orchestrate

orchestrate is a command for Claude Code from sangrokjung/claude-forge. It costs 14 tokens per session (4,163 once invoked), scanned A, original, MIT.

A command for coordinating several AI agents on one software task at the same time. Agent Teams is an experimental feature that must be enabled in Claude Code first.

In plain words
What is it for?
Use it to run parallel feature, bug-fix, refactoring, or review work with up to three concurrent team members, or to preview the planned work with a dry run.
Why use it?
It helps divide research, reviews, features, or other work across agents, while making the extra token cost and team size visible.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the claude-forge plugin — 33 skills, 39 commands, 17 agents shipped together

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 commands/sangrokjung/claude-forge/orchestrate
Clone the repo
git clone --depth 1 https://github.com/sangrokjung/claude-forge

Made for: Claude Code.

Or install claude-forge, the plugin that ships this one along with the rest of its 33 skills, 39 commands, 17 agents.

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 orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/commands/sangrokjung/claude-forge/orchestrate.svg)](https://agentmods.dev/commands/sangrokjung/claude-forge/orchestrate)
Your own site
<a href="https://agentmods.dev/commands/sangrokjung/claude-forge/orchestrate"><img src="https://agentmods.dev/badge/commands/sangrokjung/claude-forge/orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,163 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 5.1 $0.00014 $0.04163
Opus 5 $0.00007 $0.02082
Sonnet 5 $0.00003 $0.00833
Haiku 4.5 $0.00001 $0.00416

Measured 6d ago against content hash 933290a8af28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

orchestrate 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 6d 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.

commands/orchestrate.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/orchestrate - Agent Teams 기반 병렬 오케스트레이션 (v6)

v5의 worktree 기반 병렬 실행을 Agent Teams API로 대체. TeamCreate, TaskCreate, SendMessage 등을 활용한 네이티브 팀 조율.

전제조건 (CRITICAL)

Agent Teams는 실험적 기능이며 기본 비활성화 상태이다. 반드시 아래 환경변수를 설정해야 /orchestrate가 동작한다:

// settings.json (프로젝트 또는 글로벌)
{
  "env": {
    "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
  }
}

미설정 시 TeamCreate 등 팀 관련 도구가 사용 불가하다.

토큰 비용 경고

Agent Teams는 단일 세션보다 훨씬 더 많은 토큰을 사용한다. 각 팀원은 자신의 컨텍스트 윈도우를 가지며, 토큰 사용은 활성 팀원 수에 비례하여 증가한다.

  • 연구, 검토, 새 기능 작업 → 추가 토큰의 가치가 있음
  • 일상적 작업 → 단일 세션이 더 비용 효율적

v5 대비 변경사항

v5 v6
git worktree 기반 병렬 Agent Teams API (TeamCreate, TaskCreate, SendMessage)
파일 시스템 분리 태스크 목록 기반 조율
worktree 생성/정리 필요 자동 팀 라이프사이클 관리
--effort 플래그 제거 (불필요한 복잡성)
--graph, --status 플래그 --status 제거 (TaskList로 대체)
--milestone 플래그 제거 (task 필터링으로 대체)

0단계: 파라미터 파싱

$ARGUMENTS에서 플래그를 추출한다:

플래그 기본값 설명
--dry-run false 실행하지 않고 계획만 출력
--type auto feature / bugfix / refactor / review
--parallel 3 동시 팀원 수 상한 (최대 3)

파싱 규칙:

  • --type이 없으면 prompt_plan.md 키워드로 자동 감지한다.
  • --parallel은 최대 3 (Agent Teams 제한: 리더 1 + 팀원 최대 3).

1단계: 프로젝트 도메인 감지

프로젝트 루트에서 설정 파일을 탐색하여 도메인을 결정한다.

탐색 순서 (첫 매칭 우선):
  package.json          → Node.js / TypeScript
  go.mod                → Go
  requirements.txt      → Python
  pyproject.toml        → Python
  Cargo.toml            → Rust
  Makefile (단독)       → Make-based
  *.sln / *.csproj      → .NET

감지 결과를 기반으로 도메인별 명령을 설정한다:

도메인 빌드 명령 테스트 명령 린트 명령
Node.js/TS pnpm build pnpm test pnpm lint
Go go build ./... go test ./... golangci-lint run
Python python -m build pytest ruff check .
Rust cargo build cargo test cargo clippy
.NET dotnet build dotnet test dotnet format --verify-no-changes

도메인 감지에 실패하면 사용자에게 명시적으로 질문한다. 추측하지 않는다.

Read the full file on GitHub · 461 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. 6d ago First seen · 461 lines · 14 tokens per session scan A 933290a8af28

Subscribe to this mod's changes

orchestrate is a command published in the GitHub repository sangrokjung/claude-forge (825 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 4,163 once invoked, about $0.0001 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.