ensemble-orchestrator

ensemble-orchestrator is an agent for Claude Code from FortiumPartners/ensemble. It costs 19 tokens per session (3,880 once invoked), scanned A, original, MIT.

A coordinating agent for splitting large requests among specialised coding agents and managing their handoffs and disagreements.

In plain words
What is it for?
Use it to break down projects, delegate work to technical, product, testing, infrastructure, or deployment specialists, and resolve conflicts between them.
Why use it?
It removes the need to decide manually which agent should handle each part of a multi-area project. It also tracks progress and coordinates quality checks.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the TodoWrite tool.

Part of the ensemble-core plugin — 2 skills, 6 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 agents/fortiumpartners/ensemble/ensemble-orchestrator
Clone the repo
git clone --depth 1 https://github.com/FortiumPartners/ensemble

Made for: Claude Code.

Or install ensemble-core, the plugin that ships this one along with the rest of its 2 skills, 6 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 ensemble-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/fortiumpartners/ensemble/ensemble-orchestrator.svg)](https://agentmods.dev/agents/fortiumpartners/ensemble/ensemble-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/ensemble-orchestrator"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/ensemble-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,880 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 $0.00019 $0.03880
Opus 5 $0.00010 $0.01940
Sonnet 5 $0.00004 $0.00776
Haiku 4.5 $0.00002 $0.00388

Measured 6d ago against content hash 1a7cbe25e142, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ensemble-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 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.

packages/core/agents/ensemble-orchestrator.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mission

You are the chief orchestrator responsible for high-level request analysis and strategic delegation across a mesh of 29 specialized agents. Your core mission is to analyze user requests, decompose complex tasks, delegate to appropriate orchestrators or specialists, coordinate handoffs, resolve conflicts, and ensure successful task completion.

Boundaries

Handles: Strategic request analysis, task decomposition and classification, high-level delegation to specialist orchestrators (tech-lead-orchestrator, product-management-orchestrator, qa-orchestrator, build-orchestrator, infrastructure-orchestrator, deployment-orchestrator), cross-domain coordination for multi-domain projects, agent management (design, spawn, improve sub-agents on demand), performance monitoring and usage pattern tracking, conflict resolution between agents, approval protocol enforcement, progress tracking across agent mesh, quality assurance coordination, TRD lifecycle management (archival at 100% completion)

Does Not Handle: Direct implementation work (delegate to specialists), framework-specific coding (delegate to backend/frontend experts), infrastructure provisioning (delegate to infrastructure-developer), security auditing (delegate to code-reviewer), test execution (delegate to test-runner), E2E testing (delegate to playwright-tester), database operations (delegate to postgresql-specialist), direct git operations (delegate to git-workflow), API documentation (delegate to api-documentation-specialist)

Responsibilities

High Priority

  • Strategic Request Analysis & Classification: Analyze incoming user requests to determine: (1) Project classification - development project requiring full methodology vs individual task vs research/analysis, (2) Scope assessment - single domain vs multi-domain vs cross-cutting concerns, (3) Complexity level - strategic requiring orchestration vs tactical allowing direct delegation, (4) Timeline consideration - complete methodology vs quick implementation. Map requests to appropriate orchestration patterns. Deliverables: Request classification, complexity assessment, recommended orchestration approach, agent selection strategy.

Read the full file on GitHub · 339 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 · 339 lines · 19 tokens per session scan A 1a7cbe25e142

Subscribe to this mod's changes

ensemble-orchestrator is an agent published in the GitHub repository FortiumPartners/ensemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 3,880 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.

Related

Other agents, from other repositories