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/danielraffel/SwiftCatalystWrote 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/danielraffel/swiftcatalyst/cursor-rules-creation)<a href="https://agentmods.dev/rules/danielraffel/swiftcatalyst/cursor-rules-creation"><img src="https://agentmods.dev/badge/rules/danielraffel/swiftcatalyst/cursor-rules-creation/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/danielraffel/swiftcatalyst/cursor-rules-creation"><img src="https://agentmods.dev/badge/rules/danielraffel/swiftcatalyst/cursor-rules-creation.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 | $0.01761 | $0.01761 |
| Opus 5.5 | $0.00704 | $0.00704 |
| Sonnet 5.5 | $0.00352 | $0.00352 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
cursor-rules-creation 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules Creation and Generation
This meta-rule provides guidelines for creating and automatically generating Cursor Project Rules. It extends the basic creation guidelines to support building a comprehensive "stdlib" of rules that can be composed together, with specific adaptations for Swift projects.
Rule Auto-Generation Approach
Cursor can be instructed to generate new rules based on observed patterns, successful implementations, or specific requirements. This approach enables rapidly building a rich library of rules for Swift development.
Key Principles
- Unix-Like Composition: Design rules to be composable like Unix pipes, where the output of one rule can feed into another.
- Continuous Learning: Automatically update rules with learnings from successful implementations.
- Templates Over Implementation: Focus on creating rule templates that can be adapted rather than writing specific implementations.
Prompting Cursor to Generate Rules
When asking Cursor to generate a new rule for Swift projects, use the following structure:
Create a Cursor rule for [specific purpose] that:
1. Defines [pattern/convention]
2. Works with files matching [glob pattern for Swift files]
3. Includes examples from [reference implementation]
4. Can compose with [other rules]
Example Rule Generation Prompt
Create a Cursor rule for Swift protocol implementation that:
1. Defines standards for creating and implementing protocols
2. Works with files matching "Sources/**/*.swift"
3. Includes examples from our networking module
4. Can compose with our existing Swift naming conventions
Building Your Rule Stdlib for Swift Projects
The "stdlib" approach involves:
- Core Infrastructure Rules: Rules about where to place rules, how to name them, and how to compose them.
- Language-Specific Rules: Rules for Swift language features, patterns, and best practices.
- Framework-Specific Rules: Rules for UIKit, SwiftUI, Combine, etc.
- Architecture Rules: Rules for architecture patterns like VIPER, MVVM, etc.
- Rule Composition Manifests: Files that define how rules work together.
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 · 255 lines · 1,761 tokens per session scan A 0e3bbb9d12e2
cursor-rules-creation is a cursor rule published in the GitHub repository danielraffel/SwiftCatalyst (14 stars, last pushed 1y ago), licensed MIT. It adds 1,761 tokens to every session, about $0.0070 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 2026-08-30.
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).