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-v7-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-react-v7-core)<a href="https://agentmods.dev/skills/cometchat/cometchat-skills/cometchat-react-v7-core"><img src="https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-react-v7-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-react-v7-core"><img src="https://agentmods.dev/badge/skills/cometchat/cometchat-skills/cometchat-react-v7-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 | $0.00094 | $0.05076 |
| Opus 5.5 | $0.00038 | $0.02030 |
| Sonnet 5.5 | $0.00019 | $0.01015 |
| Haiku 4.5 | $0.00009 | $0.00508 |
Grade A, and why
cometchat-react-v7-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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ground truth:
@cometchat/chat-uikit-react@7+@cometchat/chat-sdk-javascript@^4.1.9. Symbols sourced from live v7 docs. This file is the THIN map loaded every run; deep detail is inreferences/*loaded ONLY when the task needs it. Anything marked [v7-verify] is a v6 carry-over to confirm against v7 docs/catalog before shipping.
Use this skill when
"add chat to my React app", "set up CometChat credentials", "integrate CometChat in React", "show a conversations + messages UI", "build a full chat app". An unscoped "add chat" means a production-ready core chat surface (a CometChatConversations list ↔ a message pane, wrapped in CometChatErrorBoundary, sized, affordances wired-or-hidden, mobile collapse) — NOT a bare two-pane demo, and NOT the whole combined app. See the golden path below. It grows on request (users/groups/calls tabs, a details/thread/search side panel, calls) to the full combined app — that recipe lives in cometchat-react-v7-placement.
Install
npm i @cometchat/chat-uikit-react@7 @cometchat/chat-sdk-javascript@4 dompurify (keep the @7/@4 major pins — a bare install resolves to latest and can pull the wrong major). dompurify is required by the kit — the docs install includes it. Voice/video calling also needs @cometchat/calls-sdk-javascript (see cometchat-react-v7-features).
Setup & credentials (essentials — full detail: references/setup-credentials.md)
- Detect React + bundler (Vite→
VITE_, CRA→REACT_APP_, Next→NEXT_PUBLIC_/.env.local). Reuse existing.cometchat/env if present (skip re-setup). - version_conflict — STOP if a non-v7 UI Kit is installed; reconcile first (never mix majors —
RULES.md). - Credentials — OFFER the dashboard fetch FIRST, default to it (never silently "paste it yourself", never defer to a "to finish, add them yourself" TODO — AUDIT-039). Reuse existing
.cometchat/env if present (skip). Else offer both, defaulting to fetch: (a) dashboard fetch (recommended) — load the CLI on demand:npx @cometchat/skills-cli@3 auth login, pick an EXISTING app (provision list --json; never auto-create),provision use --app-id <id> --jsonreturns the creds + writes a neutral.cometchat/config.json(NOT an env file); (b) manual paste — Dashboard → Credentials (dev-only Auth Key). Then the SKILL writes the framework env (§4) — the CLI stops at the fetch; framework detection, env-writing, and codegen are the SKILL's job, never the CLI's (AUDIT-059). Ask & wait if the user must choose or the CLI can't run. Full flow:references/setup-credentials.md. - Write env (correct prefix), gitignore it, never echo the Auth Key. Prod → server-side auth token, not the Auth Key.
- Authorize =
init()+login()resolve; auth error usually means wrong Region.
What ships with it
9 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 af83b1c4b11b
- 1mo ago First seen · 102 lines · 94 tokens per session scan A dbe91e42b735
cometchat-react-v7-core is a skill published in the GitHub repository cometchat/cometchat-skills (150 stars, last pushed 6d ago), licensed MIT. It adds 94 tokens to every session and 5,076 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
extract-source-sample
Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…
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.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
frontend
Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain…
21st-ui
Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.
Error Boundary Tester
Validate error boundary implementations in React and other frameworks ensuring graceful degradation, proper fallback UI rendering, and error recovery flows.