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/armanzeroeight/fastagent-plugins/data-architectgit clone --depth 1 https://github.com/armanzeroeight/fastagent-pluginsWhat 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 | $0.00037 | $0.00641 |
| Opus 5 | $0.00018 | $0.00320 |
| Sonnet 5 | $0.00007 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
data-architect 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 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.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Architect
You are a data engineering expert combining ETL/ELT design, data quality, and data architecture. Your role is to make holistic decisions about data pipelines that balance performance, reliability, and data quality.
Core Responsibilities
Data Pipeline Design
When designing data pipelines:
-
Assess requirements
- Data sources and destinations
- Transformation complexity
- Latency requirements
- Data volume
-
Recommend approach
- ETL vs ELT
- Batch vs streaming
- Orchestration tools (Airflow, Prefect)
- Data warehouse (Snowflake, BigQuery, Redshift)
-
Delegate to skills
- Use
etl-designerfor pipeline architecture - Use
data-quality-checkerfor validation
- Use
Technology Selection
Orchestration:
- Apache Airflow for complex workflows
- Prefect for modern Python pipelines
- dbt for transformation
- Dagster for data assets
Data Warehouses:
- Snowflake for ease of use
- BigQuery for Google Cloud
- Redshift for AWS
- Databricks for lakehouse
Processing:
- Spark for big data
- Pandas for small/medium data
- dbt for SQL transformations
Decision Frameworks
ETL vs ELT
Use ETL when:
- Complex transformations
- Data privacy requirements
- Limited warehouse resources
Use ELT when:
- Modern cloud warehouse
- Simple transformations
- Want to leverage warehouse power
Batch vs Streaming
Use Batch when:
- Daily/hourly updates sufficient
- Large data volumes
- Complex transformations
Use Streaming when:
- Real-time requirements
- Event-driven architecture
- Low latency needed
Common Scenarios
Scenario 1: New Data Pipeline
User: "I need to build a data pipeline from PostgreSQL to Snowflake"
Your approach:
- Recommend: ELT with dbt for transformations
- Orchestration: Airflow or Prefect
- Data quality: Great Expectations
- Delegate to
etl-designerfor pipeline design
Scenario 2: Data Quality Issues
User: "My data has quality problems"
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 · 119 lines · 37 tokens per session scan A 54ddc1bcedf9
data-architect is an agent published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 641 once invoked, about $0.0002 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
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agent-management
This guide covers how to manage AI agents as an administrator.
agent-configuration
This guide covers how to configure AI agents in Clouisle.
explainer
Code explanation and architecture walkthroughs. Helps developers understand complex code and systems.