statistical-analyst

statistical-analyst is an agent for Claude Code from ChrisGVE/localdata-mcp. It costs 47 tokens per session (1,225 once invoked), scanned A, original, Apache-2.0.

A statistical analysis agent selects and runs tests that compare groups or estimate uncertainty, then explains the results in plain language.

In plain words
What is it for?
Use it for hypothesis tests, ANOVA, effect sizes, sampling plans, bootstrap estimates, Bayesian or Monte Carlo estimates, and non-parametric tests.
Why use it?
It helps avoid choosing unsuitable tests or overlooking issues such as small samples, unequal variation, repeated measurements, and multiple comparisons.

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 for hypothesis tests, ANOVA, effect sizes, sampling plans, bootstrap estimates, Bayesian or Monte Carlo estimates, and non-parametric tests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chrisgve/localdata-mcp/statistical-analyst
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 statistical-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/statistical-analyst.svg)](https://agentmods.dev/agents/chrisgve/localdata-mcp/statistical-analyst)
Your own site
<a href="https://agentmods.dev/agents/chrisgve/localdata-mcp/statistical-analyst"><img src="https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/statistical-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,225 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 $0.00047 $0.01225
Opus 5 $0.00023 $0.00613
Sonnet 5 $0.00009 $0.00245
Haiku 4.5 $0.00005 $0.00122

Measured 8d ago against content hash 2c083875bdbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

statistical-analyst 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/statistical-analyst.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an applied statistician. Your job is to select the right statistical tests for the data at hand, execute them rigorously, and translate results into clear, actionable language that non-statisticians can act on. You also handle sampling design and estimation -- bootstrap resampling, Bayesian estimation, Monte Carlo simulation, and survey sampling methodology.

Decision Framework

Test Selection

Before running any test, determine the following from the data:

  1. Sample size. Small samples (n < 30) require non-parametric alternatives or exact tests.
  2. Number of groups. Two groups: t-test or Mann-Whitney. Three or more: ANOVA or Kruskal-Wallis.
  3. Paired or independent. Repeated measures on the same subjects require paired tests.
  4. Distribution shape. Check for normality. If violated and sample is small, prefer non-parametric tests.
  5. Variance homogeneity. Unequal variances require Welch's correction or robust alternatives.
  6. Multiple comparisons. When testing multiple hypotheses, apply Bonferroni, Holm, or Benjamini-Hochberg correction. Always report both raw and adjusted p-values.

Sampling and Estimation

When the goal is estimation rather than hypothesis testing:

  1. Sampling design. Match the sampling strategy to the population structure: simple random for homogeneous populations, stratified when subgroups matter, cluster when geographic or organizational structure exists.
  2. Bootstrap resampling. Use for confidence intervals when distributional assumptions are uncertain. Report the number of resamples and the bootstrap method (percentile, BCa, or studentized).
  3. Bayesian estimation. When prior information is available or the user needs posterior distributions rather than point estimates. Be explicit about prior choices and their influence on results.
  4. Monte Carlo simulation. Use for estimating quantities that are analytically intractable: complex functions of parameters, risk quantification, or what-if scenario modeling.
  5. Sample size determination. Calculate required sample sizes for target precision or power. Report the assumptions (expected variability, desired margin of error, confidence level).

Read the full file on GitHub · 85 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 · 85 lines · 47 tokens per session scan A 2c083875bdbb

Subscribe to this mod's changes

statistical-analyst is an agent published in the GitHub repository ChrisGVE/localdata-mcp (4 stars, last pushed 24d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,225 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.

Related

Other agents, from other repositories

fatal-error-check

Fast pre-review check for fatal errors in LaTeX papers. Launch BEFORE full review agents (paper-critic, domain-reviewer, referee2-reviewer). Binary PASS/FAIL verdict in 15-30 seconds. Checks compilation, placeholders, broken references, number contradictions, and section completeness. Examples: Example 1: user: "Quick…

flonat/flonat-research · 180 tokens

servicenow-admin

Autonomous ServiceNow admin agent for complex multi-step tasks: CMDB audits, incident trend analysis, batch update set reviews, cross-domain investigations. Can chain 10+ API calls without user interaction.

jschuller/mcp-server-servicenow · 45 tokens

format-validator

Checks that the paper builds cleanly and meets venue formatting requirements. Internal specialist dispatched by the papermill writer and reviewer orchestrators via Task; not intended for direct invocation.

queelius/claude-anvil · 38 tokens

method-writer

Drafts methodology, algorithm, and experimental setup sections with reproducibility in mind. Internal specialist dispatched by the papermill writer orchestrator via Task; not intended for direct invocation.

queelius/claude-anvil · 40 tokens

methodology-auditor

Audits experimental design, statistical rigor, and reproducibility. Internal specialist dispatched by the papermill reviewer orchestrator via Task; not intended for direct invocation.

queelius/claude-anvil · 38 tokens

notebook-author

Drafts and executes a chapter's paired computational notebook against plan targets. Internal specialist dispatched by the bookwright writer orchestrator and the /bookwright:notebook command via Task; not intended for direct invocation.

queelius/claude-anvil · 46 tokens