data-sources

A guide for choosing and using data readers for CSV, database tables, Parquet files, JSON, YAML, and TOON data. It also explains which readers provide column names and how to check whether columns form a unique key.

In plain words
What is it for?
Use it when loading tabular data, adding a data format, or checking whether selected columns uniquely identify rows.
Why use it?
It prevents code from passing a streaming reader to a task that needs the full schema. It also helps balance memory use against the cost of reading large data more than once.

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/adamw7/tools/data-sources
Any agent
npx skills add adamw7/tools --skill data-sources
Clone the repo
git clone --depth 1 https://github.com/adamw7/tools

Made for: Claude Code, Codex.

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,026 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 $0.00085 $0.02026
Opus 5 $0.00043 $0.01013
Sonnet 5 $0.00017 $0.00405
Haiku 4.5 $0.00009 $0.00203

Measured 2d ago against content hash 0017aec73447, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-sources 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.

.claude/skills/data-sources/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Sources Skill

Pick the right data source in the data module, respect the schema contract that keeps forward-only sources away from schema-dependent callers, and run the uniqueness checker to find whether a set of columns can serve as a key.

In-memory vs iterative — pick first

Every format ships in two variants:

  • InMemory… — loads all rows once (readAll()), then runs multiple recursive checks cheaply. Use when the data fits in heap.
  • Iterable… — holds one row at a time (tiny heap), but re-reads the source for each recursive pass. Use for large data or streaming.

The schema contract (don't fight it)

  • IterableDataSource — the base forward-only contract: open(), nextRow(), hasMoreData(), reset(), nextRows(int batchSize).
  • ColumnarDataSource extends IterableDataSource — adds getColumnNames() for sources whose columns are known up front.
  • Forward-only sources that discover keys as they stream — iterable JSON, YAML, TOON — deliberately do not implement ColumnarDataSource. Callers that need the schema (e.g. the uniqueness check) depend on the narrower ColumnarDataSource, so a schema-less source can never be handed in and answer with null. Don't widen IterableDataSource to "fix" a compile error — reach for a columnar source instead.
  • getColumnNames() never returns null: a columnar source that cannot name its columns throws IllegalStateException saying why. IterableSQLDataSource does it for a source read before open(); CSVDataSource does it for one built without a columnsRow (new CSVDataSource(fileName) defaults it to -1), which otherwise surfaced two frames away as execForAllColumns() failing with Wrong input: null. A CSV header survives close() and is only dropped — and reloaded — by reset().

Source picker

Format In-memory Iterable Notes
CSV InMemoryCSVDataSource CSVDataSource file path or InputStream
JDBC InMemorySQLDataSource IterableSQLDataSource batchSize sets JDBC fetch size
Parquet InMemoryParquetDataSource IterableParquetDataSource read via in-process DuckDB, JDBC-like
JSON InMemoryJSONDataSource IterableJSONDataSource nested flattened to dotted paths
YAML InMemoryYAMLDataSource IterableYAMLDataSource same flattening; no size limit
TOON InMemoryTOONDataSource IterableTOONDataSource compact, LLM-friendly

Read the full file on GitHub · 139 lines

Files

What ships with it

1 file 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 · 139 lines · 85 tokens per session scan A 0017aec73447

Subscribe to this mod's changes

data-sources is a skill published in the GitHub repository adamw7/tools (11 stars, last pushed 4d ago), licensed MIT. It adds 85 tokens to every session and 2,026 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

analyzing-network-flow-data-with-netflow

Parse NetFlow v9 and IPFIX records to detect volumetric anomalies, port scanning, data exfiltration, and C2 beaconing patterns. Uses the Python netflow library to decode flow records, builds traffic baselines, and applies statistical analysis to identify flows with abnormal byte counts, connection durations, and…

mukul975/Anthropic-Cybersecurity-Skills · 76 tokens

network-rca

Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…

kubeshark/kubeshark · 163 tokens

kfl

KFL2 (Kubeshark Filter Language) reference. This skill MUST be loaded before writing, constructing, or suggesting any KFL filter expression. KFL is statically typed — incorrect field names or syntax will fail silently or error. Do not guess at KFL syntax without this skill loaded. Trigger on any mention of KFL, CEL…

kubeshark/kubeshark · 203 tokens

info-funnel

3-6 阶递减漏斗, 突出转化率 / 筛选比例 / 流量损耗。竖图适合 IG Story / 小红书.

nexu-io/html-anything · 44 tokens

build-with-tinybase

Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, configuring browser or database persistence, configuring MergeableStore…

tinyplex/tinybase · 76 tokens

docetl

Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.

ucbepic/docetl · 59 tokens