What is agent-orchestra?

A multi-agent collaboration system with 251 specialist agents across 19 departments, plus a dispatcher and reviewers. An agent is a software worker assigned to a task.

Use it for large tasks spanning areas such as frontend, backend, design, security, finance, GIS, or game development.

It helps divide complex, multi-stage work among specialists and adds review before delivery.

agent-orchestra — Skill for Claude Code and Codex by MarecGents

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.

Any agent

npx skills add MarecGents/marec-agent-skills --skill agent-orchestra

Clone the repo

git clone --depth 1 https://github.com/MarecGents/marec-agent-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/marecgents/marec-agent-skills/agent-orchestra/github.svg)](https://agentmods.dev/skills/marecgents/marec-agent-skills/agent-orchestra)

Your own site

<a href="https://agentmods.dev/skills/marecgents/marec-agent-skills/agent-orchestra"><img src="https://agentmods.dev/badge/skills/marecgents/marec-agent-skills/agent-orchestra/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/marecgents/marec-agent-skills/agent-orchestra"><img src="https://agentmods.dev/badge/skills/marecgents/marec-agent-skills/agent-orchestra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,388 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 92% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00147	$0.04388
Opus 5	$0.00073	$0.02194
Sonnet 5	$0.00029	$0.00878
Haiku 4.5	$0.00015	$0.00439

Measured 10d ago against content hash d5120b0c0a05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-orchestra 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 10d 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.

Origin

This is a copy

92% identical to chat_with_agent — 406 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/agent-orchestra/SKILL.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Orchestra — 多智能体协作系统

251 个专业 Agent · 19 个部门 · 总调度 + 专业执行 + 审查门禁

核心理念：先评估、再调度、审评分立、跨 Agent 协作，追求的不是快，而是稳。

1. 系统架构

用户请求
    │
    ▼
┌─────────────────────────────────────┐
│          任务评估（由 SKILL 完成）     │ ← 评估复杂度、跨领域程度、交付要求
│  简单 → 直接处理  │  复杂 → 进入调度  │
└──────────────────┬──────────────────┘
                   │
                   ▼
┌─────────────────────────────────────┐
│     总调度 Agent（agents/dispatcher/） │ ← 负责任务拆解、Agent 匹配、分配、协调
└──────────┬──────────────────────────┘
           │
    ┌──────┼──────────┬──────────┐
    ▼      ▼          ▼          ▼
┌──────┐ ┌──────┐ ┌──────┐ ┌──────────┐
│专业 A │→│专业 B │→│专业 C │ │  审查官   │
│      │←│      │  │      │ │ (门禁)   │
└──────┘ └──────┘ └──────┘ └──────────┘
   │        │        │           │
   └────────┴────────┴───────────┘
              │
              ▼
        最终交付物

角色分工

角色	职责	是否执行工作	文件位置
总调度	任务评估、Agent 匹配、分配调度、跨 Agent 协调	❌（只分配不执行）	`agents/dispatcher/总调度.md`
专业 Agent	在各自领域内编写代码/设计/内容/分析	✅	`agents/<department>/`
审查官	多维度审查（功能/代码/安全/架构/合规）	❌（只审不写）	`agents/reviewer/审查官.md`

关键规则：写工作和审工作的永远分开。又当裁判又当运动员等于没审。

2. 快速开始

2.1 目录结构

agent-orchestra/
├── SKILL.md                         ← 本文件：主技能定义
├── references/AGENTS-CATALOG.md      ← Agent 目录与部门总览（按需加载）
└── agents/                          ← 251 个 Agent 定义文件
    ├── dispatcher/  总调度.md
    ├── reviewer/    审查官.md
    └── 19 个部门目录（engineering/, marketing/, design/ ...）

如需查看完整部门分类和 Agent 列表，在需要调度 Agent 时加载 references/AGENTS-CATALOG.md。

2.2 使用方式

当收到用户请求后，按以下流程操作：

先评估（见 §3）— 判断任务是否需启用多 Agent
如需调度 → 先加载 references/AGENTS-CATALOG.md 了解 Agent 部门分布，然后加载 agents/dispatcher/总调度.md 让总调度进行任务拆解和精确 Agent 匹配
专业执行 → 按总调度分配，加载对应部门的 Agent 文件执行具体工作
跨 Agent 协作 → 按需通过总调度协调多个 Agent
最终审查 → 加载 agents/reviewer/审查官.md 进行最终审查

Read the full file on GitHub · 380 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 380 lines · 147 tokens per session scan A d5120b0c0a05

Subscribe to this mod's changes

agent-orchestra is a skill published in the GitHub repository MarecGents/marec-agent-skills (3 stars, last pushed 12d ago), licensed MIT. It adds 147 tokens to every session and 4,388 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to chat_with_agent, differing in 406 lines, and is treated as a copy.

Building agents Multi-Agent Workflow Automation agent-skills ai-agents coding-agent mg-studio

fabric-fusion

Multi-model deliberation. Two to 8 distinct models answer in parallel with web-capable tools, then a judge compares consensus, contradictions, coverage gaps, unique insights, and blind spots. Act mode runs 1–4 read-only references, then one actor reconciles and executes. Use when the cost of being wrong justifies…

monotykamary/pi-fabric · 74 tokens

agent-orchestra