Borrowing it
Nothing to install: this file belongs to Dynokostya/just-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/skills/swift-coding/SKILL.mdgit clone --depth 1 https://github.com/Dynokostya/just-worksWrote 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/dynokostya/just-works/swift-coding)<a href="https://agentmods.dev/skills/dynokostya/just-works/swift-coding"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/swift-coding/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/dynokostya/just-works/swift-coding"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/swift-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 17 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Excessive Agency · line 17 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 39 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00042 | $0.01172 |
| Opus 5.5 | $0.00017 | $0.00469 |
| Sonnet 5.5 | $0.00008 | $0.00234 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
swift-coding 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 17d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift Coding
Project conventions override these defaults. Read 2-3 nearby files first, and check the project's own target: Package.swift or the .xcodeproj for Swift version, language mode, platform targets, and the concurrency build settings (strict concurrency level, default actor isolation). Do not assume a concurrency default the project has not set.
Never rules
- Never force unwrap (
!) ortry!outside tests,@IBOutlet, and provable programmer errors (a hard-coded URL literal) with an explaining comment. Useguard let,if let,??,do-catch, ortry?. - Never use a bare
catch { }that swallows the error. Catch specific types, or log and rethrow. - Never keep mutable global or static state. Use actors,
@MainActor, or dependency injection. Swift 6 language mode reports these as errors. - Never block
@MainActor. NoThread.sleep(), synchronous network calls, or heavy computation on the main actor; useasync/awaitor a background context. - Never
print()in production code. Useos.Logger: it is filterable, structured, and searchable in Console.app. - Never generate key material by hand. Use CryptoKit (
SymmetricKey(size:)) orSecRandomCopyBytesfor keys, tokens, and session IDs.SystemRandomNumberGeneratorandInt.random(in:)are fine for general use. - Never use
AnyorAnyObjectwhere a protocol or generic works. Prefer generics,some, oranywith a specific protocol. - Default to
struct. Useclassonly for reference semantics, identity, inheritance, or Objective-C interop.
Closure capture and memory
Use [weak self] (or [unowned self] when the closure cannot outlive self) only when a retain cycle is possible: self stores the closure (directly or through an object it owns) and the closure uses self. Typical cases are closures kept in properties, long-lived callbacks and observers, and Task loops that never finish. Do not add it to non-escaping closures, one-shot Task { } bodies, TaskGroup child tasks, or closures self does not retain; it only adds optional unwrapping. After a weak capture, unwrap with guard let self else { return } before doing work. A capture list such as [currentCount] snapshots a value at closure creation. Delegates are weak var with an AnyObject protocol. (Source: The Swift Programming Language, "Automatic Reference Counting", strong reference cycles for closures.)
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.
- 17d ago Changed · -253 lines · -7 tokens per session 44d53b9e671a
- 2mo ago First seen · 305 lines · 49 tokens per session scan A e89361a2ed1c
swift-coding is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,172 once invoked, about $0.0002 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 2026-09-04.
swift-coding compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| swift-codingDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 42 | Claude Code |
| ink-custom-brush-builderandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 159 | Claude Code |
| kotlin-specialistJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 86 | Claude Code |
| swiftui-devOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 3 | Claude Code, Codex |
| axiom-concurrencyCharlesWiltgen/Axiom | Skill | 1.3k | yesterday | MIT | A | 49 | Claude Code |
| boutique-best-practicesmergesort/Boutique | Skill | 1.1k | 5d ago | MIT | A | 56 | Claude Code |
| waxchristopherkarani/Wax | Skill | 806 | 2d ago | Apache-2.0 | A | 76 | Codex |