run-discovery

run-discovery is a command for Claude Code from hollandkevint/data-product-operator. It costs 25 tokens per session (1,117 once invoked), scanned A, original, MIT.

A guided conversation for deciding whether a new data product idea is worth pursuing. It asks about the problem, users, past behavior, data sources, trust, and current workarounds, then recommends whether to proceed, investigate further, or stop.

In plain words
What is it for?
Use it to explore a data product idea, interview potential users, document existing manual work, and produce a go, investigate, or kill recommendation.
Why use it?
It reduces the risk of building a data product that nobody needs or trusts by testing the problem against real evidence before development begins.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the data-product-operator plugin — 18 skills, 7 commands, 1 MCP server shipped together

Good fit Use it to explore a data product idea, interview potential users, document existing manual work, and produce a go, investigate, or kill recommendation.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/hollandkevint/data-product-operator/run-discovery
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/hollandkevint/data-product-operator

Made for: Claude Code.

Or install data-product-operator, the plugin that ships this one along with the rest of its 18 skills, 7 commands, 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 run-discovery

README.md
[![agentmods](https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/run-discovery/github.svg)](https://agentmods.dev/commands/hollandkevint/data-product-operator/run-discovery)
Your own site
<a href="https://agentmods.dev/commands/hollandkevint/data-product-operator/run-discovery"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/run-discovery/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 run-discovery

Your own site · 80×15
<a href="https://agentmods.dev/commands/hollandkevint/data-product-operator/run-discovery"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/run-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,117 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 $0.00025 $0.01117
Opus 5 $0.00013 $0.00558
Sonnet 5 $0.00005 $0.00223
Haiku 4.5 $0.00003 $0.00112

Measured 9d ago against content hash 78e20dbe8e37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

run-discovery 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.

commands/run-discovery.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a Data Product Discovery Session

Guide a structured discovery conversation for a new data product idea. This command combines consumer discovery questions with a validation scorecard to produce a go/investigate/kill recommendation.

Gather Context

If $ARGUMENTS provides a product idea or problem area, use it as the starting point. Otherwise, ask:

Question 1: What problem area are you exploring? Describe it in terms of the decision someone needs to make, not the data they want.

Run Discovery Questions

Ask these questions one at a time. Wait for each answer before proceeding. Each question builds on the prior answer.

Question 2: Who are the consumers of this data? What decisions do they make with it? (Reference data-consumer-discovery consumer segments: Explorers, Reporters, Decision-makers, Builders.)

Question 3: Walk me through the last time someone needed this data. Where did it come from? How long did it take? What did they trust or distrust about it?

Question 4: What workarounds exist today? Describe any manual processes, Excel files, scripts, or tools people have built to solve this problem. For each workaround, capture: tool used, frequency, time cost per use, trust level, downstream dependents.

Question 5: What would make consumers NOT trust this output? List specific concerns: source opacity, staleness, conflicting numbers, past incidents, no validation path.

Question 6: If consumers could get this answer in under a minute, what changes? Describe the business impact in specific terms: decisions made faster, costs avoided, risks caught earlier.

Score the Validation Scorecard

After collecting discovery answers, score each dimension 1-5 based on the evidence gathered. Reference data-product-validation for scoring criteria.

Explain your reasoning for each score in 1-2 sentences.

  1. Demand Frequency (1-5): How often do consumers need this answer?
  2. Decision Impact (1-5): What happens when they don't have it?
  3. Workaround Effort (1-5): What are they doing today instead?
  4. Data Feasibility (1-5): Can we build this with available data?
  5. Schema Risk (1-5): How locked-in are consumers once we ship?

Read the full file on GitHub · 116 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 · 116 lines · 25 tokens per session scan A 78e20dbe8e37

Subscribe to this mod's changes

run-discovery is a command published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 1,117 once invoked, about $0.0001 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.