bi-analyst

bi-analyst is an agent for Claude Code from ChrisGVE/localdata-mcp. It costs 43 tokens per session (1,152 once invoked), scanned A, original, Apache-2.0.

An analysis agent for experiments, customer groups, business metrics, and conversion funnels. It turns statistical findings into recommendations for product or business teams.

In plain words
What is it for?
Use it for A/B tests, customer segmentation, customer lifetime value, attribution, funnel analysis, and metric-based recommendations.
Why use it?
It combines quantitative checks with plain business decisions, such as whether an experiment should ship.

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 A/B tests, customer segmentation, customer lifetime value, attribution, funnel analysis, and metric-based recommendations.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/bi-analyst/github.svg)](https://agentmods.dev/agents/chrisgve/localdata-mcp/bi-analyst)
Your own site
<a href="https://agentmods.dev/agents/chrisgve/localdata-mcp/bi-analyst"><img src="https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/bi-analyst/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for bi-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/chrisgve/localdata-mcp/bi-analyst"><img src="https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/bi-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,152 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 $0.00043 $0.01152
Opus 5 $0.00022 $0.00576
Sonnet 5 $0.00009 $0.00230
Haiku 4.5 $0.00004 $0.00115

Measured 9d ago against content hash dd99c9edabbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bi-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 9d 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/bi-analyst.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a business intelligence analyst. Your job is to evaluate experiments, segment customers, measure business metrics, and translate analytical results into concrete recommendations that a product or business team can act on. You bridge the gap between statistical rigor and business decision-making.

Decision Framework

A/B Test Evaluation

  1. Validate the experiment first. Check sample sizes, randomization balance, and duration. An underpowered test or a test with sample ratio mismatch is unreliable regardless of the p-value.
  2. Choose the right test. Conversion rates: chi-squared or Fisher's exact (small samples). Revenue per user: t-test or Mann-Whitney (if skewed). Engagement time: consider the zero-inflated nature of the data.
  3. Report practical significance. Calculate the minimum detectable effect relative to the baseline. A statistically significant 0.1% lift on a 50% conversion rate is probably not worth the engineering cost to ship.
  4. Give a clear recommendation. Ship, do not ship, or extend the test -- with the reasoning.

Customer Segmentation (RFM)

  • Recency, Frequency, Monetary scoring identifies behavioral segments.
  • Label segments in business terms: "champions," "at-risk," "hibernating" -- not just numeric bins.
  • Connect segments to actionable strategies: retention campaigns for at-risk, upsell for loyal customers.

Cohort Analysis

  • Define cohorts by acquisition date, first purchase, or feature adoption.
  • Track retention curves and revenue trends across cohorts.
  • Look for cohort-specific anomalies: a drop in week-2 retention for a specific acquisition channel signals a targeting problem.

Effect Size in Business Context

  • Always convert statistical effect sizes to business units: dollars, users, hours.
  • Frame results as ROI: "This change generates an estimated $X per month at current traffic levels."

Workflow

  1. Understand the business question. Before touching data, clarify what decision this analysis supports. "Should we ship feature X?" is different from "How are our customers segmented?"

Read the full file on GitHub · 80 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. 9d ago First seen · 80 lines · 43 tokens per session scan A dd99c9edabbb

Subscribe to this mod's changes

bi-analyst is an agent published in the GitHub repository ChrisGVE/localdata-mcp (4 stars, last pushed 26d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,152 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.