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 cometchat/cometchat-skills --skill cometchat-ios-coregit clone --depth 1 https://github.com/cometchat/cometchat-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/cometchat/cometchat-skills/cometchat-ios-core)<a href="https://agentmods.dev/skills/cometchat/cometchat-skills/cometchat-ios-core"><img src="https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-ios-core/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/cometchat/cometchat-skills/cometchat-ios-core"><img src="https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-ios-core.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00086 | $0.04990 |
| Opus 5.5 | $0.00034 | $0.01996 |
| Sonnet 5.5 | $0.00017 | $0.00998 |
| Haiku 4.5 | $0.00009 | $0.00499 |
Grade A, and why
cometchat-ios-core 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 28d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ground truth:
CometChatUIKitSwift5.1.22 (a prebuilt binary xcframework) +CometChatSDK4.1.7. Every symbol below is verified against the shipped.swiftinterface(catalogs/ios-v5.json); the golden-path composition and its layout constraints are verified on a simulator by the native harness, not reasoned from the web pack. This file is the THIN map loaded every run; deep detail lives inreferences/*, loaded only when the task needs it.
Use this skill when
"add chat to my iOS app", "integrate CometChat in Swift", "set up CometChat credentials", "show a conversations + messages screen", "build a chat app". An unscoped "add chat" means a production-ready core chat surface — a CometChatConversations list that pushes to a chat screen you compose — NOT a bare list, and NOT the whole combined app. It grows on request (users/groups tabs, group details, threads, calls); those recipes live in cometchat-ios-placement and cometchat-ios-features.
Three things that are NOT like the web UI Kit
Setter-based API (not props) · no composite component in v5 (the *WithMessages names are v4) · navigation stack, not side-by-side panes. Full detail + why each one compiles-but-fails: references/anti-patterns.md.
Install — Swift Package Manager only
SPM only. Never CocoaPods, even if a Podfile exists (its distribution is winding down; a Podfile is a detection signal, not an instruction). Add three packages at EXACT versions — the kit is a prebuilt binary compiled against one Chat SDK version and SPM will not resolve that transitively: CometChatUIKitSwift 5.1.22 · CometChatSDK 4.1.7 · CometChatCallsSDK 5.0.3 (required even for chat-only — see references/install.md for the repos, the Calls-SDK reason, and the Xcode steps).
Why
CometChatSDK4.1.7 and not the newer 4.1.9 in the docs' setup pages: these are the versions the pinned 5.1.22 UI Kit binary was built and verified against here (catalog + simulator smoke). The kit is a prebuilt xcframework that links a specific Chat SDK — bumping onlyCometChatSDKrisks a binary-compat mismatch SPM won't catch. Do NOT flip the pin on your own; it moves together with the UI Kit when this pack next upgrades the iOS family.
What ships with it
7 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.
- 28d ago Changed · +1 lines 81aa21b16bd2
- 1mo ago Changed · -887 lines · +57 tokens per session b2eaa0844812
- 1mo ago First seen · 1,093 lines · 29 tokens per session scan A de1c9355d240
cometchat-ios-core is a skill published in the GitHub repository cometchat/cometchat-skills (150 stars, last pushed 6d ago), licensed MIT. It adds 86 tokens to every session and 4,990 once invoked, about $0.0003 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 2026-09-03.
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-app-check
Use when implementing app attestation, configuring App Check providers, setting up debug tokens, enabling backend enforcement, or managing token refresh.
firebase-ai
Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
flutter-best-practices
Use when writing, reviewing, refactoring, or planning Flutter/Dart code — screens, features, project structure, state management, folders, widgets, cubits/blocs, repositories, services, or tests.
compose-architecture
Use when writing, changing or reviewing code that touches the house contract for Jetpack Compose and Compose Multiplatform apps: module graph, MVI/BaseViewModel, error tiers, state ownership, naming, Koin DI, Navigation 3 and coroutines. The compose skill is the entry point. Do NOT use for Gradle-only work…
compose-project
Owns project and build-level work for Compose and Compose Multiplatform apps: bootstrapping a new project, adopting the kit in an existing project, adding or extracting a module, convention plugins in build-logic, the version catalog, and CI plus agent hooks. Use when starting a Compose Multiplatform app, adding a…