dataset_profiler

dataset_profiler is a skill for Claude Code, Codex from brevdev/workshop-build-an-agent. It costs 22 tokens per session (395 once invoked), scanned A, original, Apache-2.0.

A procedure for examining an unfamiliar CSV file or data table and reporting its shape, columns, missing values, duplicates, distributions, and notable patterns.

In plain words
What is it for?
It helps profile datasets before analysis by checking column types, nulls, duplicates, suspicious values, unique-value counts, and three important findings.
Why use it?
It replaces guesses about a dataset with measured information about its structure and data quality.

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/brevdev/workshop-build-an-agent/dataset_profiler
Any agent
npx skills add brevdev/workshop-build-an-agent --skill dataset_profiler
Clone the repo
git clone --depth 1 https://github.com/brevdev/workshop-build-an-agent

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 dataset_profiler

README.md
[![agentmods](https://agentmods.dev/badge/skills/brevdev/workshop-build-an-agent/dataset_profiler.svg)](https://agentmods.dev/skills/brevdev/workshop-build-an-agent/dataset_profiler)
Your own site
<a href="https://agentmods.dev/skills/brevdev/workshop-build-an-agent/dataset_profiler"><img src="https://agentmods.dev/badge/skills/brevdev/workshop-build-an-agent/dataset_profiler.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 395 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 $0.00022 $0.00395
Opus 5 $0.00011 $0.00198
Sonnet 5 $0.00004 $0.00079
Haiku 4.5 $0.00002 $0.00040

Measured 4d ago against content hash 5b97cc2ded4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dataset_profiler 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 4d 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.

code/7-agent-harnesses/skills/.examples/dataset_profiler/SKILL.md · 46 lines

What it actually says

Dataset Profiler Skill

You are profiling an unfamiliar dataset. Follow this procedure in order and report findings in the output format below. Prefer running small scripts over guessing; never describe data you have not inspected.

Procedure

  1. Shape & size — row count, column count, file size on disk.
  2. Schema — every column with its dtype; flag columns whose dtype looks wrong for the name (e.g. numeric IDs parsed as float, dates as object).
  3. Nulls — per-column null counts; call out any column over 5% null.
  4. Duplicates — count of fully duplicated rows.
  5. Numeric distributions — min / max / mean / std for numeric columns; flag impossible values (negative ages, future dates, sentinel -999s).
  6. Cardinality — unique-value counts for object columns; identify likely categorical columns (low cardinality) vs identifiers (cardinality ≈ rows).
  7. Three surprising facts — the three most decision-relevant things a human should know before using this data.

Output format

## Dataset Profile: <path>
- Shape: <rows> x <cols> (<size>)
- Schema: <table or list>
- Quality: <nulls, duplicates, suspicious values>
- Highlights:
  1. ...
  2. ...
  3. ...

Notes

  • For datasets over 100,000 rows on GPU-equipped machines, prefer GPU-accelerated profiling (e.g. cudf.pandas) and keep intermediate results on the GPU.
  • If the file fails to parse, report the first malformed line rather than silently switching parsers.
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. 4d ago First seen · 46 lines · 22 tokens per session scan A 5b97cc2ded4f

Subscribe to this mod's changes

dataset_profiler is a skill published in the GitHub repository brevdev/workshop-build-an-agent (133 stars, last pushed 16d ago), licensed Apache-2.0. It adds 22 tokens to every session and 395 once invoked, about $0.0001 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

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