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 TalissonVitorino/kmp-ios-skills --skill cloudkitgit clone --depth 1 https://github.com/TalissonVitorino/kmp-ios-skillsWrote 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/talissonvitorino/kmp-ios-skills/cloudkit)<a href="https://agentmods.dev/skills/talissonvitorino/kmp-ios-skills/cloudkit"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/cloudkit/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/talissonvitorino/kmp-ios-skills/cloudkit"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/cloudkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Tool Misuse · line 12 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Tool Misuse · line 78 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 | $0.00209 | $0.05536 |
| Opus 5.5 | $0.00084 | $0.02214 |
| Sonnet 5.5 | $0.00042 | $0.01107 |
| Haiku 4.5 | $0.00021 | $0.00554 |
Grade A, and why
cloudkit 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 1mo 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CloudKit (iCloud sync — iOS 26 era)
Apple's hosted backend for syncing app data across a user's devices (and, via shares, between users). No server code; you model records and CloudKit handles storage, auth (the iCloud account), and delivery.
- Fintech caution: the public database is world-readable and the record data is not end-to-end encrypted at rest under your key. Never put balances, PANs, transactions, or PII in it. For sensitive fields, either keep them out of CloudKit or store a CryptoKit-sealed blob whose key lives in the Keychain (see
swift-security) — CloudKit syncs opaque bytes fine. - When not to use CloudKit: you need server-side business logic, non-Apple clients, or a queryable ledger of record. CloudKit is a per-user sync cache, not a system of record.
- Modern default: for a hand-rolled model use
CKSyncEngine(iOS 17+). For a SwiftData/Core Data model, turn on the built-in mirroring instead of touching CKRecord directly.
Contents
- Setup & entitlements
- Account status (gate every sync)
- Containers & databases
- Records, references, assets
- Queries
- Subscriptions & push
- CKSyncEngine (iOS 17+)
- SwiftData + CloudKit
- Sharing (CKShare)
- NSUbiquitousKeyValueStore
- Error handling
- Correctness checklist
- Depth:
references/cksyncengine.md,references/errors.md,references/subscriptions.md
Setup & entitlements
- Add the iCloud capability → check CloudKit; Xcode creates the
com.apple.developer.icloud-container-identifiersentitlement and a default containeriCloud.<bundle-id>. - Add the Push Notifications capability and enable Remote notifications background mode — CloudKit subscriptions and
CKSyncEnginedeliver change pushes over APNs. - Model your schema in the CloudKit Console (or let it auto-create record types from saves in the Development environment). Development and Production schemas are separate — you must explicitly Deploy Schema Changes to Production before an App Store build works. New fields, indexes, and record types don't reach Production automatically.
- Querying by a field requires a queryable index on it in the console; sorting requires a sortable index;
recordNameneeds a queryable index forNSPredicate(value: true)fetches.
What ships with it
3 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.
- 1mo ago First seen · 372 lines · 209 tokens per session scan A 984a91e97fe0
cloudkit is a skill published in the GitHub repository TalissonVitorino/kmp-ios-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 209 tokens to every session and 5,536 once invoked, about $0.0008 per session on Opus 5.5. 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
cmp-firebase-connect
Add Firebase to a create-cmp app and wire it to its OWN real Firebase project. Use this when the user wants Firebase in their app, or asks "add firebase", "connect my app to firebase", "set up google-services.json", "wire firebase", "create a firebase project for this app", "replace the mock firebase config", "get a…
compose-multiplatform
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…
cmp-audit
Adversarial audit of one subsystem of a Kotlin/Compose Multiplatform app against its spec AND against platform semantics — the class of defect desktop-tier tests cannot see (alarms, notifications, PendingIntents, reboot, process death, DST). Use this when the user says "audit the notifications", "double check X for…
add-feature
Add a new conforming vertical-slice feature (Screen + ViewModel + UseCase + Repository + spec + tests + golden tree + nav route + DI wiring) to this Compose Multiplatform app, cloned deterministically from the project's configured exemplar feature (qa/approvals.json's exemplarFeature — home by default). Use this when…
add-screen
Add a presentation-only slice — Screen + ViewModel + tests + golden tree + spec + nav route — for an EXISTING entity/repository in this Compose Multiplatform app, cloned deterministically from the project's configured exemplar feature's presentation layer (qa/approvals.json's exemplarFeature — home by default).…
add-repository
Add a data/domain slice ONLY — model, repository interface + impl, use case, and a hand-written fake — to this Compose Multiplatform app, cloned deterministically from the project's configured exemplar feature's data layer (qa/approvals.json's exemplarFeature — home by default). No screen, no ViewModel, no nav route…