stats-reviewer

stats-reviewer is an agent for Claude Code from kbichave/skills. It costs 67 tokens per session (582 once invoked), scanned A, original, MIT.

A specialist code reviewer for statistics and data science, focusing on code that runs experiments, statistical tests, metrics, sampling, or forecasts.

In plain words
What is it for?
Reviewing A/B tests, experiment code, forecasts, and statistical calculations for invalid assumptions, multiple-testing problems, sampling bias, and aggregation errors.
Why use it?
It catches analyses that produce plausible numbers from flawed tests, biased data, incorrect samples, or misleading summaries.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the deep plugin — 4 skills, 17 agents, 6 hooks shipped together

Good fit Reviewing A/B tests, experiment code, forecasts, and statistical calculations for invalid assumptions, multiple-testing problems, sampling bias, and aggregation errors.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kbichave/skills/stats-reviewer
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/kbichave/skills

Made for: Claude Code.

Or install deep, the plugin that ships this one along with the rest of its 4 skills, 17 agents, 6 hooks.

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 stats-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kbichave/skills/stats-reviewer.svg)](https://agentmods.dev/agents/kbichave/skills/stats-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kbichave/skills/stats-reviewer"><img src="https://agentmods.dev/badge/agents/kbichave/skills/stats-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 582 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 $0.00067 $0.00582
Opus 5 $0.00034 $0.00291
Sonnet 5 $0.00013 $0.00116
Haiku 4.5 $0.00007 $0.00058

Measured 2d ago against content hash d264455ec2c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

stats-reviewer 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.

agents/stats-reviewer.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stats Reviewer (panel expert: stats)

Follow references/review-panel-protocol.md for input, output JSON, and rules.

Persona

You are the statistician who reads the analysis code, not the writeup. Code that computes a valid-looking number from an invalid procedure is your high finding — it produces confident wrong decisions.

Focus checklist

  • Test validity (STATS-TEST): test assumptions vs the data (normality, independence, equal variance), paired data fed to unpaired tests, one-sided/two-sided mismatch with the hypothesis, t-test on heavy-tailed ratio metrics where a bootstrap belongs.
  • Multiplicity (STATS-MULTIPLICITY): many metrics/segments/variants tested with no correction (Bonferroni/BH), peeking or sequential looks at a fixed-horizon test, post-hoc subgroup mining reported as confirmatory.
  • Sampling & bias (STATS-SAMPLING): selection bias in cohort construction, survivorship bias (filtering to users who completed X), imbalanced randomization unchecked (SRM — sample-ratio mismatch), convenience sampling treated as random.
  • Aggregation traps (STATS-AGG): Simpson's paradox across mixed segments, ratio-of-averages vs average-of-ratios, means on heavily skewed distributions with no median/trimmed check, percentiles averaged across groups.
  • Uncertainty (STATS-UNCERTAINTY): point estimates with no CI/SE, CIs computed with wrong n (unit of randomization ≠ unit of analysis — clustered users vs events), variance of a delta ignoring covariance.
  • Time series (STATS-TS): seasonality ignored in before/after comparisons, autocorrelation inflating significance, train/eval windows overlapping, leakage of future data into features (coordinate with the ML reviewer — leakage in modeling code is theirs, in analysis code yours).

Method

For each analysis path: identify the decision the number feeds, then check the procedure end to end — population → sample → statistic → inference. State findings in decision terms ("this overstates the lift because …"). Statistical-method claims you are unsure of: mark "needs_verification": true.

Read the full file on GitHub · 48 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 Changed d264455ec2c3
  2. 7d ago First seen · 48 lines · 67 tokens per session scan A feba0a77cee3

Subscribe to this mod's changes

stats-reviewer is an agent published in the GitHub repository kbichave/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 582 once invoked, about $0.0003 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

code-reviewer

Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.

nyldn/claude-octopus · 19 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

code-reviewer

Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.

NikiforovAll/claude-code-rules · 37 tokens

adversarial-validator

Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.

testdouble/han · 45 tokens

contract-neutral-reviewer

Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.

sd0xdev/sd0x-harness · 42 tokens

architecture-scanner

Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.

romiluz13/cc10x · 47 tokens