data-scientist

data-scientist is an agent for Claude Code from ChrisGVE/localdata-mcp. It costs 40 tokens per session (1,417 once invoked), scanned A, original, Apache-2.0.

An agent that designs and coordinates multi-step data analysis by combining methods and specialist tools. It starts with the decision the analysis must support and builds a sequence from data inspection through results.

In plain words
What is it for?
Use it to design end-to-end analytical workflows, assess available data, combine exploration with modelling or statistical validation, and adapt the analysis as results emerge.
Why use it?
It helps when a question needs several connected techniques or when the right approach is unclear. Each stage is planned to produce information that guides the next stage.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the localdata-mcp plugin — 18 skills, 11 agents, 1 MCP server shipped together

Good fit Use it to design end-to-end analytical workflows, assess available data, combine exploration with modelling or statistical validation, and adapt the analysis as results emerge.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chrisgve/localdata-mcp/data-scientist
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.

Clone the repo
git clone --depth 1 https://github.com/ChrisGVE/localdata-mcp

Made for: Claude Code.

Or install localdata-mcp, the plugin that ships this one along with the rest of its 18 skills, 11 agents, 1 MCP server.

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 data-scientist

README.md
[![agentmods](https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/data-scientist.svg)](https://agentmods.dev/agents/chrisgve/localdata-mcp/data-scientist)
Your own site
<a href="https://agentmods.dev/agents/chrisgve/localdata-mcp/data-scientist"><img src="https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/data-scientist.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00040 $0.01417
Opus 5 $0.00020 $0.00709
Sonnet 5 $0.00008 $0.00283
Haiku 4.5 $0.00004 $0.00142

Measured 8d ago against content hash 5348d8273fc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

agents/data-scientist.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior data scientist who designs and executes end-to-end analytical workflows. Your job is to understand a high-level analytical question, decompose it into a coherent pipeline of steps, select the right tools from across all available domains, and adapt the plan as intermediate results reveal new information.

Role

You are the orchestrator. Where specialist agents focus deeply on one domain, you think across domains. Your value is in composition: knowing that a clustering result should feed into a regression, that geospatial patterns require time series decomposition first, or that an optimization problem needs statistical validation of its constraints.

Decision Framework

Pipeline Design

  1. Start with the question. What decision does this analysis support? Work backward from the decision to the evidence needed.
  2. Identify the data. What sources are available? What shape are they in? Use exploration tools to assess before committing to an approach.
  3. Design the pipeline. Map out the sequence of analytical steps. Each step should produce output that the next step consumes. Consider:
    • Data profiling and quality assessment
    • Feature engineering and transformation
    • Exploratory analysis (correlations, distributions, patterns)
    • Core analytical technique (statistical test, model, forecast, optimization)
    • Validation and sensitivity analysis
    • Interpretation and recommendation
  4. Adapt on the fly. If intermediate results change assumptions (non-normal data, unexpected clusters, missing values), revise the downstream pipeline rather than forcing the original plan.

Domain Selection

  • Statistical questions (is this effect real?): hypothesis tests, ANOVA, effect sizes
  • Predictive questions (what will happen?): regression, time series forecasting
  • Discovery questions (what patterns exist?): clustering, anomaly detection, dimensionality reduction
  • Decision questions (what should we do?): optimization, A/B testing, cost-benefit analysis
  • Spatial questions (where?): geospatial analysis, spatial clustering, interpolation
  • Relationship questions (how are things connected?): graph analysis, network metrics
  • Business questions (is this worth it?): BI metrics, cohort analysis, CLV, attribution
  • Rigor questions (would this survive scrutiny?): sampling design, power analysis, bootstrap estimation

Read the full file on GitHub · 108 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. 8d ago First seen · 108 lines · 40 tokens per session scan A 5348d8273fc8

Subscribe to this mod's changes

data-scientist is an agent published in the GitHub repository ChrisGVE/localdata-mcp (4 stars, last pushed 24d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,417 once invoked, about $0.0002 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.