product-os: Command for Claude Code

.claude/commands/investigate.md

investigate is a command for Claude Code from motorway-sandbox/product-os. It costs 0 tokens per session (1,979 once invoked), scanned A, original, MIT.

A command for investigating a question or signal by combining measurements, written evidence, and evidence that may disagree.

In plain words
What is it for?
It is for examining metric changes, checking definitions and baselines, comparing segments and time periods, and producing an investigation summary.
Why use it?
It turns a vague change or concern into a stated hypothesis and suggested next steps without stopping for clarification.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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/commands/investigate.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 investigate

README.md
[![agentmods](https://agentmods.dev/badge/commands/motorway-sandbox/product-os/investigate/github.svg)](https://agentmods.dev/commands/motorway-sandbox/product-os/investigate)
Your own site
<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/investigate"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/investigate/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 investigate

Your own site · 80×15
<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/investigate"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/investigate.svg" alt="Reviewed on agentmods" width="80" 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 1,979 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 $0.01979
Opus 5 $0.00000 $0.00989
Sonnet 5 $0.00000 $0.00396
Haiku 4.5 $0.00000 $0.00198

Measured 6d ago against content hash 6db858e575dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

investigate 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 6d 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/commands/investigate.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Investigate

You have been given a signal or question to investigate: $ARGUMENTS

Run a structured investigation combining quantitative data, qualitative evidence, and counter-evidence. Produce a hypothesis and recommended next steps.

Important: Do NOT ask any clarifying questions. Do NOT pause for user input. Run the entire investigation in one pass.

Step 1: Parse the signal

Extract from the user's input:

  • Metric: What is being measured (e.g. step completion rate, sign-up-to-activation, churn rate)
  • Segment: Any filters (e.g. Android, new users, enterprise accounts)
  • Timeframe: When (e.g. this week, since app release, Q1). Default to "recent" if not specified
  • Direction: What changed (e.g. dropped, increased, anomaly)

State these clearly before proceeding.

Step 2: Quantitative investigation

Run these searches in parallel:

2a. Metric definitions and baselines

  • Read data/funnel-context.md for metric definitions, baselines, and how to interpret the metric (leading vs lagging)
  • Read context/current-priorities.md to check if this metric relates to a current goal or target

2b. Data warehouse query (if MCP available)

  • Use dbt Semantic Layer tools to search for relevant metrics (list_metrics, query_metrics)
  • Use get_all_models or get_mart_models to find relevant dbt models
  • Query BigQuery directly if the right table is identified
  • Follow the conventions in your data warehouse conventions

2c. Saved data files (always — as fallback or supplement)

  • Search data/ folder for CSV files, saved reports, and metric files matching the signal keywords
  • Search for any weekly business review (WBR) data or funnel detail files
  • Grep across the repo for the specific metric values or trend references

Record: what the data says, the source, the time period, and confidence level (High / Medium / Low).

Read the full file on GitHub · 201 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. 6d ago First seen · 201 lines · 0 tokens per session scan A 6db858e575dc

Subscribe to this mod's changes

investigate is a command 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 1,979 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.