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-problem-briefgit 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-problem-brief)<a href="https://agentmods.dev/commands/hollandkevint/data-product-operator/write-problem-brief"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/write-problem-brief.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 | $0.00020 | $0.01127 |
| Opus 5 | $0.00010 | $0.00563 |
| Sonnet 5 | $0.00004 | $0.00225 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
write-problem-brief 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write a Problem Brief
Convert raw discovery inputs (interview notes, Slack exports, meeting notes, support tickets, query logs) into a structured problem brief using the atomic research method adapted for data products.
Gather Inputs
If $ARGUMENTS provides file paths, read them. Accept any combination of:
- Interview transcripts or notes
- Slack thread exports
- Meeting notes (Granola, manual, or any format)
- Support tickets or bug reports
- Query log summaries
- Previous discovery briefs
- Raw pasted text
If no arguments provided, ask:
Question 1: What discovery inputs do you have? Provide file paths, paste text, or describe what you've gathered.
Question 2: What problem area are these inputs about? (1 sentence to anchor the synthesis)
Extract Nuggets
Read all inputs and extract atomic observations. One fact per nugget.
Format each nugget:
[Source type: Name, Role, Date] Observation
Tag each nugget with:
- Source type: interview, log, ticket, observation, slack, meeting
- Consumer segment: Explorer, Reporter, Decision-maker, Builder (see
data-consumer-discovery) - Topic: short keyword for grouping
CRITICAL: Preserve specifics. "Spends 4 hours every Monday" not "spends significant time." "$2,847 per incident" not "costly errors." Numbers and names make evidence credible.
Find Patterns
Group nuggets by topic. A pattern requires 3+ nuggets from independent sources.
For each pattern:
- State the pattern in one sentence
- List the supporting nuggets (with source attribution)
- Note the consumer segments affected
- Flag any contradictory evidence (see
research-synthesis-datacontradictory evidence rules)
Patterns with fewer than 3 sources are flagged as "Emerging" and excluded from the top problems.
Derive Insights
For each pattern, answer "so what?" in the context of data product decisions.
Connect each insight to a downstream action:
- Problem to solve → feeds
/dpo:write-data-prd - Data source to audit → feeds
/dpo:review-data-quality - Consumer need to validate → feeds
/dpo:run-discoveryon a specific sub-problem - Stakeholder to align → feeds
/dpo:write-stakeholder-brief
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 · 150 lines · 20 tokens per session scan A ab81b5af464a
write-problem-brief is a command published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 1,127 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.
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.