A procedure for acquiring datasets, meaning collections of data used for analysis or machine learning, into a project's external-data folder. Each dataset is saved with an archive and a tracked Markdown record describing its licence, size, source, restrictions, and use.

Use it to bring public or private datasets into a project while recording their provenance, legal limits, storage location, and relationship to the task.

It prevents downloaded data from becoming an undocumented or misplaced project file. The record lets other people understand where the data came from and whether they may use it.

dataset — Skill for Claude Code and Codex by stellarshenson: A procedure for acquiring datasets, meaning collections of data…

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/stellarshenson/claude-code-plugins/dataset

Any agent

npx skills add stellarshenson/claude-code-plugins --skill dataset

Clone the repo

git clone --depth 1 https://github.com/stellarshenson/claude-code-plugins

Made for: Claude Code, Codex.

Or install datascience, the plugin that ships this one along with the rest of its 20 skills, 15 commands.

Per session 171 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,187 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.

Model	Per session	Once invoked
Fable 5	$0.00171	$0.02187
Opus 5	$0.00086	$0.01094
Sonnet 5	$0.00034	$0.00437
Haiku 4.5	$0.00017	$0.00219

Measured 3d ago against content hash a471941f1fb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dataset 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.

The scan reads SKILL.md. This mod also ships 1 executable file (examples/fetch_datasets.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/datascience/skills/dataset/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dataset acquisition

Every dataset a project acquires gets TWO artifacts in a task folder under the external data directory. A corpus present without its sidecar is a defect - nobody downstream can tell what it is, where it came from, or whether it may be used.

dataset-<name>.zip - the archive, gitignored
dataset-<name>.md - the sidecar, tracked

Sidecar survives the archive. Archives are large, rebuildable and machine-local; the sidecar is the only record that reaches another machine, another repo, or a reader six months on.

Ask where it goes (MANDATORY - before creating anything)

Propose a location and WAIT for the answer. Not before the first byte is fetched - before the directory is created, because the sidecar is written and tracked before any download happens. Projects differ on where external data lives, and a corpus written to the wrong tree is a large file to move and a gitignore rule to redo.

Suggest data/external/<task>-datasets/, naming the task you inferred from the request
Offer the alternatives you can see on disk - an existing data/external/* sibling, a datasets/ root, a path already in .gitignore
Wait for the answer, then reuse the confirmed location for the rest of that task without asking again

Layout

data/external/<task>-datasets/
├── dataset-ragtruth.zip          # gitignored
├── dataset-ragtruth.md           # tracked
├── dataset-edgar-restricted.md   # tracked - describes the tree below, no archive
└── edgar-restricted/             # gitignored

Task folder, not a flat dump - one folder per task (grounding-datasets/, ner-datasets/, forecasting-datasets/), so a project running three tasks does not have to reason about which corpus belongs to which
Archive per corpus where the corpus fits an archive; an extracted tree beside the sidecar where it does not (multi-GB, incremental, or fetched file-by-file)
<name> - lowercase-hyphen, matches the spec key, identical across .zip and .md
Scaffolding a project that will hold data → create data/external/<task>-datasets/ with the gitignore rules below before the first fetch

Read the full file on GitHub · 122 lines

Files

What ships with it

3 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.

3d ago First seen · 122 lines · 171 tokens per session scan A a471941f1fb1

Subscribe to this mod's changes

dataset is a skill published in the GitHub repository stellarshenson/claude-code-plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 171 tokens to every session and 2,187 once invoked, about $0.0009 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.

Data and AI Research

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

evaluating-with-leakage-gates

Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…

maziyarpanahi/openmed · 158 tokens