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 research-agent-designergit 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/research-agent-designer)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/research-agent-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/research-agent-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.
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/research-agent-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/research-agent-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00078 | $0.02476 |
| Opus 5 | $0.00039 | $0.01238 |
| Sonnet 5 | $0.00016 | $0.00495 |
| Haiku 4.5 | $0.00008 | $0.00248 |
Grade B, and why
research-agent-designer scanned grade B with 1 finding 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
resp = httpx.post( "https://google.serper.dev/search", How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Agent Designer
Quand utiliser ce skill
Conçois un agent de recherche autonome quand le besoin est : chercher sur le web ou un corpus documentaire, croiser des sources, extraire des données structurées et produire un rapport synthétique avec citations. Cas d'usage : veille concurrentielle, due diligence, fact-checking, recherche académique, production de contenu documenté.
Critères de choix d'architecture
| Besoin | Architecture recommandée |
|---|---|
| 1 sujet, réponse rapide | Mono-agent + outils multiples |
| Sujets complexes / multi-domaines | Pipeline multi-agents (searcher → extractor → synthesizer) |
| Corpus interne (PDF, SharePoint) | RAG + search hybride (vector + keyword) |
| Fréquence élevée / coût maîtrisé | Cache Redis des résultats + deduplication URL |
| Résultat fiable avec citations | Toujours : citation tracker JSON obligatoire |
Workflow en 10 étapes
1. Définir le scope et le budget
Avant tout code, fixe trois contraintes explicites :
- Budget sources : max 20-50 URLs par run
- Budget temps : timeout global 5-15 min (configurable)
- Budget tokens : max 10k tokens par source injectée dans le LLM
RESEARCH_CONFIG = {
"max_sources": 30,
"timeout_s": 600,
"max_tokens_per_source": 8000,
"max_iterations": 3,
"alert_budget_pct": 0.80,
}
2. Architecturer les quatre couches
(a) Recherche — search tools (Tavily, Serper, SerpAPI) (b) Extraction — HTML cleaner (trafilatura), PDF (pdfplumber), JS (Playwright) (c) Analyse / synthèse — LLM fort (Claude Opus / GPT-4o) (d) Output — rapport structuré avec scores de confiance et citations
Choisis dès le départ LangGraph ou un simple loop Python ; LangGraph est préférable dès que le flow est conditionnel ou multi-agents.
3. Configurer les tools de recherche
# Tavily (recommandé — retourne directement le contenu extrait)
from tavily import TavilyClient
client = TavilyClient(api_key=os.environ["TAVILY_API_KEY"])
results = client.search(
query=query,
search_depth="advanced", # "basic" pour économiser des tokens
max_results=10,
include_raw_content=False, # True si tu veux le HTML brut
)
# Serper (alternative, moindre coût)
import httpx
resp = httpx.post(
"https://google.serper.dev/search",
json={"q": query, "num": 10},
headers={"X-API-KEY": os.environ["SERPER_API_KEY"]},
)
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 · 269 lines · 78 tokens per session scan B 6edf31fa4e49
research-agent-designer is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 18d ago), licensed MIT. It adds 78 tokens to every session and 2,476 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). 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…