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 skills add hollandkevint/data-product-operator --skill data-team-positioninggit 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/skills/hollandkevint/data-product-operator/data-team-positioning)<a href="https://agentmods.dev/skills/hollandkevint/data-product-operator/data-team-positioning"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/data-team-positioning/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/skills/hollandkevint/data-product-operator/data-team-positioning"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/data-team-positioning.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 | $0.00070 | $0.00975 |
| Opus 5 | $0.00035 | $0.00487 |
| Sonnet 5 | $0.00014 | $0.00195 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
data-team-positioning 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three Stances
Data teams operate in one of three positions. Most are stuck at position 1.
1. Request Taker
"Tell us what to build." The backlog is a queue of stakeholder requests. Prioritization is based on who asked loudest or most recently. The team is measured on throughput: stories completed, dashboards shipped, tickets closed.
Why it fails: The team builds what was asked for, not what's needed. No discovery means no understanding of the actual problem. Stakeholders lose trust when delivered products don't solve their real need.
2. Request Shaper
"You asked for X, here's why Y is better." The team pushes back on requests, translating vague asks into buildable specs. Uses stakeholder-alignment patterns to reframe requests around decisions and outcomes.
Why it's not enough: Still reactive. The team only works on problems that stakeholders bring to them. Important problems that stakeholders don't know to ask about go unsolved.
3. Demand Shaper
"We interviewed 15 stakeholders, here are the top 3 problems." The team runs its own discovery. Consumer evidence drives prioritization, not stakeholder politics. The team with the most evidence has the most influence.
This is the target. Discovery work (data-consumer-discovery) IS the positioning mechanism. You don't ask for a seat at the table. You bring the data that makes the table's decisions better.
Evidence as Currency
In organizations, influence follows evidence. The team that can say "we talked to 15 consumers and the #1 pain point is X, costing $200K/year in manual workarounds" outranks the team that says "we think we should build Y."
Build evidence systematically:
- Run discovery cycles quarterly (see
data-consumer-discovery) - Synthesize findings into problem briefs (see
research-synthesis-data) - Score opportunities against the validation scorecard (see
data-product-validation) - Present ranked opportunities at the betting table with evidence attached
The discovery practice is not overhead. It is the single highest-leverage activity for team positioning.
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 · 74 lines · 70 tokens per session scan A 849963fe5472
data-team-positioning is a skill published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 975 once invoked, about $0.0003 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 skills, from other repositories
fechar-dia
Fecha o dia de trabalho. Avalia as 3 do dia, classifica o que não fechou, semeia o movimento.
preparar-conversa
Monta a pauta antes de uma conversa que importa. 1:1 com liderado, 1:1 com o próprio líder, alinhamento com par ou stakeholder. Use quando a pessoa disser "prepara o 1:1 com [nome]", "monta a pauta", "vou falar com [nome]", "tenho reunião com [nome], me prepara", "/preparar-conversa". NÃO use pra processar a conversa…
processar-reuniao
Transforma uma reunião que aconteceu em nota estruturada e propaga o que importa. A pessoa cola a transcrição, o resumo automático ou as notas cruas. Use quando a pessoa disser "processa essa reunião", "processa esse 1:1", "olha o que rolou na reunião", colar uma transcrição pedindo organização, ou…
classify
Assess or re-assess the innovation-vs-implementation classification and 0-100 innovation weight for one feature or the whole Product/Features set, then regenerate the ranked features-index.md and run the portfolio sanity check. Use when features need (re)ranking or after editing the UVP.
feature
Create or revise a single Product feature file with a complete user story, Given/When/Then acceptance criteria, and an innovation-vs-implementation classification. Use when adding one feature to Product/Features/, or refining an existing feature, outside a full /innovate run.
iflow
The front door / orchestrator for the I-Framework. Reads the Product/ folder, determines which stage (Intent, Ideation, Innovation) you're in from the artifacts and their gates, reports the risk-burndown state, and routes you to the next step. Use to start or resume the Intent → Ideation → Innovation flow.