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 Xopoko/build-swift-apps --skill ios-intents-architectgit clone --depth 1 https://github.com/Xopoko/build-swift-appsWrote 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/xopoko/build-swift-apps/ios-intents-architect)<a href="https://agentmods.dev/skills/xopoko/build-swift-apps/ios-intents-architect"><img src="https://agentmods.dev/badge/skills/xopoko/build-swift-apps/ios-intents-architect/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/xopoko/build-swift-apps/ios-intents-architect"><img src="https://agentmods.dev/badge/skills/xopoko/build-swift-apps/ios-intents-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.00590 |
| Opus 5 | $0.00022 | $0.00295 |
| Sonnet 5 | $0.00009 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
ios-intents-architect 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 12d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS Intents Architect
Expose the smallest useful action and entity surface to the system. Start with verbs and objects users need outside the app, then route cleanly back into the app when needed.
Workflow
- Choose 1-3 high-value actions. Prefer verbs like compose, open, find, filter, continue, inspect, or start. Do not mirror the app navigation tree.
- Add only the
AppEntitytypes the system must understand. Keep them narrower than persistence models. AddEntityQuerywhen suggestions or disambiguation are useful. - Decide execution mode:
- direct system-surface action for work that can finish inline
openAppWhenRunor open-style intent when the user should land in an app workflow- one predictable handoff route in the scene/root router when the app must react
- separate inline and open-app intents when one compromise would be unclear
- Add
AppShortcutsProviderfor the first useful set. Keep titles, phrases, and symbols direct and task-oriented. - Reuse the same action/entity surface for widgets and controls when their parameters match.
- Build and verify that intents compile, open or execute correctly, and route to the expected state.
Defaults
- Prefer a dedicated intents target or module.
- Keep intent types thin; business logic stays in app services or domain models.
- Use
AppEnumfor fixed choices such as tabs, modes, or visibility before creating entities. - Treat App Intents as system integration infrastructure, not only a Shortcuts feature.
Avoid
- one intent per screen or tab without real user value
- mirroring the full model graph as entities
- global side-effect handoff with no clear app entry path
- vague shortcut phrases or generic titles
- broad taxonomy work in the first pass
Resources
Read only what is needed:
references/first-pass-checklist.md: choose the first intent/entity surface.references/example-patterns.md: copyable patterns.references/code-templates.md: generalized code templates.references/system-surfaces.md: Shortcuts, Siri, Spotlight, widgets, and controls.
What ships with it
5 files 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.
- 12d ago First seen · 54 lines · 43 tokens per session scan A 40e363a215b4
ios-intents-architect is a skill published in the GitHub repository Xopoko/build-swift-apps (45 stars, last pushed 15d ago), licensed MIT. It adds 43 tokens to every session and 590 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 2026-08-30.
Other skills, from other repositories
vercel-react-native-skills
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
firebase-app-check
Use when implementing app attestation, configuring App Check providers, setting up debug tokens, enabling backend enforcement, or managing token refresh.
flutter-app-architecture
Use when scaffolding a project, refactoring into layers, creating view models/repositories, configuring dependency injection, or implementing unidirectional data flow (MVVM).
firebase-ai
Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.