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.
npx skills add khalilbenaz/claude-skills-collection --skill task-decomposergit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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.
[](https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/task-decomposer)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/task-decomposer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/task-decomposer/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.
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/task-decomposer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/task-decomposer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00083 | $0.02131 |
| Opus 5 | $0.00042 | $0.01066 |
| Sonnet 5 | $0.00017 | $0.00426 |
| Haiku 4.5 | $0.00008 | $0.00213 |
Grade A, and why
task-decomposer 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Task Decomposer
Quand l'utiliser
Utiliser ce skill quand une tâche est trop vaste ou hétérogène pour un seul agent : longue durée estimée, compétences multiples requises, ou parties indépendantes parallélisables. Indispensable avant tout dispatch vers des sous-agents.
Seuil pratique : si la tâche dépasse ~3 min d'exécution ou implique >2 domaines distincts (recherche + code + validation), décomposer.
Choisir la bonne stratégie
| Stratégie | Quand l'utiliser | Exemple |
|---|---|---|
sequential |
Chaque étape dépend de la précédente | Pipeline ETL : extract → transform → load |
parallel |
Toutes les parties sont indépendantes | Analyser 10 fichiers log simultanément |
tree |
Décomposition récursive avec agrégation finale | Rapport multi-sections avec résumé global |
dag |
Mix de parallèle et séquentiel, dépendances complexes | Build CI : tests parallèles → package → deploy |
Critère de décision rapide :
toutes indépendantes → parallel
chaîne stricte → sequential
branches qui se rejoignent → tree ou dag
Workflow
1. Analyser la tâche principale
Avant de couper quoi que ce soit, répondre à ces questions :
- Livrable attendu : format exact, critères de qualité, destinataire
- Contraintes : budget tokens, deadline, outils disponibles
- Données d'entrée : quelles informations sont disponibles dès le départ, lesquelles viennent d'autres sous-tâches
- Risques : quelle sous-tâche peut bloquer l'ensemble si elle échoue
Si l'objectif est ambigu, clarifier d'abord. Une mauvaise décomposition coûte plus cher qu'une question posée.
2. Identifier et nommer les sous-tâches
Règles d'atomicité :
- Une sous-tâche = un seul agent, pas de sous-décomposition interne
- Elle produit un livrable intermédiaire vérifiable (fichier, JSON, résultat booléen)
- Elle est nommée avec un verbe d'action :
extraire_entités,générer_rapport,valider_schema
Modèle de données minimal :
class SubTask(BaseModel):
id: str # ex: "T1", "T2"
name: str # verbe + complément
description: str
depends_on: list[str] # IDs des sous-tâches dont le résultat est requis
expected_output: str # format précis du livrable
capability: str # "search" | "code" | "write" | "validate" | "transform"
complexity: Literal["low", "medium", "high"]
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.
- 12d ago First seen · 189 lines · 83 tokens per session scan A b4e849828374
task-decomposer is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 18d ago), licensed MIT. It adds 83 tokens to every session and 2,131 once invoked, about $0.0004 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.
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.
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.
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.
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…
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…
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…