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 commands/swiftfulthinking/swiftfulstarterproject/scaffoldgit 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/commands/swiftfulthinking/swiftfulstarterproject/scaffold)<a href="https://agentmods.dev/commands/swiftfulthinking/swiftfulstarterproject/scaffold"><img src="https://agentmods.dev/badge/commands/swiftfulthinking/swiftfulstarterproject/scaffold.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 | $0.00023 | $0.00259 |
| Opus 5 | $0.00012 | $0.00130 |
| Sonnet 5 | $0.00005 | $0.00052 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
scaffold 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.
What it actually says
Ask the user what they want to scaffold. Present these options:
- Screen — VIPER screen (View, Presenter, Interactor, Router) with RIBs wiring
- Manager — Manager with service protocol + Mock/Prod implementations
- Component — Dumb UI component with injected data
- Model — Codable/Sendable model with CodingKeys, eventParameters, mocks
- Test — Swift Testing unit test file
- Module — Top-level navigation module
- Paywall — Paywall variant with AB test wiring
- AB Test — AB test service + mock + DevSettings wiring
- View Modifier — ViewModifier + View extension
- Extension — Type extension file
- Package — SPM package integration
- Deep Link — Deep link / push notification handler
After the user picks an option and describes what they need, use the Task tool to invoke the scaffolder agent with their request. Pass the full description of what to create.
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 · 22 lines · 23 tokens per session scan A 37cfd3c2e3a2
scaffold is a command published in the GitHub repository SwiftfulThinking/SwiftfulStarterProject (74 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 259 once invoked, about $0.0001 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 commands, from other repositories
ask
Ask a question about iOS/Swift development - routes to the right Axiom skill or agent.
modernize
Migrate legacy iOS patterns to modern equivalents (launches modernization-helper agent).
initialize-ios
Manual override: initialize ast-index for iOS/Swift/ObjC project.
kmp-implement-feature
KMP Agent Skills — build a new KMP feature end-to-end, layer by layer, with the full Koin 4 / Ktor 3 / SQLDelight 2 / CMP 1.11 stack wired correctly from the start.
create-activity
Generate a Jetpack Compose screen with proper architecture.
swift-new
Create new Swift project or component.