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-react-native-featuresgit 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-react-native-features)<a href="https://agentmods.dev/skills/cometchat/cometchat-skills/cometchat-react-native-features"><img src="https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-react-native-features/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-react-native-features"><img src="https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-react-native-features.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 | $0.00107 | $0.01735 |
| Opus 5.5 | $0.00043 | $0.00694 |
| Sonnet 5.5 | $0.00021 | $0.00347 |
| Haiku 4.5 | $0.00011 | $0.00173 |
Grade A, and why
cometchat-react-native-features 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ground truth:
features.rn-v5.json(48 entries) + catalogrn-v5.json. The oracle decides, not memory. Every claim below — whether a capability exists, whether it is on by default, which components render it — comes from that file. Fetch props viacore/references/docs-map.md.
Companion skills (read first)
cometchat-react-native-core— install, provider chain, init→login→render. Assumed, not repeated here.
Use this skill when
- "enable reactions / polls / translation / stickers" · "turn on smart replies"
- "add voice and video calling" · "is X supported" · "how do I switch on Y"
Prerequisites & install
None beyond core unless the feature's branch says otherwise (only two features install a package).
Step 1 — look the feature up in the oracle
Find the entry in features.rn-v5.json. If there is no entry, the feature does not exist — say so
rather than inventing an API. The entry tells you everything:
| Field | What it decides |
|---|---|
category · enablement |
which branch below to take |
ui_components |
what to render (all validated against the catalog) |
sdk_fallback |
the SDK methods to use when the kit has no component |
needs_stitching |
you must wire host state, not just drop a component in |
needs_dashboard |
a dashboard toggle is required as well as code |
auto_rendered_ui |
the kit renders it — emit no client code |
platform_delta |
how React Native differs from React here. Read it before writing anything. |
docs_gap |
the docs don't cover this yet — flag it, don't silently source-fill |
Step 2 — take exactly one branch
A. Already on — category: default, enablement: auto (12 features)
Nothing to enable. Reactions, mentions, typing indicators, receipts, threads and attachments are core messaging in v5, not extensions.
⚠️ Do not offer these as "enable this extension". The dashboard still lists legacy Reactions and Mentions extensions; their own docs say they are already part of core and scheduled for deprecation. Suggesting them is a bug, not a helpful extra — it is the exact defect the React pack hit (AUDIT-077). Customization is via component props, not enablement.
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 · 123 lines · 107 tokens per session scan A 6dd43e915f20
cometchat-react-native-features is a skill published in the GitHub repository cometchat/cometchat-skills (157 stars, last pushed 12d ago), licensed MIT. It adds 107 tokens to every session and 1,735 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 2026-09-12.
Other skills, from other repositories
reverse-engineering-android-malware-with-jadx
Reverse engineers malicious Android APK files using JADX decompiler to analyze Java/Kotlin source code, identify malicious functionality including data theft, C2 communication, privilege escalation, and overlay attacks. Examines manifest permissions, receivers, services, and native libraries. Activates for requests…
flutter-codestyle
Custom Instructions: Senior Flutter & Dart Engineer.
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.
apple-hig-sf-symbols
Use when choosing, reviewing, or implementing SF Symbols in an Apple-platform app — picking meaningful symbols, keeping the same concept on the same symbol everywhere, and handling variants, rendering modes, and accessibility.
apple-app-intents
Use when exposing app features to App Intents, Shortcuts, Siri, Spotlight, widgets, controls, or system actions — small safe AppIntents, AppShortcutsProvider, AppEnum/AppEntity, parameters, and open-vs-background behavior.
macos-permissions-privacy
Use when a macOS app needs a TCC permission or touches private data — the map of which API, Info.plist key, and entitlement each permission needs, pre-prompt explanation patterns, denied-state recovery with System Settings deep links, and honest privacy copy.