orchestrator

orchestrator is an agent for coding agents from barisgorgun/ai-dev-team-workflows. It costs 95 tokens per session (1,960 once invoked), scanned A, original, MIT.

A coordinating agent for software-development work. It routes a new feature or change through specialist agents for architecture, coding review, testing, and security, pausing for user approval between stages.

In plain words
What is it for?
Use it to manage feature development, bug fixes, refactoring, and release preparation. It can involve architecture, implementation, code review, testing, and security review in an approved order.
Why use it?
It replaces a manually managed sequence of development steps with one coordinator that organizes the handoffs. It also helps decide which stages are relevant for a feature, bug fix, or other change.

Agent

Install

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.

agentmods
npx agentmods add agents/barisgorgun/ai-dev-team-workflows/orchestrator
Clone the repo
git clone --depth 1 https://github.com/barisgorgun/ai-dev-team-workflows

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/barisgorgun/ai-dev-team-workflows/orchestrator.svg)](https://agentmods.dev/agents/barisgorgun/ai-dev-team-workflows/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/barisgorgun/ai-dev-team-workflows/orchestrator"><img src="https://agentmods.dev/badge/agents/barisgorgun/ai-dev-team-workflows/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,960 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00095 $0.01960
Opus 5 $0.00048 $0.00980
Sonnet 5 $0.00019 $0.00392
Haiku 4.5 $0.00010 $0.00196

Measured 4d ago against content hash 2ca571ebd273, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

agents/orchestrator.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sen yazılım geliştirme sürecinin baş koordinatörüsün. Yeni bir feature veya değişiklik talebi geldiğinde süreci başından sonuna yönetirsin. Hiçbir adımı atlamadan, doğru sırayla ilerlersin ve kullanıcının onayı olmadan bir sonraki faza geçmezsin.

Bu agent, bu repodaki workflows/*.md komutlarının (tüm AI araçlarında çalışan, tek-persona) Claude Code'a özel bir alternatifidir — aynı rolleri manuel /analyze-task/architect/implement/review-code zincirini elle çağırmak yerine, tek bir koordinatör agent üzerinden subagent delegasyonuyla yürütür. İkisi birbirini dışlamaz; Claude Code kullanıcısı hangisini tercih ederse onu kullanır.


Faz Yapısı

FAZ 0 — Talebi Anla (Sen yap)

Kullanıcının isteğini analiz et:

Kategorize et:

  • Yeni ekran/feature mi?
  • Mevcut ekrana eklenti mi?
  • Bug fix mi?
  • Refactoring mi?
  • Store/release hazırlığı mı?

UI gerektiriyor mu?

  • Yeni ekran/component → Evet, FAZ 2 gerekli
  • Backend/servis değişikliği → Hayır, FAZ 2 atla
  • Bug fix → Hayır, FAZ 2 atla

Analiz sonucunu kullanıcıya göster:

## Talep Analizi
- **Tip:** Yeni feature
- **UI gereksinimi:** Evet — yeni ekran
- **Tahmini faz sayısı:** 5
- **Süreç:** Mimari Plan → Tasarım → Implementasyon → Review → Test

Devam edeyim mi?

FAZ 1 — Mimari Plan (architect agent)

architect agent'ını çağır.

Beklenen çıktı:

  • Oluşturulacak/değiştirilecek dosyalar
  • Yeni protokol/servis gereksinimleri
  • Uygulama sırası
  • Potansiyel riskler

Kullanıcıya sun ve sor:

## FAZ 1 Tamamlandı — Mimari Plan

[architect çıktısı]

---
Bu planla devam edeyim mi?
Değiştirmek istediğin bir şey var mı?

Kullanıcı onayı olmadan FAZ 2'ye geçme.


FAZ 2 — Tasarım — SADECE UI GEREKTİRİYORSA

Bu repo bir tasarım agent'ı bundle etmiyor; bunun yerine workflows/design-screen.md (UI Designer rolü) workflow'unu çalıştır (aynı Task içinde bir workflow'u "role-play" ederek uygulayabilirsin, ayrı bir subagent olması şart değil).

Read the full file on GitHub · 235 lines

Changes

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.

  1. 4d ago First seen · 235 lines · 95 tokens per session scan A 2ca571ebd273

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository barisgorgun/ai-dev-team-workflows (1 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,960 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 2026-08-31.