orchestrate

A command for assembling and coordinating several specialized AI agents to work on one problem. The number and roles of agents can vary with the problem’s complexity.

In plain words
What is it for?
Use it to create multi-agent workflows for simple, moderate, or complex tasks, combine different viewpoints, and produce a shared analysis or decision.
Why use it?
It removes the need to manually decide which agents should participate and how they should collaborate. This helps organize problems that need several kinds of expertise.

Command

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/dotclaude/marketplace/orchestrate
Clone the repo
git clone --depth 1 https://github.com/dotclaude/marketplace
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,303 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 $0.00009 $0.02303
Opus 5 $0.00005 $0.01151
Sonnet 5 $0.00002 $0.00461
Haiku 4.5 $0.00001 $0.00230

Measured 3d ago against content hash b0ff5369f336, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

plugins/cognitive-orchestration/commands/orchestrate.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Orchestration Engine

Assemble and coordinate specialized expert teams with dynamic collaboration patterns optimized for specific problem complexity and user sophistication levels. Create seamless multi-agent workflows that adapt to problem evolution and maximize collective intelligence.

Team Assembly Architecture

Complexity Scaling Framework

Simple (3-4 agents)

  • Core domain specialist with primary expertise
  • Practical implementer with hands-on experience
  • Integration coordinator for synthesis and decision-making
  • Single-phase analysis with straightforward coordination

Moderate (5-6 agents)

  • Primary domain specialist with deep technical knowledge
  • Secondary domain specialist covering adjacent areas
  • Practical implementer with implementation reality-testing
  • Constructive challenger with alternative perspective generation
  • Integration lead with cross-domain synthesis capability
  • Two-phase analysis with structured disagreement

Complex (7-9 agents)

  • Multiple domain specialists with comprehensive coverage
  • Technical implementation specialists with practical constraints
  • Strategic analyst with long-term perspective evaluation
  • Risk assessor with failure mode analysis capability
  • Innovation catalyst with creative approach generation
  • Constructive challenger with systematic assumption testing
  • Integration coordinator with hierarchical synthesis management
  • Multi-phase analysis with structured collaboration protocols

Enterprise (10+ agents)

  • Comprehensive specialist coverage across all relevant domains
  • Teams-of-teams structure with hierarchical coordination
  • Meta-integration roles with cross-team synthesis capability
  • Multiple challenging perspectives with diverse analytical approaches
  • Specialized coordination roles for complex workflow management

Orchestration Pattern Framework

Sequential Pattern

[Extended thinking: Step-by-step expert consultation where each specialist builds on previous analysis. Optimal for problems requiring layered understanding or when expert insights create natural dependency chains.]

Read the full file on GitHub · 273 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. 3d ago First seen · 273 lines · 9 tokens per session scan A b0ff5369f336

Subscribe to this mod's changes

orchestrate is a command published in the GitHub repository dotclaude/marketplace (42 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 2,303 once invoked, about $0.0000 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.