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-android-v6-kotlin-placementgit 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-android-v6-kotlin-placement)<a href="https://agentmods.dev/skills/cometchat/cometchat-skills/cometchat-android-v6-kotlin-placement"><img src="https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-android-v6-kotlin-placement/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-android-v6-kotlin-placement"><img src="https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-android-v6-kotlin-placement.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 | $0.00127 | $0.02558 |
| Opus 5.5 | $0.00051 | $0.01023 |
| Sonnet 5.5 | $0.00025 | $0.00512 |
| Haiku 4.5 | $0.00013 | $0.00256 |
Grade A, and why
cometchat-android-v6-kotlin-placement 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ground truth: catalog
android-v6.json+contracts.android-v6.json(core-chat-surface,chat-experience) + the live recipes (conversation-message-view,tab-based-chat,one-to-one-chat). Signatures below were verified against the INSTALLED 6.0.5 source. Fetch anything else from docs (core→references/docs-map.md).⚠️ Kotlin XML Views cohort. Screens are Activities/Fragments hosting kit Views. The Compose cohort (NavHost + composables) is a separate skill.
Companion skills (read first)
cometchat-android-v6-core— install, credentials,initFromSettings → login → render, andreferences/layout.md(the ONE sizing standard). Sizing rules live THERE; this skill places screens.cometchat-android-v6-kotlin-components— what exists in this cohort.
Use this skill when
"put chat behind a tab", "build the full chat app", "open a chat screen for this user/group", "embed the conversation list in an existing screen", "how should I navigate between the list and the messages".
Prerequisites & install
Same kit + initFromSettings → login gate as core — no chat Activity is started before login resolves. Every Activity below must be lifecycle-aware (AppCompatActivity/ComponentActivity/FragmentActivity) — the kit hooks lifecycle events — and registered in AndroidManifest.xml.
The rule that governs every layout: one screen per Activity
Android composes by navigation, not by side-by-side panes. The list, the message screen, the thread and search are separate destinations with a real back stack. Never build a web-style two-pane split or a "side panel" on a phone.
Placement 1 — conversations → messages (the default)
The core-chat-surface contract. core carries the full code; the structure:
// ConversationActivity — the list
conversations.setOnItemClick { conversation ->
val intent = Intent(this, MessageActivity::class.java)
when (val entity = conversation.conversationWith) {
is User -> intent.putExtra("user", entity)
is Group -> intent.putExtra("group", entity)
}
startActivity(intent)
}
conversations.setOnSearchClick { startActivity(Intent(this, SearchActivity::class.java)) }
activity_message.xml is a vertical LinearLayout: header wrap_content → list 0dp + layout_weight="1" → composer wrap_content, all match_parent wide. The weight is what makes the list scroll instead of pushing the composer off-screen. Bind the SAME User/Group into header + list + composer, and wire header.setOnBackPress { finish() }.
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 Changed · -146 lines · +92 tokens per session 263f6c72fb50
- 1mo ago First seen · 264 lines · 35 tokens per session scan A c2a689f133eb
cometchat-android-v6-kotlin-placement is a skill published in the GitHub repository cometchat/cometchat-skills (157 stars, last pushed 12d ago), licensed MIT. It adds 127 tokens to every session and 2,558 once invoked, about $0.0005 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
compose-platform
Owns platform splits for Compose Multiplatform apps: places declarations in commonMain, chooses expect/actual vs interface plus DI, wires host adapters and ports, and validates iOS/Swift interop, desktop and web targets, and platform lifecycle. Use when touching commonMain, expect, actual, iosMain, Swift, SKIE, Flow…
stream-swift
Build, integrate, migrate to, and answer how-to questions for Stream Chat, Video, and Feeds in Swift / SwiftUI / UIKit / iOS apps - including AI assistants and agentic experiences (ChatGPT-style apps, LLM bots in chat, streaming responses, thinking indicators, reasoning and tool-call steps, tool approvals, device-side…
flutter-codestyle
Custom Instructions: Senior Flutter & Dart Engineer.
ios-agent-skill
Expert iOS/Swift developer behavior for AI coding agents. Use when writing, reviewing, or refactoring Swift, SwiftUI, UIKit, or SwiftData code; when designing iOS app architecture (MVVM, Clean Architecture, coordinators, routing); when building UI that must meet Apple's Human Interface Guidelines, contrast, dark-mode…
ios-builder
Turn an Apple app idea into a concrete implementation using Swift, Apple technology references, release notes, and separately editable Icon Composer layers. Use for creating or extending native Apple apps; requires a coding environment for file edits and Xcode for iOS builds.
visionos-swift-spatial
Architecting native spatial computing applications for visionOS using Swift, SwiftUI, RealityKit, and ARKit. Use when developing 3D Windows, Volumes, Immersive Spaces, RealityView components, Spatial Audio, ShaderGraph Materials, and Hand/Eye tracking interaction models.