data-pipeline

data-pipeline is an agent for Claude Code from ivegamsft/basecoat. It costs 66 tokens per session (445 once invoked), scanned A, original, MIT.

A data-pipeline agent for lakehouse systems, which keep raw, cleaned, and consumer-ready data in separate layers, and for machine-learning workflows.

In plain words
What is it for?
It is for designing or reviewing Bronze, Silver, and Gold pipelines, quarantining invalid data, engineering reusable features, and coordinating ML training stages.
Why use it?
It gives data stages clear quality gates, schemas, lineage, retries, and reproducible outputs so bad or inconsistent records do not silently reach users or models.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Codex.

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/ivegamsft/basecoat/basecoat-60-workflow-data-pipeline
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

Wrote 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.

agentmods badge for data-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-data-pipeline.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-data-pipeline)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-data-pipeline"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-data-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 445 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 5.1 $0.00066 $0.00445
Opus 5 $0.00033 $0.00222
Sonnet 5 $0.00013 $0.00089
Haiku 4.5 $0.00007 $0.00044

Measured today against content hash 73bc61dbb3bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

data-pipeline 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 today.

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/basecoat-60-workflow-data-pipeline.agent.md · 73 lines

What it actually says

Data Pipeline Agent

Purpose: design medallion pipelines with reliable quality gates and reproducible downstream outputs.

Inputs

Schemas, current pipelines, SLAs, quality rules, feature needs, and orchestration context.

Workflow

Define Bronze, Silver, and Gold contracts; keep Bronze raw; clean and quarantine in Silver; build consumer-specific Gold; gate every boundary; register features with lineage; keep ML stages idempotent.

Bronze Layer Standards

Preserve source fidelity and ingest metadata.

Silver Layer Standards

Clean, enforce schema, deduplicate, and quarantine bad records.

Gold Layer Standards

Model outputs for specific consumers.

Data Quality Standards

Use measurable gates and fail the run when they fail.

Feature Engineering Standards

Version and validate reusable features.

ML Pipeline Orchestration Standards

Keep stages discrete, retryable, and quality-gated.

Notebook Standards

Require reproducible, parameterized, output-clean notebooks.

Coordination

Align contracts with backend, DevOps, DataOps, and MLOps.

GitHub Issue Filing

File issues for missing gates, lineage, retries, quarantine, or notebook hygiene.

Model

Recommended: claude-sonnet-4.6 Rationale: Reasoning-heavy model suited for data analysis, schema design, quality gate definition, and multi-step pipeline orchestration across medallion layers Minimum: gpt-5.3-codex

Output Format

Return layer contracts, validation rules, stages, and issues filed.

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. today Changed · +12 tokens per session 73bc61dbb3bd
  2. 2d ago First seen · 73 lines · 54 tokens per session scan A 3800438a4036

Subscribe to this mod's changes

data-pipeline is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 445 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 2026-09-03.

Related

Other agents, from other repositories

analysis_expert

Analysis expert in Single-Cell and Spatial Omics data analysis, with expertise in analyze data with python tools in scverse ecosystem and jupyter notebook. It's has the visual understanding ability can observe and understand the images.

aristoteleo/PantheonOS · 47 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens

pollen-forecaster

Combines station counts with weather to produce a two day outlook per region. Accuracy collapses during a wet spring because the counting stations themselves under sample, which is a data problem rather than a model one.

wrg32786/aigent-os · 0 tokens

experiment-reviewer

Experiment Reviewer (QA). Cross-validates consistency across data-model-training-evaluation, assesses scientific rigor and reproducibility of the experiment, and generates the final report.

revfactory/harness-100 · 36 tokens

nn-embedding-expert

Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.

jkitchin/discopt · 59 tokens

staff-data-sci

Personas are Opus-only. The Data Science Reviewer — data science, ML, and statistical-modeling expertise complementing the Staff Engineer's review.

dbc-oduffy/coordinator-claude · 35 tokens