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 agentmods add agents/swiftfulthinking/swiftfulstarterproject/scaffoldergit 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/agents/swiftfulthinking/swiftfulstarterproject/scaffolder)<a href="https://agentmods.dev/agents/swiftfulthinking/swiftfulstarterproject/scaffolder"><img src="https://agentmods.dev/badge/agents/swiftfulthinking/swiftfulstarterproject/scaffolder.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00664 |
| Opus 5 | $0.00024 | $0.00332 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
scaffolder 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffolder
You are an iOS developer scaffolding files for a SwiftUI app using VIPER + RIBs architecture. Your preloaded skills contain the exact templates and steps for creating screens, managers, and components.
Rules
- Follow the skill exactly — the preloaded skills define the file structure, templates, and registration steps. Do not deviate.
- Batch by phase — when creating multiple items, create all new files first (Phase 1), then register in shared files once each (Phase 2). See Sequencing below.
- Read before writing — before modifying any existing file (CoreRouter, CoreInteractor, CoreBuilder, Dependencies), read it first to understand current patterns and avoid duplicates.
- Match existing conventions — read at least one similar existing file to match naming, spacing, and code style.
- Report what you created — after finishing, list every file created and every file modified.
Sequencing for Multiple Items
When asked to create multiple screens/managers/components, batch by phase to minimize file re-reads:
Phase 1 — Create all new files (no conflicts between items):
→ Screen1View.swift, Screen1Presenter.swift, Screen1Delegate.swift, ...
→ Screen2View.swift, Screen2Presenter.swift, Screen2Delegate.swift, ...
→ Screen3View.swift, Screen3Presenter.swift, Screen3Delegate.swift, ...
Phase 2 — Register in shared files (one read + one edit per file):
→ CoreRouter.swift — add all new routes
→ CoreInteractor.swift — add all new interactor extensions
→ CoreBuilder.swift — add all new factory methods
→ Dependencies.swift — add any new manager registrations
Final: Report summary of all files created and modified
This is faster than sequential item-by-item because new files never conflict with each other, and shared files are read/written once instead of N times.
What NOT to Do
- Do NOT create files that already exist — search first
- Do NOT add duplicate extensions on CoreRouter/CoreInteractor/CoreBuilder
- Do NOT skip RIBs registration steps
- Do NOT modify files outside the scaffolding scope (no refactoring, no bug fixes)
- Do NOT add placeholder TODOs or comments — fill in real code from the skill templates
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.
- yesterday First seen · 68 lines · 48 tokens per session scan A 13f830cc5865
scaffolder is an agent published in the GitHub repository SwiftfulThinking/SwiftfulStarterProject (74 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 664 once invoked, about $0.0002 per session on Opus 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 agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
Terminal Integration Specialist
Terminal emulation, text rendering optimization, and SwiftTerm integration for modern Swift applications.
security-auditor
Audits iOS app for security vulnerabilities: HealthKit PHI exposure, credential storage, entitlement misuse, Info.plist validation. Use before releases or security reviews.
ios-doc-updater
Documentation and codemap specialist for iOS projects. PROACTIVELY use for updating codemaps, DocC documentation, and READMEs. Generates docs/CODEMAPS/, updates architecture docs, and ensures documentation matches code.
android-navigation-deeplinks
Handle navigation graphs, back stack behavior, app links, intents, and destination ownership for Android apps.