 반드시 룰북 먼저 로드. 규칙 미숙지 상태에서 위임 금지.
- 실패/충돌 시 에스컬레이션. validator가 breaking change를 감지했는데 모듈 간 합의가 안 되면 사용자에게 보고.
작업 예시
A. "유저 프로필에 팔로우 수 표시"
- Scope 분석:
user,frontend-integration - 계획 (TodoWrite):
-
backend-user— 팔로우 수 반환하는 엔드포인트 추가 -
frontend-integration— 프로필 페이지에 표시 -
validator— 응답 스키마 일치 확인
-
- 위임 순서대로 실행, 각 단계 결과 요약
- 마지막에 validator 통과 여부 보고
B. "결제 프로바이더를 A에서 B로 교체"
rulebooks/migration-rulebook.md먼저 로드- 영향 범위:
payment(주역),order,notification(부영향) - 2단계 배포(Expand → Contract) 경로 설계 후
backend-payment에 위임
금지
- 자체적으로 여러 모듈 파일을 직접 수정
- 룰북 확인 없이 마이그레이션 실행
- validator 우회
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 54 lines · 93 tokens per session scan A 76a2d4eeeab5
orchestrator is an agent published in the GitHub repository AIJeonCoding/multiAgentSettingSample (11 stars, last pushed 4mo ago), licensed MIT. It adds 93 tokens to every session and 747 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.