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 skills/tienenwu/fables/iosnpx skills add tienenwu/fables --skill iosgit clone --depth 1 https://github.com/tienenwu/fablesWrote 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/tienenwu/fables/ios)<a href="https://agentmods.dev/skills/tienenwu/fables/ios"><img src="https://agentmods.dev/badge/skills/tienenwu/fables/ios.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 | $0.00094 | $0.01276 |
| Opus 5 | $0.00047 | $0.00638 |
| Sonnet 5 | $0.00019 | $0.00255 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
ios-dev-playbook 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🌐 繁體中文（canonical） · English mirror
iOS Development Judgment Handbook
Core Principles
- A green simulator proves nothing: signing, provisioning, release optimization,
assertbeing stripped, background modes, memory pressure — these are only real on device/release. Changes on the shipping path must be verified on a real device + at release level. - State has exactly one owner; data flows down, events flow up: a View is a function of state, and
bodymust be cheap and side-effect-free. - UI state always on MainActor: not by remembering to call
DispatchQueue.main, but by using@MainActorso the type system guarantees it for you. - A continuation must resume exactly once: when bridging an old API, zero times = permanent hang, twice = crash — this is a red line, not a style preference.
- Cancellation is cooperative: a
Taskdoes not stop itself; long work must actively callTask.checkCancellation(). Only the.taskmodifier binds to the lifecycle automatically.
Kickoff Routing
| Situation | Path | Read first |
|---|---|---|
| New screen/feature | Define state owner and data flow first, then write the View | references/architecture-state.md |
| Whether to build a ViewModel, where state lives | Decide MV vs MVVM first; don't reflexively reach for MVVM | references/architecture-state.md §2 |
| Navigation, deep links, back stack | Drive NavigationStack path from state | references/architecture-state.md §5 |
| async/await, Task, actor, data races | Check scope and the level of MainActor annotation | references/concurrency.md |
| Bridging an old completion handler / delegate | continuation resumes exactly once | references/concurrency.md §6 |
| Swift 6 strict concurrency reports a Sendable error | Don't slap on @unchecked; look at data ownership first |
references/concurrency.md §4 |
| Shipping to TestFlight / App Store / changing signing | Run the checklist item by item | references/release-checklist.md |
| Fine in the simulator, blows up only on device/at ship time | Suspect signing/optimization/background modes first | references/release-checklist.md |
What ships with it
4 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.
- 4d ago First seen · 59 lines · 94 tokens per session scan A 308c52ca7a09
ios-dev-playbook is a skill published in the GitHub repository tienenwu/fables (4 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,276 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 2026-08-31.
Other skills, from other repositories
implementing-android-code
This skill should be used when implementing Android code in Bitwarden. Covers critical patterns, gotchas, and anti-patterns unique to this codebase. Triggered by "How do I implement a ViewModel?", "Create a new screen", "Add navigation", "Write a repository", "BaseViewModel pattern", "State-Action-Event", "type-safe…
migrating-to-modifier-node
Use this skill to author new custom Jetpack Compose modifiers and migrate legacy ones from Modifier.composed { } to Modifier.Node + ModifierNodeElement . Covers the persistent-node lifecycle (onAttach, onDetach, onReset, coroutineScope), the specialized node interfaces (DrawModifierNode, LayoutModifierNode…
setting-up-compose-hotswan
Use this skill to install and verify Compose HotSwan end to end so a developer goes from zero to working sub-second hot reload on a real device or emulator in one session. Covers the JetBrains IDE plugin install, the com.github.skydoves.compose.hotswan.compiler Gradle plugin wiring, the canonical hotSwanCompiler {…
configuring-lazy-prefetch
Use this skill to tune Jetpack Compose lazy-layout prefetch with LazyLayoutCacheWindow (Compose Foundation 1.9+, @ExperimentalFoundationApi) and pausable composition in prefetch (Compose Foundation 1.10+, default on). Covers configurable Dp-based ahead/behind cache windows plumbed through…
collecting-flows-safely
Use this skill to migrate Compose UI from collectAsState() to collectAsStateWithLifecycle(), hoist Flow parameters out of composables, and apply .conflate() / .distinctUntilChanged() / snapshotFlow so background CPU and battery stop draining and chatty flows stop invalidating the UI per emission. Covers ViewModel…
using-efficient-effects
Use this skill to choose the cheapest correct effect API in Jetpack Compose — LaunchedEffect, DisposableEffect, SideEffect, rememberUpdatedState, and skydoves/compose-effects' RememberedEffect and ViewModelStoreScope. Covers stale-callback bugs in long-lived LaunchedEffect, setup/teardown for non-coroutine…