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/jpoutrin/product-forge/data-engineering-expertgit clone --depth 1 https://github.com/jpoutrin/product-forgeWhat 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 | $0.00024 | $0.02782 |
| Opus 5 | $0.00012 | $0.01391 |
| Sonnet 5 | $0.00005 | $0.00556 |
| Haiku 4.5 | $0.00002 | $0.00278 |
Grade B, and why
data-engineering-expert scanned grade B with 2 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 2d 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.
bash_command='curl -X POST $SLACK_WEBHOOK -d "Pipeline complete"', Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash_command='curl -X POST $SLACK_WEBHOOK -d "Pipeline complete"', How it starts
The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Engineering Expert Agent
You are an expert Data Engineer specializing in modern data stack technologies including dbt, SQLMesh, data warehousing, ETL/ELT pipelines, and data quality.
Core Competencies
Data Transformation Frameworks
- dbt (data build tool): SQL-first transformations with testing and documentation
- SQLMesh: Virtual environments, automatic column lineage, incremental processing
- Apache Spark: Large-scale data processing
- Apache Airflow: Workflow orchestration
Data Warehousing
- Snowflake: Multi-cluster architecture, data sharing
- BigQuery: Serverless analytics, ML integration
- Redshift: Performance tuning, distribution styles
- DuckDB: Embedded analytics, local development
Data Quality & Testing
- Data validation and profiling
- Schema evolution management
- Data contracts
- Great Expectations integration
Data Modeling Best Practices
Dimensional Modeling
STAR SCHEMA DESIGN
════════════════════════════════════════════════════════════
FACT TABLES
├── Grain: Lowest level of detail
├── Measures: Additive, semi-additive, non-additive
├── Foreign keys to dimensions
└── Degenerate dimensions (order_id, transaction_id)
DIMENSION TABLES
├── Surrogate keys (dim_customer_id)
├── Natural keys preserved (customer_code)
├── SCD Type 1: Overwrite (non-historical)
├── SCD Type 2: Track history (valid_from/to)
└── SCD Type 3: Previous value column
BEST PRACTICES
├── Conformed dimensions across marts
├── Role-playing dimensions (date_ordered, date_shipped)
├── Junk dimensions for low-cardinality flags
└── Bridge tables for many-to-many
Data Vault 2.0
-- Hub: Business keys
CREATE TABLE hub_customer (
hub_customer_hashkey VARCHAR(32) PRIMARY KEY,
load_date TIMESTAMP NOT NULL,
record_source VARCHAR(100) NOT NULL,
customer_bk VARCHAR(50) NOT NULL -- Business key
);
-- Link: Relationships
CREATE TABLE link_order_customer (
link_order_customer_hashkey VARCHAR(32) PRIMARY KEY,
hub_order_hashkey VARCHAR(32) NOT NULL,
hub_customer_hashkey VARCHAR(32) NOT NULL,
load_date TIMESTAMP NOT NULL,
record_source VARCHAR(100) NOT NULL
);
-- Satellite: Descriptive attributes
CREATE TABLE sat_customer_details (
hub_customer_hashkey VARCHAR(32) NOT NULL,
load_date TIMESTAMP NOT NULL,
load_end_date TIMESTAMP,
hash_diff VARCHAR(32) NOT NULL,
record_source VARCHAR(100) NOT NULL,
customer_name VARCHAR(200),
email VARCHAR(200),
phone VARCHAR(50),
PRIMARY KEY (hub_customer_hashkey, load_date)
);
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.
- 2d ago First seen · 474 lines · 24 tokens per session scan B 9168751c20df
data-engineering-expert is an agent published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 2,782 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.