multi-agent-orchestrator

multi-agent-orchestrator is a skill for Claude Code, Codex from khalilbenaz/claude-skills-collection. It costs 111 tokens per session (2,089 once invoked), scanned A, original, MIT.

A guide to building systems where several specialised AI agents divide work and coordinate their results. It covers patterns such as a supervisor assigning tasks, parallel workers, and voting.

In plain words
What is it for?
Use it to design research pipelines, supervisor-and-worker systems, agent debates, coordinated data workflows, and error handling.
Why use it?
It helps decide when one agent is enough and when splitting work can handle different specialities, parallel tasks, or limited context more clearly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design research pipelines, supervisor-and-worker systems, agent debates, coordinated data workflows, and error handling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/khalilbenaz/claude-skills-collection/multi-agent-orchestrator
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 khalilbenaz/claude-skills-collection --skill multi-agent-orchestrator
Clone the repo
git clone --depth 1 https://github.com/khalilbenaz/claude-skills-collection

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.

agentmods badge for multi-agent-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/multi-agent-orchestrator/github.svg)](https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/multi-agent-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/multi-agent-orchestrator"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/multi-agent-orchestrator/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.

agentmods 80×15 button for multi-agent-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/multi-agent-orchestrator"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/multi-agent-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,089 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00111 $0.02089
Opus 5 $0.00056 $0.01045
Sonnet 5 $0.00022 $0.00418
Haiku 4.5 $0.00011 $0.00209

Measured 11d ago against content hash 99c7a7903b22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

multi-agent-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 11d 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.

agent-skills/multi-agent-orchestrator/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Orchestrator

Quand utiliser ce skill

Utilise ce skill dès qu'une tâche gagne à être décomposée en sous-tâches spécialisées et exécutées par des agents distincts : pipelines de recherche parallèle, systèmes supervisor/worker, débats multi-agents, workflows ETL IA, etc.

Seuil de déclenchement — un seul agent suffit si la tâche est linéaire et tient en un contexte. Passe en multi-agent si :

  • la tâche nécessite des spécialisations différentes (recherche + rédaction + validation),
  • des sous-tâches peuvent s'exécuter en parallèle,
  • la fenêtre de contexte d'un agent unique serait saturée.

Choix du pattern (critères de décision)

Pattern Quand l'utiliser Complexité
Supervisor / Router Tâche décomposable en N sous-tâches distinctes ; résultats à consolider Faible
Pipeline séquentiel Sous-tâches avec dépendances strictes A→B→C Faible
Parallel fan-out Sous-tâches indépendantes, latence critique Moyenne
Hiérarchique Organisation de type chef de projet → équipes → exécutants Moyenne
Swarm Exploration large, diversité de solutions, pas de dépendances Haute
Debate / Voting Décisions à fort enjeu, besoin de consensus ou de validation croisée Haute

Workflow en étapes

1. Décomposition de la tâche

Identifie les sous-tâches atomiques et leurs dépendances. Produis un graphe orienté (DAG) avant tout code.

tâche principale
├── sous-tâche A (indépendante)
├── sous-tâche B (indépendante)
└── sous-tâche C (dépend de A + B)

Règle : si deux sous-tâches n'ont aucune dépendance, elles doivent s'exécuter en parallèle.

2. Définition des agents

Un agent = un rôle unique + un system prompt ciblé. Évite les agents "couteau suisse".

AGENTS = {
    "researcher": Agent(
        system="Tu es un agent de recherche. Tu extrais des faits vérifiables. "
               "Retourne TOUJOURS un JSON {facts: [], sources: []}.",
        tools=[web_search, fetch_url],
    ),
    "writer": Agent(
        system="Tu es un rédacteur. Tu transformes des faits structurés en prose claire.",
        tools=[],
    ),
    "validator": Agent(
        system="Tu es un agent de validation. Tu détectes les affirmations non sourcées.",
        tools=[],
    ),
}

Read the full file on GitHub · 220 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. 11d ago First seen · 220 lines · 111 tokens per session scan A 99c7a7903b22

Subscribe to this mod's changes

multi-agent-orchestrator is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 18d ago), licensed MIT. It adds 111 tokens to every session and 2,089 once invoked, about $0.0006 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 skills, from other repositories

explain

Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.

softspark/ai-toolkit · 34 tokens

common-sense-index-investing-bogle

Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.

simbajigege/book2skills · 38 tokens

finance-econ-literacy

A Korean-language guide to understanding economic indicators such as interest rates, exchange rates, inflation, GDP, employment, and trade. It explains how these figures can affect loans, savings, investments, and spending.

modu-ai/moai-cowork · 128 tokens

stock-analysis-lead

Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…

johnqtcg/awesome-skills · 229 tokens

stock-business-review

Review a US-listed company's business model and revenue structure for an equity-research workup. Covers product/service mix, customer concentration, geographic exposure, industry position, revenue-growth decomposition (organic vs acquired vs price vs volume), and information-tier discipline (which numbers are facts vs…

johnqtcg/awesome-skills · 121 tokens

stock-earnings-quality-review

Review a US-listed company's earnings quality, cash-flow integrity, and operating leverage for an equity-research workup. Covers operating cash flow vs net income drift, free cash flow trajectory, capex character (maintenance vs expansion), equity issuance / shareholder-return yield, revenue-quality signals…

johnqtcg/awesome-skills · 147 tokens