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/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/source-management)<a href="https://agentmods.dev/rules/ai-learning-gems/ai-learning-gems.github.io/source-management"><img src="https://agentmods.dev/badge/rules/ai-learning-gems/ai-learning-gems.github.io/source-management/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/rules/ai-learning-gems/ai-learning-gems.github.io/source-management"><img src="https://agentmods.dev/badge/rules/ai-learning-gems/ai-learning-gems.github.io/source-management.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 | $0.01695 | $0.01695 |
| Opus 5.5 | $0.00678 | $0.00678 |
| Sonnet 5.5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
source-management scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. Download LaTeX source: `curl -sL "https://arxiv.org/src/{PAPER_ID}" -o source.tar.gz && tar -xzf source.tar.gz` How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Management
Shared source handling rules for all textbook chapter workflows. For site-specific fetch strategies, see web-source-fetching.md. For the curated blog registry, see high-quality-blogs.md.
Centralized Source Storage (CRITICAL)
All sources are stored in AI-Learning-Gems/sources/ — NOT in each chapter folder.
This is a shared, centralized repository. The same source can be referenced by multiple chapters.
Source Folder Naming Conventions
| Source Type | Folder Pattern | Example |
|---|---|---|
| arXiv papers | sources/arxiv-{PAPER_ID} |
sources/arxiv-2010.11929/ |
| Blog posts | sources/{domain}/{path}/ |
sources/lilianweng.github.io/posts/2022-06-09-vlm/ |
| d2l.ai chapters | sources/d2l.ai/{chapter-path}/ |
sources/d2l.ai/chapter_attention-mechanisms-and-transformers/vision-transformer/ |
| HuggingFace docs | sources/huggingface.co/docs/{path}/ |
sources/huggingface.co/docs/transformers/model_doc/vit/ |
| PyTorch docs | sources/pytorch.org/{path}/ |
sources/pytorch.org/docs/stable/generated/torch.nn.MultiheadAttention/ |
| Other sites | sources/{domain}/{path}/ |
sources/distill.pub/2021/gnn-intro/ |
Blog/site URL → folder name rules:
- Strip
https://andhttp:// - Strip
www. - Use the remaining URL path as the folder path
- Store main content as
content.mdinside the folder - Store images in
images/subfolder
arXiv rules:
- Use
arxiv-{PAPER_ID}(hyphenated) - Download LaTeX source:
curl -sL "https://arxiv.org/src/{PAPER_ID}" -o source.tar.gz && tar -xzf source.tar.gz - Contains
.texfiles,images/,.bib
Checking for Existing Sources (MANDATORY)
BEFORE downloading any source, check if it already exists:
ls "AI-Learning-Gems/sources/arxiv-2010.11929/" 2>/dev/null && echo "EXISTS" || echo "NEW"
If a source already exists, skip downloading and reference the existing path.
Source Downloading Quick Reference
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 · 148 lines · 1,695 tokens per session scan A 5210a7e6bfea
source-management is a cursor rule published in the GitHub repository AI-Learning-Gems/AI-Learning-Gems.github.io (23 stars, last pushed 4mo ago), licensed MIT. It adds 1,695 tokens to every session, about $0.0068 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).