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 n0an/App-Intents-Agent-Skill --skill app-intentsgit clone --depth 1 https://github.com/n0an/App-Intents-Agent-SkillWrote 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/n0an/app-intents-agent-skill/app-intents)<a href="https://agentmods.dev/skills/n0an/app-intents-agent-skill/app-intents"><img src="https://agentmods.dev/badge/skills/n0an/app-intents-agent-skill/app-intents/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/n0an/app-intents-agent-skill/app-intents"><img src="https://agentmods.dev/badge/skills/n0an/app-intents-agent-skill/app-intents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00099 | $0.05321 |
| Opus 5 | $0.00049 | $0.02661 |
| Sonnet 5 | $0.00020 | $0.01064 |
| Haiku 4.5 | $0.00010 | $0.00532 |
Grade A, and why
app-intents 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 11d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write and review Swift code that exposes app functionality through the App Intents framework, ensuring correct protocol conformance, safe data flow, and idiomatic discoverability wiring.
Review process:
- Check intent fundamentals (protocol,
perform(), return types, dialog) usingreferences/fundamentals.md. - Validate parameters and parameter options using
references/parameters.md. - Validate entity types, display representations, and queries using
references/entities.md. - Check the
AppShortcutsProviderregistration and discoverability UI usingreferences/shortcuts-and-siri.md. - Validate
OpenIntentnavigation and snippet view return types usingreferences/open-and-snippet-intents.md. - Check dependency injection and the data-controller pattern using
references/dependencies.md. - Validate Spotlight indexing via
IndexedEntity,IndexedEntityQuery, and attribute sets usingreferences/spotlight.md. - Check
@AssistantEntity/@AssistantIntentschema adoption usingreferences/assistant-schemas.md. - Validate the Siri / Apple Intelligence integration (finding content, custom responses, donations, confirmation, ownership) using
references/siri-intelligence.md. - Check on-screen awareness and content transfer (view annotations,
IntentValueRepresentation, system-integration annotations) usingreferences/onscreen-awareness.md. - For intents that run past 30 seconds, handle cancellation, or target a specific process, use
references/long-running-and-execution.md. - If writing or reviewing tests for intents, use
references/testing-intents.md(covers the newAppIntentsTestingframework). - Catch common mistakes using
references/anti-patterns.md.
If doing partial work, load only the relevant reference files.
Task-based routing
Match the user's goal to the read order. Load only what you need.
"Create my first App Intent"
references/fundamentals.md- protocol,perform(), return typesreferences/shortcuts-and-siri.md- register it so it shows up
What ships with it
14 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.
- agents/openai.yaml 253 B
- references/anti-patterns.md 33 KB
- references/assistant-schemas.md 22 KB
- references/dependencies.md 12 KB
- references/entities.md 26 KB
- references/fundamentals.md 17 KB
- references/long-running-and-execution.md 9.7 KB
- references/onscreen-awareness.md 12 KB
- references/open-and-snippet-intents.md 27 KB
- references/parameters.md 22 KB
- references/shortcuts-and-siri.md 11 KB
- references/siri-intelligence.md 11 KB
- references/spotlight.md 12 KB
- references/testing-intents.md 16 KB
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.
- 11d ago First seen · 339 lines · 99 tokens per session scan A 95bb54047ad9
app-intents is a skill published in the GitHub repository n0an/App-Intents-Agent-Skill (33 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 5,321 once invoked, about $0.0005 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
swift-expert
Expert-level Swift development for iOS, macOS with SwiftUI, Combine, and modern Swift 5.9+. Use when the user mentions iOS, macOS, SwiftUI, Combine, async await, or Apple platforms, or when the task involves Modern Swift Features, Basics and Optionals, Functions and Closures, or Structs and Classes.
ios-expert
Expert in iOS development with SwiftUI, UIKit, Combine, and Apple ecosystem integration. Use when the user mentions mobile, Swift, SwiftUI, UIKit, Apple platforms, or Xcode, or when the task involves iOS App Architecture, SwiftUI Fundamentals, UIKit Essentials, or Combine Framework.
swift-format-style
Writes and reviews Swift FormatStyle code, replacing legacy Formatter subclasses and C-style String(format:) with modern .formatted() APIs. Use when formatting numbers, dates, durations, measurements, lists, names, byte counts, or URLs.
swift-development
You MUST activate this skill when working on Swift projects.
generators
Code generator skills that produce production-ready Swift code for common app components. Use when user wants to add logging, analytics, onboarding, review prompts, networking, authentication, paywalls, settings, persistence, error monitoring, CI/CD pipelines, localization, push notifications, deep linking, testing…
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.