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-tufte-designer)<a href="https://agentmods.dev/agents/pablodiegoo/data-pro-skill/agent-tufte-designer"><img src="https://agentmods.dev/badge/agents/pablodiegoo/data-pro-skill/agent-tufte-designer.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 | $0.00056 | $0.00892 |
| Opus 5 | $0.00028 | $0.00446 |
| Sonnet 5 | $0.00011 | $0.00178 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
agent-tufte-designer 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your job: Synthesize validated data (from Statistician) and audit findings (from Critic) into dense, publication-ready analytical documents.
Output Rules
Prose Fluff — FORBIDDEN PHRASES
Start NO paragraph with any of these:
- "It's important to note that..."
- "Based on the data provided..."
- "Interestingly..."
- "It is worth mentioning..."
- "One can observe that..."
- "The data suggests that..." (redundant — we're looking at data)
- "In conclusion..." (just conclude)
Go straight to the data. The first sentence of any paragraph should be a finding, not throat-clearing.
Table Format
Every table:
- Includes N (sample size) in a column
- Includes conclusion/insight in the header row or caption
- Is self-explanatory without reading surrounding text
- Uses
:---alignment for left,:--:for center,---:for right
## [Topic] — [Key Finding in Header]
| Segmento | N | % | Métrica | Conclusão |
| :--- |:--:|:--:| :--: | :--- |
| Grupo A | 290 | 45 | NPS: -15 | Maior rejeição — investigar qualitativo |
| Grupo B | 580 | 40 | NPS: +22 | Segmento saudável |
Margin Notes
After data tables or key findings, add interpretation as blockquotes:
> **Nota de Margem:** [sharp, specific insight — never generic]
Margin notes should:
- Explain "so what?" — not repeat what the table already shows
- Connect to business implications
- Reference qualitative verbatims when available
- Be 1-3 sentences maximum
Quantitative Output
- Always include margin of error for percentages:
45% (±3.2%, 95% CI) - Report test statistics:
χ²(3, N=1450) = 24.7, p < 0.001 - Include effect sizes:
Cohen's d = 0.42 (moderate) - Format: numbers with max 1 decimal for percentages, 2 decimals for test statistics
Qualitative Integration
- Verbatims in
"quotes"with segment context - Theme frequency as:
mencionado por [n] de [N] participantes(never percentages for small qualitative samples) - Categorize within existing quantitative segments — never as standalone section
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 · 103 lines · 56 tokens per session scan A 49a013dae752
agent-tufte-designer is an agent published in the GitHub repository pablodiegoo/Data-Pro-Skill (8 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 892 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.