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 subagent-delegatorgit 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/subagent-delegator)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/subagent-delegator"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/subagent-delegator/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/subagent-delegator"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/subagent-delegator.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 | $0.00096 | $0.02885 |
| Opus 5 | $0.00048 | $0.01443 |
| Sonnet 5 | $0.00019 | $0.00577 |
| Haiku 4.5 | $0.00010 | $0.00288 |
Grade A, and why
subagent-delegator 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.
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Delegator
Quand utiliser ce skill
| Situation | Action |
|---|---|
| Tâche décomposable en sous-tâches indépendantes | Déléguer en parallèle (fan-out) |
| Domaines métier distincts (research / write / validate) | Sous-agents spécialisés |
| Tâche trop longue pour un seul contexte LLM | Pipeline séquentiel A → B → C |
| Besoin de résultats redondants/comparés | Fan-out + voting |
| Charge variable, agents réutilisables | Pool pré-alloué |
Ne pas déléguer si la tâche tient en 1-2 appels directs : la coordination coûte plus que le gain.
1. Définir le contrat d'interface avant tout
Avant de coder la logique de dispatch, figer les types d'entrée/sortie. Tout le reste en dépend.
from pydantic import BaseModel
from typing import Any, Literal
class TaskDefinition(BaseModel):
task_id: str # UUID unique, tracé de bout en bout
objective: str # Ce que le sous-agent DOIT produire (1 phrase)
context: dict[str, Any] # Données nécessaires (pas le world state entier)
constraints: list[str] # Ce qui est interdit ou imposé
output_format: Literal["json", "text", "structured"]
timeout: int = 30 # Secondes — toujours explicite
priority: int = 1
retry_limit: int = 3
class TaskResult(BaseModel):
task_id: str
agent_id: str
status: Literal["success", "partial", "failed"]
data: Any
errors: list[str] = []
execution_time: float
confidence: float = 1.0 # 0.0-1.0, utile pour le fan-in
Règle : le context ne contient que ce dont le sous-agent a besoin — pas le state global complet. Surcharger le contexte = latence + hallucination.
2. Choisir la stratégie de dispatch
Tâches identiques, N agents disponibles → round-robin
Agents avec capacités différentes → capability-based (manifest)
Charge en temps réel connue → load-based (queue size)
Tâches sémantiquement variées → semantic routing (embeddings)
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.
- 11d ago First seen · 318 lines · 96 tokens per session scan A 2964ccf908d6
subagent-delegator is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 17d ago), licensed MIT. It adds 96 tokens to every session and 2,885 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.
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…