What is data-acquire?

A process for obtaining and documenting the original datasets used in a research project. It records each source's version, license, format, date, and integrity check, while keeping restricted data out of the project repository.

Use it to download public datasets, record sources and versions, save restricted-data instructions, create file checksums, and write a provenance log before cleaning data.

It prevents uncertainty about where data came from, which version was used, and whether files changed. It also provides instructions for obtaining data that cannot be shared directly.

data-acquire — Skill by matthewdigiuseppe

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/matthewdigiuseppe/mstack/data-acquire

Any agent

npx skills add matthewdigiuseppe/MStack --skill data-acquire

Clone the repo

git clone --depth 1 https://github.com/matthewdigiuseppe/MStack

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 904 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00084	$0.00904
Opus 5	$0.00042	$0.00452
Sonnet 5	$0.00017	$0.00181
Haiku 4.5	$0.00008	$0.00090

Measured 2d ago against content hash 75c208adf5b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-acquire scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- For public data: download via `curl` / `wget` / API, save with the version in the filename.

skills/data-acquire/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mstack:data-acquire

Stage: build Voice: data-engineer

When to invoke

Start of empirical work. Before /mstack:data-clean.

Procedure

List the sources the project needs. For each:
- Name + URL or DOI of the canonical source.
- Vintage / version (e.g., V-Dem v14, WDI 2024).
- License (open / restricted / proprietary).
- Format (CSV, Stata, SPSS, API, scrape).
- Granularity (country-year, individual, dyad-year).
Acquire each source to data/raw/<source-shortname>/:
- For public data: download via curl / wget / API, save with the version in the filename.
- For DOI'd data: download from the archive (Dataverse, OSF), keep the DOI.
- For scraped data: write a fetch script in code/00-fetch-<source>.R and save the output, plus the date of fetch.
- For restricted data: do not put it in the repo. Save a stub README in data/raw/<source>/README.md describing how to acquire it.
Hash each file for integrity verification, with sha256sum (Linux) or shasum -a 256 (macOS): e.g. sha256sum data/raw/<source>/* > data/raw/<source>/SHA256SUMS.

Write data/raw/PROVENANCE.md with one entry per source:

### <source-shortname>
- URL / DOI: <link>
- Version / vintage: <version + date>
- Acquired: <YYYY-MM-DD by <user>>
- License: <license>
- Format: <format>
- Granularity: <unit-of-analysis>
- Files: <list of files in data/raw/<source>/>
- SHA256 manifest: data/raw/<source>/SHA256SUMS
- Restrictions: <none | description>
- Notes: <e.g., "imputed by source for missing 2023 values">

Sanity check. For each source:
- Open the file; confirm row count and column count match what the source documents.
- Note any column-name aliases the source uses (country vs. cname vs. country_text_id).
Update .mstack/config.yaml: append to the decisions: list (- "<date>: acquired raw data from [sources]") and set paper.status: "building".

Read the full file on GitHub · 78 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.

2d ago First seen · 78 lines · 84 tokens per session scan A 75c208adf5b1

Subscribe to this mod's changes

data-acquire is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 5d ago), licensed MIT. It adds 84 tokens to every session and 904 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

data-acquire