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 d-padmanabhan/agent-engineering-handbook --skill data-engineeringgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/data-engineering)<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/data-engineering"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/data-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/d-padmanabhan/agent-engineering-handbook/data-engineering"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/data-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 16 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 77 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00079 | $0.00791 |
| Opus 5.5 | $0.00032 | $0.00316 |
| Sonnet 5.5 | $0.00016 | $0.00158 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
data-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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Engineering
Scope
Use this skill to:
- Review data pipeline PRs (batch or streaming)
- Design new datasets, ingestion pipelines, and transformations
- Plan backfills/replays safely
- Apply platform-specific guidance for Databricks, Snowflake, Confluent Kafka, and Teradata
- Route cross-service Outbox/Inbox and Saga consistency design to the distributed transactions skill (
${HANDBOOK_ROOT}/skills/distributed-transactions/SKILL.md)
Core principles (defaults)
- Idempotent: safe to re-run for a given window/offset
- Contract-driven: schema + semantics + SLA are explicit
- Observable: each run emits counts, timings, and progress/watermarks
- Governed: least privilege, masking/row filtering for sensitive data
- Cost-aware: incremental + pruning by default; avoid full scans
Quick start: PR review workflow (local)
- Determine base branch (usually
main). - Collect git facts:
git branch --show-current
git log main..HEAD --oneline
git diff --name-status main...HEAD
git diff --numstat main...HEAD
git diff main...HEAD
- Review using the structure below.
Review output format
- Critical: correctness, data loss/duplication, security/PII leaks, breaking contracts
- Recommended: performance/cost risks, operational gaps, maintainability
- Optional: style, naming, documentation improvements
Quick start: design workflow (new pipeline / dataset)
Produce a short design covering:
- Inputs: sources, formats, volumes, SLAs
- Contract: schema, keys, semantics (event vs processing time), evolution policy
- Processing: batch vs streaming, watermarking/offset tracking, dedupe/upsert strategy
- Outputs: layers (raw/curated/serving), consumers, downstream blast radius
- Quality: freshness/volume/uniqueness checks, quarantine strategy
- Security: PII classification, masking/row filters, least privilege
- Ops: alerting, retries, DLQ/quarantine, runbook for backfills
- Cost: partitioning/pruning, incremental strategy, warehouse sizing (if relevant)
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 7.4 KB
- evals/fixtures/consumer_retry_config.json 125 B
- evals/fixtures/order_backfill.sql 188 B
- evals/fixtures/order_contract.json 178 B
- references/backfills-and-replays.md 908 B
- references/contracts-and-evolution.md 990 B
- references/databricks.md 559 B
- references/kafka-confluent.md 511 B
- references/snowflake.md 468 B
- references/teradata.md 318 B
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.
- 1mo ago First seen · 78 lines · 79 tokens per session scan A 397d2c16a958
data-engineering is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (19 stars, last pushed 6d ago), licensed MIT. It adds 79 tokens to every session and 791 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…