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 dashboards-to-decisionsgit 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/dashboards-to-decisions)<a href="https://agentmods.dev/skills/hollandkevint/data-product-operator/dashboards-to-decisions"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/dashboards-to-decisions/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/dashboards-to-decisions"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/dashboards-to-decisions.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 | $0.00063 | $0.01066 |
| Opus 5.5 | $0.00025 | $0.00426 |
| Sonnet 5.5 | $0.00013 | $0.00213 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
dashboards-to-decisions 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 2mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Reframe
When someone asks "I need a dashboard," the first question is: "What decision will this inform?"
If they can't answer, the dashboard shouldn't exist yet. Not "never build it." Just "not yet." Get the decision clear first.
The Process
Step 1: Surface the Decision
Ask: "What decision will this dashboard help you make? Be specific — not 'understand performance' but 'decide whether to expand into the Southeast region this quarter.'"
If the requester struggles, use these prompts:
- "What would you DO differently after seeing this dashboard?"
- "If the number is high, what changes? If it's low, what changes?"
- "Who makes this decision, and when?"
If no decision emerges: the request is a monitoring need, not a decision need. Route to Layer 1 (dashboard craft) and move on.
Step 2: Map the Decision Architecture
| Element | Question | Example |
|---|---|---|
| Decision | What specifically is being decided? | "Expand to Southeast: yes/no" |
| Decision-maker | Who has authority? | "VP of Operations, with CFO sign-off" |
| Timeline | When does this decision get made? | "Q3 planning, due July 15" |
| Metrics needed | What data informs this? | "Market size, current penetration, operational capacity, P&L impact" |
| Threshold | What number triggers action? | "If projected ROI > 15% AND capacity utilization < 80%" |
| Context | What else does the decision-maker need to know? | "Previous expansion to Midwest failed at 12% ROI" |
| Failure mode | What would make the wrong decision? | "Misleading market size data (happened with Midwest)" |
Step 3: Design the Decision Spec (Not the Dashboard)
Write a decision specification that captures:
- The question (in plain language, not metric language)
- The answer format (yes/no, rank order, threshold comparison)
- The data required (specific metrics with definitions and sources)
- The context required (what the decision-maker needs to know before looking at data)
- The intent (when metrics conflict, which wins?)
- The failure mode (what would lead to a wrong decision?)
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.
- 2mo ago First seen · 118 lines · 63 tokens per session scan A 3a7d6158344f
dashboards-to-decisions is a skill published in the GitHub repository hollandkevint/data-product-operator (5 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 1,066 once invoked, about $0.0003 per session on Opus 5.5. 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.
dashboards-to-decisions compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dashboards-to-decisionshollandkevint/data-product-operator | Skill | 5 | 4d ago | MIT | A | 63 | Claude Code |
| shipkyle-chalmers/ticketwright | Skill | 4 | 2d ago | MIT | A | 50 | Claude Code |
| ticketkyle-chalmers/ticketwright | Skill | 4 | 2d ago | MIT | A | 48 | Claude Code |
| reviewkyle-chalmers/ticketwright | Skill | 4 | 2d ago | MIT | A | 40 | Claude Code |
| close-daype-menezes/pm-chief-of-staff | Skill | 5 | 3d ago | MIT | A | 25 | Claude Code |
| process-meetingpe-menezes/pm-chief-of-staff | Skill | 5 | 3d ago | MIT | A | 124 | Claude Code |
| prep-conversationpe-menezes/pm-chief-of-staff | Skill | 5 | 3d ago | MIT | A | 135 | Claude Code |