data-pipeline

data-pipeline is a skill for Claude Code, Codex from JansenAnalytics/claudex. It costs 30 tokens per session (550 once invoked), scanned A, original, MIT.

A set of scripts for transforming data files such as CSV, JSON, Parquet, and NDJSON. It supports common data work such as filtering, joining, and grouping values.

In plain words
What is it for?
Use it to convert between CSV and JSON, detect file formats, merge files by a shared key, filter records, and calculate grouped sums, averages, counts, minimums, or maximums.
Why use it?
It avoids writing one-off scripts for routine format conversion and dataset cleanup.

Skill for Claude CodeCodex

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 skills/jansenanalytics/claudex/data-pipeline
Any agent
npx skills add JansenAnalytics/claudex --skill data-pipeline
Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex

Made for: Claude Code, Codex.

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/skills/jansenanalytics/claudex/data-pipeline.svg)](https://agentmods.dev/skills/jansenanalytics/claudex/data-pipeline)
Your own site
<a href="https://agentmods.dev/skills/jansenanalytics/claudex/data-pipeline"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/data-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 550 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 $0.00030 $0.00550
Opus 5 $0.00015 $0.00275
Sonnet 5 $0.00006 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 3d ago against content hash f4f6b84c6c38, 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 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.

skills/data-pipeline/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

data-pipeline

ETL and data transformation: CSV, JSON, Parquet, NDJSON processing with filtering, mapping, joining, aggregating.

When to Use

  • Converting between data formats (CSV ↔ JSON, NDJSON, etc.)
  • Cleaning or filtering datasets
  • Merging/joining files on a common key
  • Aggregating data (sum, avg, count, min, max by group)
  • Detecting file formats automatically
  • Building multi-step data processing pipelines

Scripts

Script Purpose Usage
csv-to-json.py Convert CSV → JSON array python3 csv-to-json.py input.csv [output.json]
json-to-csv.py Convert JSON array → CSV python3 json-to-csv.py input.json [output.csv]
data-merge.py Join two files on a key python3 data-merge.py left.csv right.csv --key id [--how inner]
data-filter.py Filter + aggregate data python3 data-filter.py input.csv --filter "col=val" --agg "col:sum"
detect-format.py Auto-detect file format python3 detect-format.py file.ext

All scripts read from stdin if no file argument given. Output goes to stdout by default.

References

  • references/jq-cheatsheet.md — Common jq patterns for JSON processing
  • references/csvkit-patterns.md — csvkit one-liners
  • references/large-file-handling.md — Strategies for big datasets

Examples

# Convert CSV to JSON
python3 scripts/csv-to-json.py sales.csv > sales.json

# Filter rows and aggregate
python3 scripts/data-filter.py sales.csv --filter "region=Europe" --agg "revenue:sum,count"

# Merge two CSVs on 'id' column
python3 scripts/data-merge.py users.csv orders.csv --key user_id --how left

# Detect format
python3 scripts/detect-format.py mystery_file.dat

Dependencies

Read the full file on GitHub · 60 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 · 60 lines · 30 tokens per session scan A f4f6b84c6c38

Subscribe to this mod's changes

data-pipeline is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 550 once invoked, about $0.0002 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.