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-operating-modelgit 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-operating-model)<a href="https://agentmods.dev/skills/hollandkevint/data-product-operator/data-team-operating-model"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/data-team-operating-model.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 5.1 | $0.00086 | $0.00917 |
| Opus 5 | $0.00043 | $0.00458 |
| Sonnet 5 | $0.00017 | $0.00183 |
| Haiku 4.5 | $0.00009 | $0.00092 |
Grade A, and why
data-team-operating-model 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 8d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Squad Structure
Data products need four co-equal roles, not a hierarchy:
| Role | Owns | Veto Authority |
|---|---|---|
| Product Manager | Strategy, prioritization, stakeholder alignment | Business viability |
| Tech Lead | Architecture, infrastructure, technical feasibility | Technical direction |
| Design Lead | UX, usability, information design | User experience |
| Data Lead | Data quality, ethics, data engineering | Ethical concerns |
CRITICAL: The Data Lead is co-equal to the PM, not subordinate. They have veto authority on ethical data concerns. This is what distinguishes data product teams from software product teams.
Shape Up for Data Teams
Six-week cycles replace two-week sprints. Data work has more unknowns than typical software — discovery doesn't stop when building starts.
Cycle structure:
- 2 weeks shaping (before the cycle): PM and Data Lead define the problem, set the appetite
- 6 weeks building (the cycle): squad executes with fixed time, variable scope
- 2 weeks cooldown: bug fixes, tech debt, exploration, skill development
Shaping artifacts:
- Problem statement with evidence
- Appetite: how much time is this problem worth? (not an estimate, a budget)
- Solution sketch: directional, not detailed
- Rabbit holes: known risks that could blow up the timeline
- No-gos: things explicitly excluded from this cycle
Hill Charts over burndown charts. Track progress as "figuring it out" (uphill) vs "getting it done" (downhill). Data products spend more time uphill than software products because data surprises are constant.
Scope hammering: When you discover the problem is bigger than the appetite, narrow the scope. Don't extend the timeline. Ask: "What is the smallest version that delivers value?"
Role x Lifecycle Matrix
Who leads, supports, and consults at each stage:
| Stage | PM | Tech Lead | Design Lead | Data Lead |
|---|---|---|---|---|
| Discover | Lead | Consult | Support | Support |
| Decide | Lead | Support | Support | Support |
| Build | Support | Lead | Support | Lead |
| Test | Consult | Support | Support | Lead |
| Ship | Lead | Lead | Support | Support |
| Evaluate | Lead | Consult | Support | Lead |
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.
- 8d ago First seen · 87 lines · 86 tokens per session scan A f8e68ce17f3a
data-team-operating-model is a skill published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed 5mo ago), licensed MIT. It adds 86 tokens to every session and 917 once invoked, about $0.0004 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
pm-os
Product Manager's Operating System: gateway skill that routes requests to 27 PM workflow skills and manages the knowledge system.
sprint-scope
Sprint planning with capacity awareness. Pulls from backlog (via MCP or manual input), calculates what fits based on team velocity, and outputs recommended scope with stretch goals and deferred items.
meeting-prep
Generate meeting preparation docs tailored by meeting type, pulling context from past meetings, recent decisions, action items, and sprint status.
pm-dashboard
Reads all knowledge files and MCP integrations to produce a single-page product status dashboard with OKR progress, sprint status, decisions, blockers, launches, and metrics.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…