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.
npx agentmods add commands/hollandkevint/data-product-operator/write-data-prdgit clone --depth 1 https://github.com/hollandkevint/data-product-operatorWrote 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.
[](https://agentmods.dev/commands/hollandkevint/data-product-operator/write-data-prd)<a href="https://agentmods.dev/commands/hollandkevint/data-product-operator/write-data-prd"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/write-data-prd.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00011 | $0.01104 |
| Opus 5 | $0.00005 | $0.00552 |
| Sonnet 5 | $0.00002 | $0.00221 |
| Haiku 4.5 | $0.00001 | $0.00110 |
Grade A, and why
write-data-prd scanned grade A with 1 finding 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 4d 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.
Strips warnings and disclaimerslowAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
If none of these apply, state "No ethical considerations identified" with a brief justification. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write a Data Product PRD
Generate a requirements document for a data product. This is not a standard software PRD. Data products require sections for data lineage, quality SLAs, consumer contracts, and ethical considerations that typical PRDs skip.
Gather Context
If $ARGUMENTS provides a product name or description, use it. Otherwise, ask:
Question 1: What data product are you building? Describe the problem it solves.
Question 2: Who consumes the output? Options: analysts, clinicians, executives, data scientists, external API consumers, end users.
Question 3: What data sources are involved? List the databases, APIs, files, or systems this product depends on.
Question 4: What are the quality requirements? Consider: maximum acceptable latency, accuracy threshold, data freshness SLA, uptime requirement.
Write the PRD
Write the document to data-prd-<name>.md where <name> is a kebab-case version of the product name.
Use this structure:
1. Problem Statement
State the problem in one paragraph. Include:
- Who has this problem (specific role, not "users")
- What they currently do (the workaround)
- Evidence the problem is real (customer quotes, usage data, support tickets)
- What success looks like (measurable outcome)
NEVER write a problem statement without evidence. "We think users want X" is not a problem statement.
2. Data Sources and Lineage
For each data source:
- Source system name and type (database, API, file, stream)
- Refresh frequency (real-time, hourly, daily, batch)
- Volume estimate (rows/day, GB)
- Known quality issues
- Access method and credentials needed
Include a lineage diagram showing source -> transformation -> output flow.
3. Consumer Contracts
For each consumer of this data product:
- Who they are (role or system name)
- What format they need (API, file, dashboard, embedded)
- What SLA they expect (latency, freshness, uptime)
- What schema/fields they require
- How they access it (pull vs push, auth method)
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.
- 4d ago First seen · 123 lines · 11 tokens per session scan A 02de93e61f30
write-data-prd is a command published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 1,104 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
quick-prd
Generate a complete PRD with competitive analysis in one workflow.
ompm
Oh-My-PM 的全局入口：理解你想做什么，路由到最合适的 skill 或 workflow。.
full-pm-cycle
编排从市场研究到上线后分析的完整产品管理周期.
feature-launch
编排从 PRD 到上线后分析的完整功能发布工作流.
ceo-review
Run a CEO-level strategic review of a feature before development.
init
Install the formatters this repository needs, with every command visible before it runs.