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/vaquarkhan/data-engineering-agent-skills/data-specificationnpx skills add vaquarkhan/data-engineering-agent-skills --skill data-specificationgit clone --depth 1 https://github.com/vaquarkhan/data-engineering-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/vaquarkhan/data-engineering-agent-skills/data-specification)<a href="https://agentmods.dev/skills/vaquarkhan/data-engineering-agent-skills/data-specification"><img src="https://agentmods.dev/badge/skills/vaquarkhan/data-engineering-agent-skills/data-specification.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 | $0.00034 | $0.00520 |
| Opus 5 | $0.00017 | $0.00260 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
data-specification 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Specification
Overview
Write the data specification before writing pipeline code. The spec should define business intent, source and destination expectations, quality rules, and success criteria so the agent is not forced to guess.
When to Use
- new ingestion or transformation projects
- schema or contract changes
- major changes to data products, marts, or semantic models
- requests that sound simple but leave operational details unclear
Do not use this for trivial spelling fixes or non-behavioral documentation edits.
Workflow
-
State assumptions up front. Include:
- business objective
- source systems
- destination systems
- data grain
- update cadence
- retention expectations
- security or privacy constraints
-
Write the specification around required sections.
- Objective
- Business outcomes
- Source systems and contracts
- Destination tables, files, or streams
- Freshness and SLA expectations
- Data quality rules
- Security and access boundaries
- Backfill and replay expectations
- Success criteria
- Open questions
-
Resolve ambiguity before planning. If the spec cannot answer frequency, grain, keys, slowly changing behavior, or null handling, pause and ask.
-
Save the spec in version control. A data change without a written spec becomes tribal knowledge.
Common Rationalizations
| Rationalization | Reality |
|---|---|
| "We just need the table built quickly." | The wrong grain or contract creates expensive downstream rework. |
| "We can infer the business metric later." | That usually creates multiple conflicting definitions of the same metric. |
| "The destination schema is enough." | Schedules, freshness, backfills, and access rules matter just as much as columns. |
Red Flags
- no business owner is named
- source-of-truth systems are unclear
- success is defined as "pipeline runs"
- backfill behavior is omitted
- quality rules are implied instead of written
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 · 74 lines · 34 tokens per session scan A dc93f5bade98
data-specification is a skill published in the GitHub repository vaquarkhan/data-engineering-agent-skills (40 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 520 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 skills, from other repositories
kafka-shadowtraffic-java
Generate a TestContainers Java test class that spins up ShadowTraffic in-process to populate a Kafka topic with synthetic data during tests. Invokes the kafka-shadowtraffic skill to build the ShadowTraffic config, then adapts it for a containerized test network and scaffolds a JUnit 5 test class with Kafka, optional…
kafka-shadowtraffic
Generate a ShadowTraffic configuration to populate a Kafka topic with realistic synthetic data. Discovers the target topic, its key and value schemas, and the correct serializers from the live cluster via any attached Kafka MCP server, then writes a ready-to-run shadowtraffic-config.json and Docker command. Use when…
kafka-dlq-review
Review dead letter queue implementations for completeness using the Lenses MCP server. Checks DLQ topic existence, configuration, monitoring, metadata preservation, retry logic, reprocessing paths and connector DLQ alignment. Use when user says "review dead letter queues", "check DLQ setup", "DLQ audit" or asks about…
kafka-connector-review
Review Kafka Connect connector configurations for common misconfigurations using the Lenses MCP server. Checks error handling, DLQ setup, converters, transforms, task count and task health. Use when user says "review connectors", "check connector configs", "why is my connector failing" or asks about Kafka Connect…
kafka-consumer-lag
Analyse Kafka consumer group lag using the Lenses MCP server. Diagnoses lag causes (throughput bottlenecks, rebalancing, partition skew, stalled consumers) and suggests remediation. Use when user says "check consumer lag", "why are consumers slow", "lag report" or asks about consumer group health or offset progress.…
kafka-perf-review
Review Kafka producer and consumer performance configurations in both the live cluster (via Lenses MCP) and the codebase. Flags un-tuned defaults, anti-patterns and missing best practices. Use when user says "review Kafka performance", "check producer configs", "tune Kafka settings" or asks about throughput, batching…