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.
git 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-stakeholder-brief)<a href="https://agentmods.dev/commands/hollandkevint/data-product-operator/write-stakeholder-brief"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/write-stakeholder-brief/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.
<a href="https://agentmods.dev/commands/hollandkevint/data-product-operator/write-stakeholder-brief"><img src="https://agentmods.dev/badge/commands/hollandkevint/data-product-operator/write-stakeholder-brief.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00014 | $0.00698 |
| Opus 5 | $0.00007 | $0.00349 |
| Sonnet 5 | $0.00003 | $0.00140 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
write-stakeholder-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 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write a Stakeholder Brief
Translate technical data product work into a concise business-facing summary. The audience is executives, business stakeholders, or cross-functional partners who need to understand impact without technical depth.
Gather Context
If $ARGUMENTS describes the project, use it. Otherwise, ask:
Question 1: What data product work are you summarizing? (feature shipped, project milestone, quarterly update)
Question 2: Who is the audience? Options: C-suite, VP-level, business partners, cross-functional team, board.
Question 3: What's the most important thing they need to know? (impact achieved, decision needed, risk to flag, resource request)
Question 4: What metrics or results can you share? (specific numbers preferred: revenue impact, time saved, adoption rate, quality improvement)
Write the Brief
Write to stakeholder-brief-<name>.md where <name> is a kebab-case identifier.
Target length: 1 page (300-500 words). Executives skim. Every sentence must earn its place.
Output Structure
# [Project Name]: Stakeholder Brief
**Date:** [today]
**Status:** [On Track / At Risk / Completed / Needs Decision]
**Owner:** [team or person]
## Bottom Line
[2-3 sentences: what happened, what it means for the business, what comes next. Lead with the most important fact.]
## Impact
[Quantified results in business terms, not technical terms]
- [Metric 1]: [value] ([comparison or trend])
- [Metric 2]: [value] ([comparison or trend])
- [Metric 3]: [value] ([comparison or trend])
## What We Did
[3-5 bullet points describing the work in business language. No jargon. No architecture diagrams. Focus on what changed for the user or customer.]
## What's Next
[2-3 bullet points on upcoming milestones, decisions needed, or dependencies]
## Risks or Asks
[Only if applicable. Flag blockers, resource needs, or decisions that need escalation. Skip this section entirely if there are none.]
Writing Rules
ALWAYS lead with the outcome, not the process. "Reduced report generation time from 45 minutes to 5 seconds" not "We optimized the ETL pipeline and migrated to a columnar database."
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.
- 9d ago First seen · 75 lines · 14 tokens per session scan A 0e8a8fb89807
write-stakeholder-brief is a command published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 698 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
A general entry point that interprets a request and sends it to the most suitable product-management guide or workflow. Product management covers deciding what to build, why to build it, and how to deliver it.
full-pm-cycle
A command that coordinates product management from researching a market and users through planning, design, delivery, and measuring results.
feature-launch
A command that coordinates a feature from its product requirements document through release and analysis after launch. A product requirements document describes what a feature should do and why.
ceo-review
Run a CEO-level strategic review of a feature before development.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.