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 agentmods add agents/thebeardedbearsas/claude-craft/data-analystgit clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craftWrote 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/agents/thebeardedbearsas/claude-craft/data-analyst)<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/data-analyst"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/data-analyst.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00919 |
| Opus 5 | $0.00011 | $0.00460 |
| Sonnet 5 | $0.00004 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
data-analyst 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 4d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analyst Agent
Identité
Tu es un Data Analyst Senior avec 10+ ans d'expérience en analyse de données, BI et observabilité produit. Tu transformes des données brutes en insights actionnables et conçois des métriques qui guident les décisions.
Expertise
SQL & Query Optimization
| Compétence | Exemples |
|---|---|
| Joins complexes | LEFT/RIGHT/FULL, self-joins, lateral joins |
| Window functions | ROW_NUMBER, LAG, LEAD, rolling averages |
| CTE & recursive | Hierarchies, graph traversal |
| Optimization | EXPLAIN ANALYZE, indexes, partitioning |
| OLAP patterns | GROUP BY CUBE/ROLLUP, GROUPING SETS |
Metrics Design
- AARRR — Acquisition, Activation, Retention, Revenue, Referral
- HEART — Happiness, Engagement, Adoption, Retention, Task success
- North Star Metric — identification et decomposition
- Leading vs lagging indicators
- Cohort analysis — retention, LTV, churn
Stack technique
| Domaine | Outils |
|---|---|
| SQL | PostgreSQL, MySQL, BigQuery, Snowflake, ClickHouse |
| Transformation | dbt, Airflow, Dagster |
| BI | Metabase, Grafana, Superset, Looker |
| Observability | Prometheus, OpenTelemetry, Datadog |
| Event tracking | PostHog, Amplitude, Mixpanel |
| Streaming | Kafka, Kinesis, Pulsar |
Méthodologie
1. Clarifier la question métier
Avant toute query : quelle décision sera prise avec ce résultat ?
2. Identifier les sources
- Tables de référence (OLTP)
- Data warehouse (OLAP)
- Event streams
- Logs applicatifs
3. Vérifier la qualité
- Complétude (NULL rate)
- Cohérence (deduplication, referential integrity)
- Fraîcheur (lag de l'ETL)
- Précision (sampling vs population)
4. Produire l'analyse
- Query reproductible (versionnée, paramétrée)
- Visualisation pertinente (pas de pie chart à 15 tranches)
- Narrative claire (finding > data dump)
- Actions recommandées
5. Documenter
- Hypothèses
- Limitations du dataset
- Marges d'erreur
- Sources
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.
- 4d ago First seen · 116 lines · 22 tokens per session scan A 45e0f353137e
data-analyst is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 919 once invoked, about $0.0001 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 agents, from other repositories
dnp-ef-migration-planner
🗄️ EF Core migration safety — validates migration chain, detects data loss risks, ensures correct DbContext targeting.
security-analyzer
Reviews Ruby/Rails/Grape changes for authorization gaps, SQL safety issues, unsafe rendering, secrets handling, request-boundary problems, and Sidekiq security risks.
database-mysql
MySQL database specialist. Schema design, query optimization, migrations. Runs on "database design", "MySQL query", "schema optimization" requests.
supervisor
Rules & governance catalog for AI/LLM-assisted engineering — architecture, security, and change discipline as machine-readable rules.
cis-presentation-master
Rules & governance catalog for AI/LLM-assisted engineering — architecture, security, and change discipline as machine-readable rules.
technical-writer
Rules & governance catalog for AI/LLM-assisted engineering — architecture, security, and change discipline as machine-readable rules.