data-batch-processing

data-batch-processing is a skill for Claude Code, Codex from j4flmao/agent-skills. It costs 98 tokens per session (4,597 once invoked), scanned A, original, MIT.

A batch-processing guide for handling large datasets in scheduled jobs with Hive or Spark SQL. Batch processing collects and transforms data in groups instead of immediately as each record arrives.

In plain words
What is it for?
Design Hive or Spark SQL jobs, organize Parquet, ORC, or Avro files, partition tables, and tune large analytical queries.
Why use it?
It helps avoid slow queries and wasteful storage by choosing suitable file formats, partitions, buckets, and processing settings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: 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 skills/j4flmao/agent-skills/batch-processing
Any agent
npx skills add j4flmao/agent-skills --skill batch-processing
Clone the repo
git clone --depth 1 https://github.com/j4flmao/agent-skills

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-batch-processing

README.md
[![agentmods](https://agentmods.dev/badge/skills/j4flmao/agent-skills/batch-processing.svg)](https://agentmods.dev/skills/j4flmao/agent-skills/batch-processing)
Your own site
<a href="https://agentmods.dev/skills/j4flmao/agent-skills/batch-processing"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/batch-processing.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,597 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 $0.00098 $0.04597
Opus 5 $0.00049 $0.02299
Sonnet 5 $0.00020 $0.00919
Haiku 4.5 $0.00010 $0.00460

Measured 2d ago against content hash 92a451776717, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

data-batch-processing 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 2d 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/batch-processing/SKILL.md · 525 lines

How it starts

The opening of the file, as written. The whole thing — 525 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Batch Processing

Purpose

Design efficient batch processing architectures using Hive, Spark SQL, and optimized file formats. Master partitioning, bucketing, Catalyst optimizer tuning, vectorized reads, file format selection, and dynamic partition pruning for large-scale analytical workloads.

Agent Protocol

Trigger

Exact user phrases: "batch processing", "Hive", "Spark SQL", "Pig", "HQL", "Hive partition", "Spark partition", "bucketing", "query optimization", "ORC", "Parquet", "Avro", "vectorized read", "dynamic partition pruning", "Catalyst optimizer", "Tungsten", "Hive metastore", "reduce tasks".

Input Context

Before activating, verify:

  • Query engine (Hive on Tez, Hive on MR, Spark SQL, Presto, Trino)
  • File format currently used (text, Parquet, ORC, Avro, JSON)
  • Table volume (row count, size in TB, partition count)
  • Partition column(s) and cardinality
  • Common query patterns (full scan, filtered, aggregated, joined)
  • Cluster resources (cores, memory, number of nodes)

Output Artifact

Batch processing configuration with engine selection, partition strategy, and optimization parameters.

Response Format

Engine: {Hive on Tez | Spark SQL | Presto | Trino}
File Format: {Parquet | ORC | Avro}
Partition: {column: type, granularity: daily/hourly/monthly}
Bucketing: {column: cluster count}
Optimizations: {vectorized, CBO, DPP, broadcast join}
Tuning: {executor/container config, parallelism}
-- DDL with partition/bucket spec
-- Query with optimization hints

No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.

Completion Criteria

  • Query engine selected with justification
  • File format selected and configured
  • Partition strategy defined (column, granularity, layout)
  • Bucketing strategy defined if applicable
  • Catalyst/BE optimizer settings configured
  • Vectorized read enabled

Max Response Length

250 lines of config.

Read the full file on GitHub · 525 lines

Files

What ships with it

7 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.

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. 2d ago First seen · 525 lines · 98 tokens per session scan A 92a451776717

Subscribe to this mod's changes

data-batch-processing is a skill published in the GitHub repository j4flmao/agent-skills (21 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 4,597 once invoked, about $0.0005 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.