hierarchy-designer

hierarchy-designer is a skill for Claude Code, Codex from khalilbenaz/claude-skills-collection. It costs 91 tokens per session (2,477 once invoked), scanned A, original, MIT.

A method for organizing many specialized AI agents into levels, such as an orchestrator, managers, and workers. It helps decide when a hierarchy is justified and how responsibilities should be divided.

In plain words
What is it for?
Designing two- or three-level agent structures, assigning research or validation managers, choosing between hierarchies and event-based workflows, and limiting unnecessary layers.
Why use it?
It reduces coordination problems when agents cover different domains or when a flat group becomes difficult to manage, while warning about added latency and complexity.

Skill for Claude CodeCodex

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

Good fit Designing two- or three-level agent structures, assigning research or validation managers, choosing between hierarchies and event-based workflows, and limiting unnecessary layers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/khalilbenaz/claude-skills-collection/hierarchy-designer
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 hierarchy-designer
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 hierarchy-designer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/hierarchy-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/hierarchy-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,477 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 $0.00091 $0.02477
Opus 5 $0.00046 $0.01239
Sonnet 5 $0.00018 $0.00495
Haiku 4.5 $0.00009 $0.00248

Measured 12d ago against content hash ae54e9063cee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hierarchy-designer 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 12d 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/hierarchy-designer/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Hierarchy Designer

1. Décider si une hiérarchie est justifiée

Signal Action
Tâche linéaire, < 5 agents, domaine homogène Agent unique ou flat pipeline — pas de hiérarchie
5–15 agents, 2–3 domaines distincts Hiérarchie 2 niveaux (orchestrateur + workers)
> 15 agents, domaines hétérogènes, charge variable Hiérarchie 3 niveaux avec managers intermédiaires
Sous-tâches complètement isolées Préférer une orchestration par événements plutôt qu'une pyramide

Coût réel d'une hiérarchie : +30–50 % de latence, débogage exponentiellement plus complexe, surface d'erreur plus large. N'ajouter un niveau que si le gain de parallélisme ou de spécialisation le justifie clairement.

2. Définir les niveaux et leur rôle

Orchestrateur  (1 seul)
├── Manager A  (domaine : recherche)
│   ├── Specialist Web
│   └── Specialist BDD
├── Manager B  (domaine : rédaction)
│   ├── Worker Draft
│   └── Worker Révision
└── Manager C  (domaine : validation)
    └── Specialist Fact-checker

Règle absolue : maximum 4 niveaux. Au-delà, le gain de spécialisation ne compense plus le coût de coordination.

Niveau Rôle unique Peut créer des agents ? Portée des outils
Orchestrateur Stratégie, décomposition, agrégation finale Oui (managers) Toutes ressources
Manager Coordination d'un domaine, allocation de budget Oui (workers dans son domaine) Ressources du domaine
Specialist Expertise profonde dans une niche Non Outils spécialisés seulement
Worker Exécution atomique, sans décision complexe Non Scope minimal

3. Formaliser les responsabilités (prompt système de chaque niveau)

Chaque agent reçoit un system prompt qui précise exactement :

  • Son rôle et ses limites d'autorité
  • Ce qu'il peut décider seul vs ce qu'il doit escalader
  • Le format des messages entrants et sortants
  • Son budget token/API calls
ORCHESTRATOR_PROMPT = """
Tu es l'orchestrateur. Tu reçois un objectif global.
1. Décompose en sous-objectifs par domaine.
2. Assigne chaque sous-objectif à un manager via un message JSON.
3. Attends les résultats, agrège, et produis la réponse finale.
Tu NE réalises pas de tâche atomique toi-même.
Budget max : {budget_tokens} tokens pour toute la session.
"""

MANAGER_PROMPT = """
Tu es le manager du domaine {domain}.
Tu reçois un sous-objectif. Décompose-le en tâches atomiques.
Assigne chaque tâche à un worker. Supervise et agrège les résultats.
Budget alloué : {child_budget} tokens. Escalade si insuffisant.
"""

Read the full file on GitHub · 230 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. 12d ago First seen · 230 lines · 91 tokens per session scan A ae54e9063cee

Subscribe to this mod's changes

hierarchy-designer is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 18d ago), licensed MIT. It adds 91 tokens to every session and 2,477 once invoked, about $0.0005 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