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 SwiftfulThinking/SwiftfulStarterProject --skill creating-modelgit clone --depth 1 https://github.com/SwiftfulThinking/SwiftfulStarterProjectWrote 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/swiftfulthinking/swiftfulstarterproject/creating-model)<a href="https://agentmods.dev/skills/swiftfulthinking/swiftfulstarterproject/creating-model"><img src="https://agentmods.dev/badge/skills/swiftfulthinking/swiftfulstarterproject/creating-model/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/swiftfulthinking/swiftfulstarterproject/creating-model"><img src="https://agentmods.dev/badge/skills/swiftfulthinking/swiftfulstarterproject/creating-model.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 | $0.00059 | $0.00680 |
| Opus 5.5 | $0.00024 | $0.00272 |
| Sonnet 5.5 | $0.00012 | $0.00136 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
creating-model 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Model
Scaffold a data model with the correct conformances, CodingKeys, analytics parameters, and mock data.
Steps
- Get the model name from the user (PascalCase, e.g., "Post", "Message", "Avatar")
- Determine the model type (see below)
- Read references/templates.md for the templates
- Substitute
{ModelName},{modelName}, and{modelname}throughout - Determine the folder location (see below)
- Create the file
Choosing the Model Type
| Type | When to Use | Conformances |
|---|---|---|
| Data Sync Model | Model will be synced to/from a database via DataManagers | DataSyncModelProtocol (StringIdentifiable, Codable, Sendable) |
| Simple Model | Local config, UI state, or API response that isn't database-synced | StringIdentifiable, Codable, Hashable |
| Enum Model | Fixed set of options (AB test variants, categories, status) | String, Codable, CaseIterable |
If unclear, ask the user whether the model will be synced to a database.
Folder Location
Models live under their related manager: Managers/{ManagerName}/Models/
- Check existing managers in
Managers/to determine which manager owns this model - If the model belongs to a new manager, suggest creating the manager first
- If unclear, ask the user which manager this model belongs to
Key Patterns
- Naming: File and struct are
{ModelName}Model.swift/{ModelName}Model— enum models omit theModelsuffix - Data sync models must be
public structwithpublic var id: String— required byDataSyncModelProtocol - CodingKeys always use snake_case raw values (e.g.,
case firstName = "first_name") eventParameters— computed property mapping each property to a prefixed analytics key using CodingKeys raw values. Prefix with the model's lowercase name, max 8 characters (e.g.,"user_\(CodingKeys.email.rawValue)"). Check existing models inManagers/**/Models/to ensure no other model uses the same prefix — if there's a conflict, abbreviate (e.g., "avatar" → "avtr", "message" → "msg")static var mockreturnsmocks[0]—static var mocksreturns an array of realistic test instances- All properties should be optional (with
?) unless truly required — models from a database may have missing fields initwith all properties as parameters — use default values ofnilfor optionalsimport SwiftfulDataManagersonly for data sync models — simple models just needimport SwiftUI
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 47 lines · 59 tokens per session scan A 72446abd8893
creating-model is a skill published in the GitHub repository SwiftfulThinking/SwiftfulStarterProject (74 stars, last pushed 7d ago), licensed MIT. It adds 59 tokens to every session and 680 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.
Other skills, from other repositories
kotlin-specialist
Provides idiomatic Kotlin implementation patterns including coroutine concurrency, Flow stream handling, multiplatform architecture, Compose UI construction, Ktor server setup, and type-safe DSL design. Use when building Kotlin applications requiring coroutines, multiplatform development, or Android with Compose.…
swiftui-dev
Use this skill for SwiftUI development, architecture, structure, performance, and Apple native app profiling. It combines.
axiom-concurrency
Use when writing ANY async code, actors, or threads in an Apple-platform app, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.
mobiai-kmp
Use when working on a Kotlin Multiplatform project — shared code, expect/actual declarations, platform-specific implementations, building and testing.
wax
Swift client guidance for Wax's public Memory, PhotoMemory, and VideoMemory APIs. Use only when writing or changing Swift app code that imports Wax. Do not use at session start. Do not use for MCP remember/recall/stats — those follow the live MCP server instructions. Do not use for waxmcp install or doctor (that is…
re-swift
A guide to examining compiled Swift programs, including their symbols, protocol data, closures, and links to Objective-C code. It covers Swift binaries on macOS and Linux with tools such as swift-demangle.