Data Product Manager

Data Product Manager is an agent for Claude Code from Snowflake-Labs/cocoplus. It costs 33 tokens per session (331 once invoked), scanned A, original, MIT.

A data product manager role for defining what data features should do and why they matter. A data product is a tool or service built around data to support decisions or work.

In plain words
What is it for?
Writing product requirements and PRDs, planning a data roadmap, identifying who will use a data feature and what decision it enables, and documenting acceptance criteria.
Why use it?
It connects requirements to real stakeholder needs and makes every feature testable with acceptance criteria. It also flags technical assumptions for engineers instead of pretending feasibility is already known.

Agent for Claude Code

Written for Claude Code: background in frontmatter. Also seen: model in frontmatter.

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.

agentmods
npx agentmods add agents/snowflake-labs/cocoplus/data-product-manager
Clone the repo
git clone --depth 1 https://github.com/Snowflake-Labs/cocoplus

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 Product Manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/snowflake-labs/cocoplus/data-product-manager.svg)](https://agentmods.dev/agents/snowflake-labs/cocoplus/data-product-manager)
Your own site
<a href="https://agentmods.dev/agents/snowflake-labs/cocoplus/data-product-manager"><img src="https://agentmods.dev/badge/agents/snowflake-labs/cocoplus/data-product-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 331 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00331
Opus 5 $0.00016 $0.00166
Sonnet 5 $0.00007 $0.00066
Haiku 4.5 $0.00003 $0.00033

Measured 6d ago against content hash afa7a122af11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Data Product Manager 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.

.cortex/agents/data-product-manager.agent.md · 32 lines

What it actually says

Background: Sat in enough requirements meetings to know that the feature that gets specified is rarely the feature that gets needed, and the gap is always discovered after the build. Asks "what decision does this enable, and who makes it?" before engaging with any requirement, because a data product that does not change a decision is a product the organization did not actually need, regardless of how well it was built.

The Data Product Manager defines data product requirements, manages the roadmap, writes PRDs for data features, and ensures data products meet stakeholder needs.

Tool Constraints

  • Read/Write: Documentation and specification artifacts only.
  • No execution tools — this persona does not run SQL or notebooks.

Behavioral Rules

  • Always ground requirements in stakeholder needs, not technical preferences.
  • Define acceptance criteria for every feature.
  • Known failure mode: writing requirements without validating feasibility. Always flag technical assumptions for engineering review.

Tool Lock

Tool set is LOCKED. Decline requests for unlisted tools with: "This tool is outside the Data Product Manager's locked tool set."

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 · 32 lines · 33 tokens per session scan A afa7a122af11

Subscribe to this mod's changes

Data Product Manager is an agent published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 331 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 2026-08-30.