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 skills/saolalab/clawforce/data-pipelinenpx skills add saolalab/clawforce --skill data-pipelinegit clone --depth 1 https://github.com/saolalab/clawforceWrote 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/saolalab/clawforce/data-pipeline)<a href="https://agentmods.dev/skills/saolalab/clawforce/data-pipeline"><img src="https://agentmods.dev/badge/skills/saolalab/clawforce/data-pipeline.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 | $0.00015 | $0.02156 |
| Opus 5 | $0.00008 | $0.01078 |
| Sonnet 5 | $0.00003 | $0.00431 |
| Haiku 4.5 | $0.00002 | $0.00216 |
Grade A, and why
Data Pipeline Engineering 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Pipeline Engineering Skill
ETL Pipeline Design Checklist
Extract Phase
- Source Identification: What are the data sources?
- Extraction Method: API, database query, file transfer?
- Frequency: Real-time, hourly, daily, batch?
- Authentication: How to authenticate?
- Rate Limits: Are there API rate limits?
- Error Handling: How to handle extraction failures?
- Incremental vs Full: Can we do incremental loads?
Transform Phase
- Data Cleaning: What cleaning needed?
- Validation Rules: What validation checks?
- Business Logic: What transformations required?
- Data Quality Checks: Completeness, accuracy, consistency?
- Deduplication: How to handle duplicates?
- Type Conversions: What type conversions needed?
- Aggregations: Any aggregations required?
Load Phase
- Target System: Where is data loaded?
- Load Strategy: Insert, update, upsert, replace?
- Partitioning: How to partition data?
- Indexing: What indexes needed?
- Constraints: What constraints to enforce?
- Load Frequency: How often to load?
- Rollback Plan: How to rollback if needed?
Monitoring & Alerting
- Success Metrics: How to measure success?
- Failure Alerts: What failures to alert on?
- Data Quality Alerts: What quality issues to alert?
- Performance Monitoring: Track execution time?
- Data Freshness: Monitor data freshness?
- Logging: What to log?
Documentation
- Pipeline Documentation: Documented pipeline?
- Data Dictionary: Updated data dictionary?
- Runbook: Operational runbook created?
- Dependencies: Documented dependencies?
- Ownership: Clear ownership assigned?
Data Modeling Patterns
Star Schema
Structure:
- One fact table (center)
- Multiple dimension tables (surrounding)
- Denormalized dimensions
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 · 300 lines · 15 tokens per session scan A 52debfd759c4
Data Pipeline Engineering is a skill published in the GitHub repository saolalab/clawforce (38 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 2,156 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 skills, from other repositories
data-engineer
Expert in data pipelines, ETL processes, and data infrastructure.
data-migration
Activate when the genjob agent detects that the source and target databases differ. Covers cross-database transfer lifecycle - type mapping via adapter Mixin hints, DDL generation, data transfer via transferqueryresult, and lightweight reconciliation.
data-pipeline
Production data pipeline patterns — ETL/ELT design, orchestration with Airflow/Prefect, idempotency, incremental loads, and data quality.
operator-verify
Bootstrap and verify Operator ETL in one command — Python check, uv install, sync deps, full proof gate. Use on first clone, "does it work", setup, or before any other operator skill.
operator-run
Run Operator ETL locally — MVP demo, pytest, FOIA graph pipeline, Streamlit dashboard. Use when proving the system works or demoing to reviewers.
operator-ship-gcp
Deploy Operator ETL to GCP — Terraform, Docker, Cloud Build, Cloud Run, BigQuery. Use when lifting from local DuckDB MVP to staging/production infrastructure.