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 skills add laxrajpurohit/swift-skills-pro --skill swift-language-progit clone --depth 1 https://github.com/laxrajpurohit/swift-skills-proWrote 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/skills/laxrajpurohit/swift-skills-pro/swift-language-pro)<a href="https://agentmods.dev/skills/laxrajpurohit/swift-skills-pro/swift-language-pro"><img src="https://agentmods.dev/badge/skills/laxrajpurohit/swift-skills-pro/swift-language-pro/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/skills/laxrajpurohit/swift-skills-pro/swift-language-pro"><img src="https://agentmods.dev/badge/skills/laxrajpurohit/swift-skills-pro/swift-language-pro.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 | $0.00037 | $0.00811 |
| Opus 5.5 | $0.00015 | $0.00324 |
| Sonnet 5.5 | $0.00007 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
swift-language-pro 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 2mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift Language Pro
Write idiomatic, safe, modern Swift. Follow Apple's API Design Guidelines.
When to use
- Writing or reviewing non-UI Swift (models, services, utilities).
- Designing public APIs, naming, and type choices.
- Cleaning up optional handling, error handling, or generics.
Trigger: /swift-language-pro.
Core principles
- Prefer value types (
struct/enum) by default; useclassonly for identity or reference semantics. - Make illegal states unrepresentable with enums and non-optional types.
- Throw typed errors; don't return sentinel values or booleans for failure.
- Name for clarity at the call site, not the definition.
Value vs reference
❌
class Point { var x = 0.0; var y = 0.0 } // accidental shared mutation
✅
struct Point { var x = 0.0; var y = 0.0 }
Model with enums, kill optionals
❌ Two bools that allow impossible states
struct State { var isLoading: Bool; var error: Error? } // loading + error?
✅
enum LoadState<Value> { case idle, loading, loaded(Value), failed(Error) }
Optionals
- Unwrap with
if let/guard let; avoid force-unwrap!outside tests. guardfor early exit, keeping the happy path unindented.
❌
func name(_ u: User?) -> String { return u!.name }
✅
func name(_ u: User?) -> String {
guard let u else { return "Guest" }
return u.name
}
Error handling
❌ Boolean failure
func save() -> Bool
✅
enum SaveError: Error { case diskFull, notAuthorized }
func save() throws // call sites use try/catch; errors carry meaning
API design (naming)
- Read at the call site like a phrase. Include the noun a method acts on.
- Omit needless words; drop type names from labels.
❌
func insertObject(_ obj: Element, atIndex i: Int)
list.insertObject(x, atIndex: 0)
✅
func insert(_ element: Element, at index: Int)
list.insert(x, at: 0)
Generics & protocols
- Constrain generics with
where; prefer protocols with associated types overAny. - Use protocol extensions for default behavior; don't reach for class inheritance.
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.
- 2mo ago First seen · 122 lines · 37 tokens per session scan A d2fa53e009ca
swift-language-pro is a skill published in the GitHub repository laxrajpurohit/swift-skills-pro (6 stars, last pushed 20d ago), licensed MIT. It adds 37 tokens to every session and 811 once invoked, about $0.0001 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 2026-08-31.
swift-language-pro compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| swift-language-prolaxrajpurohit/swift-skills-pro | Skill | 6 | 20d ago | MIT | A | 37 | Claude Code |
| generatorsrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 176 | Claude Code |
| swift-concurrency-updatesrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 52 | Claude Code |
| memoryrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 36 | Claude Code |
| watchOSrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 39 | Claude Code |
| attributed-stringrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 37 | Claude Code |
| coding-best-practicesrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 55 | Claude Code |