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 instructions/vaquarkhan/data-engineering-agent-skills/agents-mdgit 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/instructions/vaquarkhan/data-engineering-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/vaquarkhan/data-engineering-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/vaquarkhan/data-engineering-agent-skills/agents-md.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 | $0.01517 | $0.01517 |
| Opus 5 | $0.00758 | $0.00758 |
| Sonnet 5 | $0.00303 | $0.00303 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
data-engineering-agent-skills AGENTS.md 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Engineering Agent Entry Point
Use this file as the generic entry point for agents that support AGENTS.md-style repository instructions.
Start Here
- Load
skills/using-data-engineering-agent-skills/SKILL.md - Load the platform preset from
presets/that matches the environment - Load only the workflow skills needed for the current task
- Pull in references, templates, and examples only when they improve decisions or proof
Lifecycle Commands
/spec-> define contract, SLA, lineage, schema, retention, ownership/plan-> break pipeline changes into atomic tasks/build-> implement pipeline, model, or job changes incrementally/validate-> prove data quality, contract compliance, and reconciliation/review-> review reliability, cost, governance, and operability/backfill-> run safe replay and cutover workflows/ship-> deploy, observe, rollback-safe release
Default Routing
- unclear request ->
data-specification - approved scope ->
pipeline-planning-and-task-breakdown Pythondata pipeline implementation ->python-data-engineering-and-pipeline-packagingScalaSpark, Flink, or JVM data job implementation ->scala-data-engineering-on-jvm-runtimesJavaconnector, integration, or metadata service work ->java-data-engineering-and-integration-services- file drops,
SFTP, or partner-managed feeds ->file-and-partner-feed-ingestion Glue Data CatalogorLake Formationgovernance ->glue-data-catalog-and-lake-formation-governanceUnity Cataloggovernance ->unity-catalog-and-lakehouse-governancePurviewor Azure governance ->microsoft-purview-and-azure-data-governanceDataplexorBigQuerygovernance ->dataplex-and-bigquery-governance- operational store choice such as
MySQLversusNoSQL->operational-datastore-selection-relational-and-nosql - warehouse/dbt work ->
warehouse-and-schema-design+dbt-and-analytics-engineering Snowflakewarehouse-native pipelines ->snowflake-native-pipelines-and-governanceBigQueryorDataformplatform work ->bigquery-and-dataform-platform-engineeringETLorELTtransformation-boundary work ->etl-elt-and-modernization-strategy- mainframe offload or modernization ->
mainframe-modernization-and-data-offload - streaming work ->
streaming-and-messaging-systems - Kafka production hardening, DLQs, or schema guardrails ->
kafka-resilience-and-schema-evolution - serverless Spark on Lambda or short-lived runtimes ->
spark-serverless-reliability-and-state-management - agent observability via MCP (lag, Spark plans, run state) ->
mcp-data-observability-integration - lakehouse work ->
data-lake-and-zone-architecture+lakehouse-table-format-engineering - release workflow, promotion design, or gated rollout ->
data-platform-ci-cd-and-release-management - test data or QA datasets ->
test-data-preparation-and-synthetic-data - lower-environment refreshes or masked non-prod data ->
lower-environment-data-masking-and-obfuscation Informatica,Talend, or legacy ETL estates ->enterprise-etl-and-data-integration-modernization- regional or country-specific data obligations ->
regional-data-compliance-and-sovereignty ESGor sustainability reporting ->esg-and-sustainability-regulatory-reporting- quality or release gates ->
data-quality-and-contract-testing - data-quality tool selection, rule severity, or quality operating model ->
data-quality-platforms-and-rule-management - resiliency testing, failure injection, or failover drills ->
data-resiliency-testing-and-failure-injection - disaster recovery or business continuity planning ->
data-platform-disaster-recovery-and-business-continuity - reliability issue ->
data-observability-and-sla-management+incident-triage-and-pipeline-recovery - platform-team ownership, golden paths, or support-boundary design ->
data-platform-operating-model-and-service-ownership - replay or migration work ->
safe-backfill-and-replay-orchestration+orchestration-and-backfills+data-migration-and-platform-cutover - regulated data and audit-bound publish paths ->
data-security-compliance-and-regulated-data+lineage-pii-and-governance
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 · 110 lines · 1,517 tokens per session scan A c6af8b6d56a5
data-engineering-agent-skills AGENTS.md is an instructions file published in the GitHub repository vaquarkhan/data-engineering-agent-skills (40 stars, last pushed 2mo ago), licensed MIT. It adds 1,517 tokens to every session, about $0.0076 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 instructions, from other repositories
databricks-template CLAUDE.md
Instructions for andre-salvati/databricks-template, covering claude.md, project overview, tooling: mcp servers, cli, skills → see specs/tooling.md, commands and architecture & data model → see specs/.
llm-ide-rules react.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering react, mock data, react hook form and styling.
dbt_duckdb_demo_public CLAUDE.md
Instructions for edwinweber/dbt_duckdb_demo_public, covering claude.md — project context for ai assistants, project overview, tech stack, architecture and directory structure.
llm-ide-rules typescript.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering typescript and dates & times.
llm-ide-rules python-route-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, a project described as: Centralized LLM prompt instructions for Copilot and Cursor, including scripts to convert and sync rules for Python, React, Shell, and TypeScript. Designed for rapid reuse and contribution across projects.
llm-ide-rules shell.instructions.md
Instructions for iloveitaly/llm-ide-rules, a project described as: Centralized LLM prompt instructions for Copilot and Cursor, including scripts to convert and sync rules for Python, React, Shell, and TypeScript. Designed for rapid reuse and contribution across projects.