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 etl-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/etl-designer)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/etl-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/etl-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/etl-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/etl-designer.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 | $0.00082 | $0.02104 |
| Opus 5 | $0.00041 | $0.01052 |
| Sonnet 5 | $0.00016 | $0.00421 |
| Haiku 4.5 | $0.00008 | $0.00210 |
Grade A, and why
etl-designer scanned grade A 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
r = requests.get(url, headers=headers, params=params, timeout=30) How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ETL Designer
Workflow en étapes
1. Analyse des sources et destinations
- Inventorier chaque source : type (SGBD, API REST, fichier plat, Kafka, SaaS), volume moyen/max, fréquence de rafraîchissement, contraintes d'accès réseau, latence acceptable.
- Identifier la destination : data warehouse (Snowflake, BigQuery, Redshift, SQL Server DWH), data lake (S3, ADLS), data mart ou base opérationnelle.
- Consigner les SLA de fraîcheur (batch quotidien, quasi-temps-réel <5 min, streaming) et les fenêtres de maintenance source.
2. Choix ETL vs ELT
| Critère | ETL | ELT |
|---|---|---|
| Puissance de la destination | faible (on-prem DWH) | forte (Snowflake, BigQuery) |
| Données sensibles | masquage/anonymisation tôt | plus difficile à isoler |
| Flexibilité exploration | faible | forte (raw zone conservée) |
| Coût compute | moteur ETL dédié | warehouse paie la transformation |
Décision à documenter : justifier le choix dans un ADR ou un commentaire de pipeline.
3. Extraction
Full load — snapshot complet ; simple, utiliser quand la table source est petite (<1 M lignes) ou sans colonne de delta fiable.
Incrémental par timestamp/ID :
-- Extraction SQL incrémentale
SELECT *
FROM source_table
WHERE updated_at > :last_run_ts
AND updated_at <= :current_run_ts
ORDER BY updated_at;
CDC (Change Data Capture) — Debezium sur PostgreSQL/MySQL/SQL Server, Oracle GoldenGate, AWS DMS. Capturer INSERT/UPDATE/DELETE sans polling. Nécessite que le WAL ou le binlog soit activé.
Extraction API paginée (Python) :
def extract_all_pages(url, headers, page_size=200):
results, cursor = [], None
while True:
params = {"limit": page_size, **({"cursor": cursor} if cursor else {})}
r = requests.get(url, headers=headers, params=params, timeout=30)
r.raise_for_status()
data = r.json()
results.extend(data["items"])
cursor = data.get("next_cursor")
if not cursor:
break
return results
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.
- 9d ago First seen · 185 lines · 82 tokens per session scan A 0fed72ec1700
etl-designer is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 82 tokens to every session and 2,104 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
model-routing-patterns
Multi-model pipelines (Haiku/Sonnet/Opus): cost routing, escalation, fallback chains. Triggers: model routing, Haiku, Sonnet, Opus, escalation, fallback chain.
rag-patterns
RAG: embeddings, chunking, hybrid search (BM25+vector), reranking, CRAG, multi-hop. Triggers: RAG, embedding, pgvector, Qdrant, Pinecone, Weaviate, reranker, semantic search.
evaluate
Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). Triggers: measure RAG quality, knowledge gap, RAG eval, golden dataset.
json-mode-patterns
Structured JSON output from Claude: tool-use-as-JSON, schema, parsing, partial recovery. Triggers: JSON mode, structured output, schema validation, JSON parsing.
index
Reindexes KB for semantic search via vector store (Qdrant). Triggers: reindex KB, rebuild index, vector reindex, refresh embeddings.
ai-portable-setup
Erstellt einen portablen KI-Arbeitsbereich auf einem USB-Stick oder beliebigen Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurierten Prompts.