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/nedcodes-ok/cursorrules-collectionWrote 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/nedcodes-ok/cursorrules-collection/swift)<a href="https://agentmods.dev/rules/nedcodes-ok/cursorrules-collection/swift"><img src="https://agentmods.dev/badge/rules/nedcodes-ok/cursorrules-collection/swift/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/nedcodes-ok/cursorrules-collection/swift"><img src="https://agentmods.dev/badge/rules/nedcodes-ok/cursorrules-collection/swift.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 | $0.00310 | $0.00310 |
| Opus 5.5 | $0.00124 | $0.00124 |
| Sonnet 5.5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
swift 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.
What it actually says
Swift Cursor Rules
You are an expert Swift developer. Follow these rules:
Code Style
- Target Swift 5.9+. Use async/await, actors, result builders
- Follow Swift API Design Guidelines: clarity at point of use
- Verb phrases for mutating, noun phrases for non-mutating methods
- Use trailing closure syntax
Type System
- Structs by default. Classes only for reference semantics
- Use enums with associated values for state modeling
- Use protocols for abstraction with protocol extensions
- Generics with where clauses for constrained polymorphism
Optionals
- guard let for early exits, if let for conditional paths
- Use ?. and ?? to avoid force unwrapping
- Never ! in production except IBOutlets
- map/flatMap on optionals for transformations
Concurrency
- async/await for all async code
- Actors for mutable shared state
- TaskGroup for structured concurrency
- MainActor for UI updates
SwiftUI
- @State for local state, @Binding for parent-child
- @Observable over ObservableObject for new code
- Keep views small, extract at 30+ lines
- Environment for dependency injection
Error Handling
- Use typed throws (Swift 5.9+) for predictable errors
- Handle errors at appropriate level — don't catch and ignore
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 · 44 lines · 310 tokens per session scan A 662f22522293
swift is a cursor rule published in the GitHub repository nedcodes-ok/cursorrules-collection (38 stars, last pushed 7mo ago), licensed MIT. It adds 310 tokens to every session, about $0.0012 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
04-kotlin
Cursor rule "04-kotlin" from orbitalsonic/AndroidPilot, covering kotlin rules, prefer, coroutines, null safety and naming.
python
Python best practices.
typescript
TypeScript best practices.
kotlin-ktor-development-cursorrules-prompt-file
Cursor rules for Kotlin development with Ktor integration.
kotlin-springboot-best-practices-cursorrules-prompt-file
Cursor rules for Kotlin Springboot Best Practices.
swift-uikit-cursorrules-prompt-file
Cursor rules for Swift Uikit.