data-review

A review of a data file—such as a CSV, spreadsheet, JSON, or XML export—to assess whether it can be loaded into a data warehouse. A data warehouse stores structured data for analysis and reporting.

In plain words
What is it for?
Use it to review exported data before warehouse loading and produce a tiered cleansing report for the person or process that will transform it.
Why use it?
It identifies file problems that could make loading fail, produce incorrect results, or make later analysis difficult. It recommends which cleanup changes matter most without changing the file.

Skill for Claude CodeCodex

Part of the data-max plugin — 3 skills shipped together

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/insanetic/data-max/data-review
Any agent
npx skills add insanetic/data-max --skill data-review
Clone the repo
git clone --depth 1 https://github.com/insanetic/data-max

Made for: Claude Code, Codex.

Or install data-max, the plugin that ships this one along with the rest of its 3 skills.

Per session 211 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,226 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 $0.00211 $0.03226
Opus 5 $0.00105 $0.01613
Sonnet 5 $0.00042 $0.00645
Haiku 4.5 $0.00021 $0.00323

Measured 2d ago against content hash 01f5693d2dd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-review 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-review/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Max — Data Review

Review a data file for warehouse readiness and tell the user, with reasons, how to cleanse it. The mental model: the user wants to upload this file mostly as-is into a columnar data warehouse and then run analytics and calculations on it. Your job is to find everything that will make that painful or wrong, and to propose the smallest set of changes that buys the biggest benefit — while still showing the ideal target.

This skill reviews; it does not transform. The deliverable is a markdown report (<filename>-review.md) plus a short inline summary. You never hand-edit data and you never write transformation scripts here. When the user wants the cleanup actually done, that report is the hand-off to the data-transform skill (see "Handing off" below).

Core principles

  • Explain the why, every time. A recommendation without a reason is noise. The user often can't change the source freely (it's an export, an API dump, a vendor file), so they need to understand the payoff to decide what's worth it.
  • Tier everything by cost/benefit. Separate what breaks loading from what improves analytics from what's merely nice. See the report template.
  • Minimal viable change first, ideal second. Always give a cheap path that still helps, and the better redesign. Let the user choose. Don't bury them.
  • Denormalization is fine. This is analytics, not OLTP. Duplication that makes one flat, query-friendly table is usually better than textbook 3NF. Don't normalize for its own sake.
  • CSV is the target output. If the input is JSON/XML/Excel, describe the CSV(s) it should become. If it's already CSV, describe the cleaned CSV.

Workflow

  1. Inspect the file yourself. Read it directly — the header row, the first chunk of rows, and the tail (footers hide there). Judge each review dimension by eye:
    • rows that aren't part of the table (title banners, blank separators, repeated mid-table headers, TOTAL footers) and rows whose column count differs from the rest;
    • column-name hygiene (spaces, capitals, punctuation, units-as-symbols, leading digits, blanks, duplicates);
    • money columns stored as text ("$1,234.50") or float;
    • date/datetime columns and whether they're ISO 8601 / RFC 3339;
    • whether any column anchors each row in time;
    • headers that are really period or category values (Jan, Feb, …, 2021, 2022) — the wide-format smell.

Read the full file on GitHub · 255 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 · 255 lines · 211 tokens per session scan A 01f5693d2dd8

Subscribe to this mod's changes

data-review is a skill published in the GitHub repository insanetic/data-max (2 stars, last pushed 3mo ago), licensed MIT. It adds 211 tokens to every session and 3,226 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

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

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

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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