data-pipeline.agents

A template for building Python data pipelines, which are programs that move and reshape data from sources to destinations. It covers extracting, checking, transforming, and loading data while keeping its structure clear.

In plain words
What is it for?
Use it to structure pipelines into clear stages, add type hints and boundary checks, choose pandas or Polars, and make loading repeatable through merge keys, partition replacement, or checkpoints.
Why use it?
It reduces errors caused by unexpected columns, missing values, dropped rows, repeated loads, and failures that are difficult to see or reproduce.

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/kid-sid/codex-spellbook/data-pipeline.agents
Clone the repo
git clone --depth 1 https://github.com/kid-sid/codex-spellbook
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 534 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 $0.00000 $0.00534
Opus 5 $0.00000 $0.00267
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00053

Measured 3d ago against content hash f75c4eb93b63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-pipeline.agents 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 3d 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.

agents/data-pipeline.agents.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Pipeline Agent Template

Purpose

Use this template for Python data pipelines that extract, transform, and load data while preserving schema clarity, idempotency, and observable failure modes.

Environment Setup

Run these commands before starting work:

set -euo pipefail
bash setup-scripts/python.sh
python --version
pytest --version
python -c "import pandas" >/dev/null 2>&1 || true
python -c "import polars" >/dev/null 2>&1 || true

Working Style

  • Prefer explicit pipeline stages over giant notebooks or monolithic scripts.
  • Make transformations deterministic and idempotent.
  • Fail loudly on schema drift, nullability surprises, and row drops.
  • Keep side effects isolated to extract and load boundaries.

Python and Data Conventions

  • Add type hints to stage functions and helpers.
  • Use pandas or polars intentionally; do not mix both in one module without cause.
  • Validate external records and config at boundaries.
  • Use immutable or append-only intermediate data where practical.

Pipeline Design

  • Split work into extract, validate, transform, and load phases.
  • Make load steps idempotent through merge keys, partition replacement, or checkpoints.
  • Track row counts and critical aggregates between stages.
  • Reject silent coercions that hide data loss.

Logging and Observability

  • Use structlog or the project logger for structured events.
  • Log dataset identifiers, batch windows, input counts, output counts, and error reasons.
  • Emit warnings for dropped or quarantined records with enough context to debug safely.

Testing

  • Use pytest for stage-level unit tests.
  • Build fixtures from small realistic datasets, not giant snapshots.
  • Assert row counts, schema expectations, and transformation invariants.
  • Add regression tests for previously corrupted or malformed inputs.

Storage and Performance

  • Avoid row-by-row loops when vectorized or batch operations exist.
  • Keep memory growth visible when processing large datasets.
  • Push filters and projections down to extract queries when possible.

Read the full file on GitHub · 75 lines

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. 3d ago First seen · 75 lines · 0 tokens per session scan A f75c4eb93b63

Subscribe to this mod's changes

data-pipeline.agents is an agent published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 534 tokens. 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.

Related

Other agents, from other repositories

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

streaming

Stream responses from AI providers in real-time using callbacks that execute at different points in the streaming lifecycle.

activeagents/activeagent · 20 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

mlops-reviewer

MLOps / model lifecycle pre-implementation reviewer. Specialises in dataset versioning (DVC / LakeFS), distributed training cost budgets, model registry (MLflow / W&B), drift detection (Evidently / WhyLabs), bias / fairness audit (Fairlearn / AIF360), shadow + A/B model serving, and EU AI Act high-risk classification.…

avelikiy/great_cto · 105 tokens

by-epitope

Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.

001TMF/blatant-why · 58 tokens

prompt_engineer

Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…

josstei/maestro-orchestrate · 98 tokens