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 skills add vignesh2027/AI-AGENT-SKILLS --skill data-pipeline-engineeringgit clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLSWrote 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/vignesh2027/ai-agent-skills/data-pipeline-engineering)<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/data-pipeline-engineering"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/data-pipeline-engineering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/data-pipeline-engineering"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/data-pipeline-engineering.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00020 | $0.00890 |
| Opus 5 | $0.00010 | $0.00445 |
| Sonnet 5 | $0.00004 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
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 10d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Data pipelines fail silently. Bad data flows downstream, corrupts reports, poisons ML training sets, and violates compliance requirements — often for days before anyone notices. This skill builds pipelines with the discipline to catch failures at the source.
When to Use
- Before building any ETL/ELT pipeline
- When designing data transformations
- When adding a new data source to a pipeline
- When a downstream consumer reports incorrect data
Process
Step 1: Define the data contract
Before any code: document the contract for every data source:
- Schema (columns, types, nullability)
- Volume expectations (rows per batch/day)
- Freshness SLA (how old can data be?)
- Quality invariants (column X is always positive, column Y is always a valid email)
The contract is your test suite specification.
Step 2: Implement contract validation at ingestion
Validate incoming data against the contract as the first step of every pipeline. Fail loudly on schema violations, out-of-range values, and unexpected nulls. Never silently drop bad records without alerting.
Step 3: Design for idempotency
Every pipeline run must be idempotent: running it twice on the same input produces the same output. Implement with: append-only writes + deduplication, or upserts with stable primary keys, or overwrite semantics with explicit partitions.
Step 4: Implement data lineage
Track: where did each record come from? What transformations were applied? When was it processed? This is required for debugging, compliance (GDPR right-to-erasure), and impact analysis.
Step 5: Design the quality gate
After transformation, before writing to the destination:
- Row count check (within expected range?)
- Key quality metrics (null rates, uniqueness, referential integrity)
- Distribution check (not wildly different from yesterday?)
- Business rule validation (revenue never negative, user_id always set)
Fail the pipeline and alert if quality gates fail.
Step 6: Handle late-arriving and out-of-order data
Define: what is the watermark? How long do you wait for late data? What happens to a record that arrives after the window closes?
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.
- 10d ago First seen · 91 lines · 20 tokens per session scan A 6ca6c4c0acae
data-pipeline-engineering is a skill published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 12d ago), licensed MIT. It adds 20 tokens to every session and 890 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 2026-08-31.
Other skills, from other repositories
ai-shaped-readiness-advisor
Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build.
context-engineering-advisor
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
ai-evaluation-engineering
An AI evaluation engineering specialist for testing models and prompts. The description does not provide enough detail to state which concrete operations it performs.
mdc-langchain
Definitive guidelines for writing maintainable, performant, and robust LangChain applications using modern best practices (LCEL, LangGraph, Pydantic, createagent).
mdc-tensorflow
This guide defines the definitive best practices for writing TensorFlow code, focusing on tf.keras for models, tf.data for input pipelines, and @tf.function for performance, ensuring reproduc...
mdc-vllm
Definitive guidelines for writing high-performance, maintainable, and production-ready LLM inference code using vLLM.