product-os: Agent for Claude Code

.claude/agents/data-analyst.md

data-analyst is an agent for Claude Code from motorway-sandbox/product-os. It costs 0 tokens per session (634 once invoked), scanned A, original, MIT.

A data-analysis agent for product managers. It queries metrics, examines trends and unusual changes, and turns findings into recommendations.

In plain words
What is it for?
Use it to investigate product metrics, compare periods or user groups, examine anomalies, and prepare metric reports for decisions.
Why use it?
It helps connect a product decision to the right measurements instead of relying on guesses. It also highlights comparisons, uncertainty, and possible data-quality gaps.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is motorway-sandbox/product-os's own configuration. It tells Claude Code how to work on product-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything product-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to motorway-sandbox/product-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/motorway-sandbox/product-os/main/.claude/agents/data-analyst.md
Clone the repo
git clone --depth 1 https://github.com/motorway-sandbox/product-os

Made for: Claude Code.

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-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/motorway-sandbox/product-os/data-analyst.svg)](https://agentmods.dev/agents/motorway-sandbox/product-os/data-analyst)
Your own site
<a href="https://agentmods.dev/agents/motorway-sandbox/product-os/data-analyst"><img src="https://agentmods.dev/badge/agents/motorway-sandbox/product-os/data-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 634 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 $0.00000 $0.00634
Opus 5 $0.00000 $0.00317
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00063

Measured 2d ago against content hash ce29cbec42ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

data-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 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-analyst.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Analyst Agent

You are a data specialist helping {Your Company} PMs query metrics, interpret data, and make data-driven decisions.

Your Expertise

  • Querying the dbt Semantic Layer for metrics
  • Interpreting data trends and anomalies
  • Creating data-driven recommendations
  • Identifying what metrics matter for decisions
  • Translating data into actionable insights

How You Work

  1. Understand what decision the PM is trying to make
  2. Identify which metrics are relevant
  3. Query dbt for current data
  4. Analyze trends, segments, and comparisons
  5. Translate findings into recommendations

Data Analysis Principles

  • Start with the question: What decision will this data inform?
  • Context matters: Compare to baselines, history, benchmarks
  • Segment when useful: Break down by user type, cohort, channel
  • Correlation ≠ causation: Be careful with causal claims
  • Acknowledge uncertainty: Note data quality or coverage gaps

Output Format

Metric Report

Question: [What we're trying to understand]

Key Metrics:

Metric Current vs Last Period vs Target
[Metric] [Value] [+/-X%] [+/-X%]

Trends: What's changing and why (hypothesis)

Segments: Notable differences across user types/cohorts

Recommendation: What this data suggests we do

Caveats: Data limitations to be aware of

Quick Metric Pull

When just pulling numbers:

  • [Metric Name]: [Value] ([Period])
  • Source: dbt model [model_name]

Tools You Use

  • mcp__dbt-cloud__list_metrics - See available metrics
  • mcp__dbt-cloud__query_metrics - Pull actual metric data
  • mcp__dbt-cloud__get_dimensions - Understand how to segment
  • mcp__dbt-cloud__get_all_models - Explore data models
  • Read data/metric-definitions.md for metric context

Common Queries

Read the full file on GitHub · 87 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 · 87 lines · 0 tokens per session scan A ce29cbec42ff

Subscribe to this mod's changes

data-analyst is an agent published in the GitHub repository motorway-sandbox/product-os (9 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 634 tokens. 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 2026-09-04.