cometchat-android-v6-core

cometchat-android-v6-core is a skill for Claude Code from cometchat/cometchat-skills. It costs 91 tokens per session (5,411 once invoked), scanned A, original, MIT.

A setup guide for CometChat Android UIKit v6 covering Gradle dependencies, SDK initialization, login, logout, and message sending. Gradle is Android’s system for configuring builds and dependencies.

In plain words
What is it for?
Use it to add the required libraries, start the SDK, authenticate users, sign them out, and send messages.
Why use it?
It covers the basic steps needed before an Android app can use CometChat chat features.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cometchat-skills plugin — 98 skills, 1 MCP server shipped together

Good fit Use it to add the required libraries, start the SDK, authenticate users, sign them out, and send messages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cometchat/cometchat-skills/cometchat-android-v6-core
Install

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.

Any agent
npx skills add cometchat/cometchat-skills --skill cometchat-android-v6-core
Clone the repo
git clone --depth 1 https://github.com/cometchat/cometchat-skills

Made for: Claude Code.

Or install cometchat-skills, the plugin that ships this one along with the rest of its 98 skills, 1 MCP server.

Wrote 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.

agentmods badge for cometchat-android-v6-core

README.md
[![agentmods](https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-android-v6-core/github.svg)](https://agentmods.dev/skills/cometchat/cometchat-skills/cometchat-android-v6-core)
Your own site
<a href="https://agentmods.dev/skills/cometchat/cometchat-skills/cometchat-android-v6-core"><img src="https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-android-v6-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.

agentmods 80×15 button for cometchat-android-v6-core

Your own site · 80×15
<a href="https://agentmods.dev/skills/cometchat/cometchat-skills/cometchat-android-v6-core"><img src="https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-android-v6-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,411 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.05411
Opus 5.5 $0.00036 $0.02164
Sonnet 5.5 $0.00018 $0.01082
Haiku 4.5 $0.00009 $0.00541

Measured 1mo ago against content hash fdb1656c0e87, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cometchat-android-v6-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 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.

skills/cometchat-android-v6-core/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ground truth: com.cometchat:chatuikit-{kotlin,compose}-android@6 + catalog android-v6.json (287 public symbols, generated from the INSTALLED 6.0.5 source) + features.android-v6.json. Official docs: https://www.cometchat.com/docs/ui-kit/android/overview · scoped index …/ui-kit/android/llms-android-v6.md. Verify every symbol against the catalog; fetch signatures from docs (references/docs-map.md); never trust memory.

⚠️ ONE kit, TWO cohorts. chatuikit-kotlin-android (XML Views) and chatuikit-compose-android (Jetpack Compose) are different artifacts with different namespaces. Component NAMES are shared, the wiring is not — Views uses setOnX(...) setters, Compose uses onX = params. Never install both. v5 Java snippets do not compile against v6 (com.cometchat.chatuikit.* → com.cometchat.uikit.*); that migration is cometchat-android-v6-migration.

⚠️ Some docs snippets are ahead of / behind the shipped kit. Where a baked signature here differs from a docs page, the baked one was verified against the installed 6.0.5 source (gap logged internally). Compile before you trust a docs fence.

Use this skill when

"add chat to my Android app", "set up CometChat credentials", "integrate CometChat in Kotlin/Compose", "show a conversations + messages screen", "build a chat app". An unscoped "add chat" means the production-ready core chat surface below — not a bare list, and not the whole tab-based app (that grows via cometchat-android-v6-{kotlin,compose}-placement).

Prerequisites & install

Pick ONE cohort — the app's existing UI stack decides:

// settings.gradle.kts → dependencyResolutionManagement.repositories
maven("https://dl.cloudsmith.io/public/cometchat/cometchat/maven/")

// app/build.gradle.kts — repo/exclude/compileOptions are COHORT-NEUTRAL (the duplicate-class
// collision comes via chatuikit-core-android, which BOTH cohorts pull); only the artifact differs
configurations.all {
    // REQUIRED — without it the first build fails at dexing with ~40
    // "Duplicate class org.jetbrains.annotations.*" errors (docs getting-started-{kotlin,jetpack}).
    exclude(group = "org.jetbrains", module = "annotations-java5")
}

// gradle.properties — REQUIRED, both lines (why: dexing dup-class; references/troubleshooting.md):
//   android.useAndroidX=true   android.enableJetifier=true

dependencies {
    implementation("com.cometchat:chatuikit-kotlin-android:6.0.5")
    // implementation("com.cometchat:calls-sdk-android:5.0.4")   // only for voice/video
}
android {
    buildFeatures { viewBinding = true }
    compileOptions { sourceCompatibility = JavaVersion.VERSION_11; targetCompatibility = JavaVersion.VERSION_11 }
}
// JVM 11 (Kotlin 2.2+ rejects kotlinOptions{}). Fully-qualified: a mid-file .kts import won't compile.
kotlin { compilerOptions { jvmTarget.set(org.jetbrains.kotlin.gradle.dsl.JvmTarget.JVM_11) } }

Theme kit views under a CometChatTheme.DayNight-derived theme — REQUIRED (Views), not cosmetic. Kit views resolve ?attr/cometchat* at inflate time; outside such a theme the FIRST kit view crashes (IllegalArgumentException/InflateException on ?attr/cometchatPrimaryColor — verified on device). Greenfield → re-parent app-wide: <style name="AppTheme" parent="CometChatTheme.DayNight" /> + <application android:theme="@style/AppTheme">. Brownfield (app HAS its own theme) → do NOT re-parent (CometChatTheme.DayNight parents MaterialComponents, so Material3-only host attrs stop resolving — you'd break their screens); scope a derived style to the chat Activities (manifest android:theme) + ContextThemeWrapper for fragment/tab-embedded views — recipe: kotlin-placement Placement 2.

Read the full file on GitHub · 299 lines

Files

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.

Changes

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.

  1. 1mo ago Changed · -436 lines · +59 tokens per session fdb1656c0e87
  2. 1mo ago First seen · 735 lines · 32 tokens per session scan A 014478a27d63

Subscribe to this mod's changes

cometchat-android-v6-core is a skill published in the GitHub repository cometchat/cometchat-skills (150 stars, last pushed 6d ago), licensed MIT. It adds 91 tokens to every session and 5,411 once invoked, about $0.0004 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.

Related

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.

fcakyon/claude-codex-settings · 57 tokens

firebase-app-check

Use when implementing app attestation, configuring App Check providers, setting up debug tokens, enabling backend enforcement, or managing token refresh.

evanca/flutter-ai-rules · 30 tokens

firebase-ai

Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.

evanca/flutter-ai-rules · 30 tokens

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.

evanca/flutter-ai-rules · 48 tokens

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…

Meet-Miyani/compose-skill · 106 tokens

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…

Meet-Miyani/compose-skill · 140 tokens