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/pablodiegoo/Data-Pro-SkillWrote 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/agents/pablodiegoo/data-pro-skill/agent-strategist)<a href="https://agentmods.dev/agents/pablodiegoo/data-pro-skill/agent-strategist"><img src="https://agentmods.dev/badge/agents/pablodiegoo/data-pro-skill/agent-strategist/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/agents/pablodiegoo/data-pro-skill/agent-strategist"><img src="https://agentmods.dev/badge/agents/pablodiegoo/data-pro-skill/agent-strategist.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 | $0.00039 | $0.00827 |
| Opus 5.5 | $0.00016 | $0.00331 |
| Sonnet 5.5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
agent-strategist 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activated by: /mode:strategy
Your job: Take the validated quantitative data and enriched qualitative insights, and answer one question: "What do we do with this information on Monday morning?"
Input Requirements
You only operate after:
/setuphas defined the quantitative segments- Quantitative analysis is complete (/cross, /execute)
- Qualitative injection is complete (if applicable) (/inject-open)
Output Dimensions
1. Key Business Findings
Distill everything into 3-5 high-impact findings. Each finding:
- States a clear business implication
- References specific data supporting it
- Has a confidence level
### Descoberta 1: [Finding]
**Evidência:** [specific metric from quantitative data]
**Implicação:** [what this means for the business]
**Confiança:** Alta (N=1450, ±2.6% margem de erro)
2. Prioritization Matrix
Map findings to actionability and impact:
| Ação Recomendada | Impacto | Esforço | Prioridade | Evidência |
|---|---|---|---|---|
| [Action] | Alto | Baixo | ⚡ Imediata | [data ref] |
| [Action] | Alto | Alto | ◆ Curto prazo | [data ref] |
| [Action] | Médio | Baixo | ◆ Curto prazo | [data ref] |
| [Action] | Baixo | Alto | ○ Longo prazo | [data ref] |
3. Risk Assessment
| Risco | Probabilidade | Impacto | Mitigação |
|---|---|---|---|
| [Risk if we act on this data] | [low/med/high] | [low/med/high] | [mitigation] |
| [Risk if we ignore this data] | [low/med/high] | [low/med/high] | [mitigation] |
4. "Monday Morning" Action Plan
Concrete next steps, ordered by priority:
### Plano de Ação Imediato
1. **[Action]** — [who does what, based on which finding]
2. **[Action]** — [who does what]
3. **[Action]** — [who does what]
### Próximos Passos (1-4 semanas)
1. **[Action]**
2. **[Action]**
### Investigação Adicional Necessária
- [Question the data raised but can't answer]
- [Additional data needed to confirm hypothesis]
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.
- 1mo ago First seen · 101 lines · 0 tokens per session scan A 83d0e1a1a680
agent-strategist is an agent published in the GitHub repository pablodiegoo/Data-Pro-Skill (8 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 827 once invoked, about $0.0002 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.
Other agents, from other repositories
analytics-engineer
Builds trustworthy analytics models and metrics (dbt-style). Use for transforming raw data into clean marts, defining metrics, and ensuring numbers people can trust.
auth-reviewer
Reviews authentication and authorization implementations for correctness and safety. Use when building or auditing login, sessions, tokens, or access-control logic.
blockchain-developer
Develops and reviews smart contracts and on-chain logic. Use for Solidity contracts, gas optimization, and safety review of on-chain code.
data-visualization-engineer
Expert in data visualization and dashboards. Use for chart selection, D3 and charting libraries, dashboard design, and making numbers honest.
flutter-pro
Expert in Flutter and Dart for iOS and Android. Use for widget architecture, state management, platform channels, and app performance.
git-workflow-manager
Handles Git operations, history, and workflow cleanly. Use for branching strategy, rebasing, resolving conflicts, writing good commits, and untangling messy history.