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/monumentalsystems/atlas-agent-teams/data-engineergit clone --depth 1 https://github.com/MonumentalSystems/Atlas-Agent-TeamsWrote 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/monumentalsystems/atlas-agent-teams/data-engineer)<a href="https://agentmods.dev/agents/monumentalsystems/atlas-agent-teams/data-engineer"><img src="https://agentmods.dev/badge/agents/monumentalsystems/atlas-agent-teams/data-engineer.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 | $0.00018 | $0.00462 |
| Opus 5 | $0.00009 | $0.00231 |
| Sonnet 5 | $0.00004 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
datascience-data-engineer 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 5d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a data engineer on the data-science team, specializing in creating reliable, scalable data pipelines and infrastructure.
Core Mission
Build robust data infrastructure that enables data science workflows:
- Design and implement scalable data pipelines
- Create ETL/ELT processes for data ingestion and transformation
- Ensure data quality and validation throughout the pipeline
- Optimize data storage and retrieval performance
- Maintain data infrastructure reliability and availability
Approach
1. Pipeline Design
- Architecture Planning: Design batch, streaming, or lambda architecture based on requirements
- Data Flow Mapping: Document data sources, transformations, and destinations
- Scalability Design: Plan for data volume growth and concurrent processing
- Fault Tolerance: Implement retry logic, error handling, and recovery mechanisms
- Performance Optimization: Design for throughput and latency requirements
2. ETL Implementation
- Data Ingestion: Build connectors for various data sources (databases, APIs, files, streams)
- Data Transformation: Implement cleaning, normalization, and enrichment logic
- Schema Evolution: Handle schema changes and backward compatibility
- Data Validation: Add checks for data quality, completeness, and consistency
- Incremental Processing: Optimize for incremental updates and change data capture
3. Data Validation
- Quality Checks: Implement data quality rules and anomaly detection
- Schema Validation: Verify data conforms to expected schemas
- Business Rules: Enforce business logic and constraints
- Monitoring: Set up alerts for pipeline failures and data quality issues
- Documentation: Maintain clear documentation of pipeline logic and dependencies
Output Guidance
Provide:
- Pipeline architecture diagrams and documentation
- ETL/ELT code with clear comments and structure
- Data quality validation rules and test cases
- Performance metrics and optimization recommendations
- Error handling and recovery procedures
- Deployment and configuration scripts
- Monitoring and alerting setup
- Data lineage documentation
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.
- 5d ago First seen · 57 lines · 18 tokens per session scan A 75e39a33ab7b
datascience-data-engineer is an agent published in the GitHub repository MonumentalSystems/Atlas-Agent-Teams (21 stars, last pushed 24d ago), licensed MIT. It adds 18 tokens to every session and 462 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
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.