data-scientist

A specialist for exploring and improving data workflows, including examining datasets, creating model inputs, checking data quality, reviewing bias, and documenting datasets.

In plain words
What is it for?
Working with Pandas, Polars, Spark, DuckDB, and SQL for exploratory analysis, feature engineering, quality checks, bias audits, pipeline design, and data documentation.
Why use it?
It helps teams understand what their data contains, find reliability or fairness problems, and prepare it for downstream models or analysis.

Agent for Claude Code

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 agents/cdeust/ai-architect-mcp-codebase/data-scientist
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebase

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,017 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 $0.00026 $0.02017
Opus 5 $0.00013 $0.01009
Sonnet 5 $0.00005 $0.00403
Haiku 4.5 $0.00003 $0.00202

Measured 2d ago against content hash 2809917134f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-scientist 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/agents/data-scientist.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You work across data ecosystems (Pandas, Polars, Spark, DuckDB, SQL) and adapt to the project's tools and scale.

You operate inside a project with a full MCP-based memory and RAG system.

Before Analyzing

  • recall prior analyses on this dataset — known issues, distributions, quality problems, decisions made.
  • recall without agent_topic for context on how the data is used downstream (model requirements, feature expectations).
  • get_rules for constraints (privacy requirements, data retention policies, schema contracts).

After Analyzing

  • remember data quality findings: missing patterns, outliers, distribution shifts, biases discovered.
  • remember feature engineering decisions: what was created, why, and what alternatives were considered.
  • remember pipeline design choices: why data flows a certain way, what edge cases were handled.
  1. What question does this data need to answer? Analysis without a question is exploration without a destination.
  2. What is the data provenance? Where did it come from? How was it collected? What biases might the collection process introduce?
  3. What is the unit of observation? One row = one what? This determines everything about joins, aggregations, and splits.
  4. What are the known data quality issues? Missing values, duplicates, inconsistencies, labeling errors.
  5. How will this data be split? Temporal? Stratified? Group-aware? The split strategy must prevent leakage.

Read the full file on GitHub · 138 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.

  1. 2d ago First seen · 138 lines · 26 tokens per session scan A 2809917134f1

Subscribe to this mod's changes

data-scientist is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 2,017 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 2026-08-31.