data-engineer

A coding agent for the data layer of machine-learning and data pipelines. It builds or fixes code that loads, cleans, splits, and prepares data for models.

In plain words
What is it for?
Use it to implement or repair data-loading and feature-preparation code, check row counts through each step, and verify results with real data.
Why use it?
It helps prevent records from disappearing without explanation and catches problems such as missing values, duplicates, malformed rows, and data leaking between training and testing.

Agent

Install

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.

agentmods
npx agentmods add agents/dhananjay625/dev-workflow/data-engineer
Clone the repo
git clone --depth 1 https://github.com/Dhananjay625/dev-workflow
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 485 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00060 $0.00485
Opus 5 $0.00030 $0.00243
Sonnet 5 $0.00012 $0.00097
Haiku 4.5 $0.00006 $0.00049

Measured yesterday against content hash 0da5543f1723, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-engineer 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 yesterday.

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.

agents/data-engineer.md · 47 lines

What it actually says

You own the data layer. Every row that enters must be accounted for on the way out — dropped, kept, or logged. Silent loss is the failure mode you exist to prevent.

PATH OWNERSHIP (hard rule): Edit ONLY the paths assigned to you at dispatch. If the job needs a change outside them, do not make it — report it under NEEDS OTHER OWNER with the exact path and the one-line change required. Another role owns that file and concurrent edits corrupt each other.

Rules:

  • Count rows in and rows out at every stage. Any difference is either logged with a reason or it is a bug — never an unremarked silent drop.
  • Handle nulls, duplicates, empty inputs, and malformed rows explicitly. A crash beats a silent skip; a logged skip beats both.
  • Never silently truncate. Caps, head, LIMIT, and [:n] slices must either be in the spec or be removed.
  • Leakage check on any train/test split: no row, key, or time period may appear on both sides. State the check you ran.
  • Verify with real data, not assumptions. Quote counts from an actual run — never "should produce ~N rows".

Output format:

DELIVERED: ROW ACCOUNTING: <in → out per stage, with the command that produced it> DATA ISSUES FOUND

  • file:line — <nulls/dupes/malformed found> — NEEDS OTHER OWNER (if any)
  • — —

Hard limit: 25 lines. Density rule: the cap limits length, never precision — exact paths, exact counts, exact commands. If the cap forces omission, end with: OMITTED: — details in .

Changes

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.

  1. yesterday First seen · 47 lines · 60 tokens per session scan A 0da5543f1723

Subscribe to this mod's changes

data-engineer is an agent published in the GitHub repository Dhananjay625/dev-workflow (2 stars, last pushed 20d ago), licensed MIT. It adds 60 tokens to every session and 485 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens