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 agentmods add rules/ai-learning-gems/ai-learning-gems.github.io/quarto-conventionsgit clone --depth 1 https://github.com/AI-Learning-Gems/AI-Learning-Gems.github.ioWrote 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/rules/ai-learning-gems/ai-learning-gems.github.io/quarto-conventions)<a href="https://agentmods.dev/rules/ai-learning-gems/ai-learning-gems.github.io/quarto-conventions"><img src="https://agentmods.dev/badge/rules/ai-learning-gems/ai-learning-gems.github.io/quarto-conventions.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 | $0.02039 | $0.02039 |
| Opus 5 | $0.01019 | $0.01019 |
| Sonnet 5 | $0.00408 | $0.00408 |
| Haiku 4.5 | $0.00204 | $0.00204 |
Grade A, and why
quarto-conventions 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 4d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quarto Conventions
Shared Quarto formatting and structure rules for all textbook chapter workflows.
Folder-Based Structure
Because IDE agents rewrite files from scratch on each edit, a single-file approach causes the entire chapter to be rewritten when editing any section. Instead, use a folder-based structure where:
- Each section is a separate file (can be edited independently)
- An index file includes all sections (renders as a single document)
File Structure
Statistics/
├── Bayesian Credible Intervals.qmd ← Index file (includes all sections)
└── Bayesian Credible Intervals/ ← Folder (same name as index)
├── TEXTBOOK-PLAN.md ← Created by the research workflow
├── _01-introduction.qmd ← Section 1
├── _02-the-bayesian-framework.qmd ← Section 2
├── _03-computing-credible-intervals.qmd ← Section 3
├── _04-examples.qmd ← Section 4
├── _98-math-background.qmd ← Math Background appendix (if needed)
├── _99-closing.qmd ← Summary, questions, resources
└── sources/ ← Symlink or note pointing to AI-Learning-Gems/sources/
Key conventions:
- Index file:
[Topic Name].qmd— contains YAML header and{{< include >}}statements - Folder:
[Topic Name]/— same name as the index file (without.qmd) - Section files: Prefixed with
_so Quarto doesn't render them standalone - Numeric prefixes:
_01-,_02-, etc. for ordering (starting at_01, not_00) - Sources: Referenced from central
AI-Learning-Gems/sources/— see TEXTBOOK-PLAN.md for paths
Index File Template
The index file should contain ONLY the YAML header and include statements. Most settings (format, jupyter kernel, execute options) are inherited from the project's _quarto.yml file — the index file only needs the title and the D2 diagram filter.
CRITICAL: The filter path is RELATIVE from the .qmd file to the _extensions folder at the project root. Adjust the number of ../ based on folder depth:
- Files 1 level deep (e.g.,
Statistics/Topic.qmd):../_extensions/... - Files 2 levels deep (e.g.,
Statistics/Subfolder/Topic.qmd):../../_extensions/...
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.
- 4d ago First seen · 229 lines · 2,039 tokens per session scan A c99fe3c4efad
quarto-conventions is a cursor rule published in the GitHub repository AI-Learning-Gems/AI-Learning-Gems.github.io (22 stars, last pushed 2mo ago), licensed MIT. It adds 2,039 tokens to every session, about $0.0102 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 2026-08-30.
Other cursor rules, from other repositories
citazioni
Citazioni corrette (stile numerico) e bibliografia coerente per tesi triennale in LaTeX.
sigma-reports
Build, validate, retrieve, and safely update Sigma report code representations through /v2/reports/spec. Use for fixed-layout or pixel-perfect reports, invoices, statements, regulatory documents, and PDF delivery. Covers report pages, absolute pixel layout, header/footer panels, common elements, verification…
wize-create-prd
Goal. Turn brief + research + trigger map into a Product Requirements Document the team can build from. The PRD names what and why with measurable boundaries. Mantis, Fury, Tony will read it. Shuri ships against the acceptance criteria.
shard-doc
BMAD CORE Tool: Shard Document.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.