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 roedyrustam/vibes-plug --skill realtime-collaboration-expertgit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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/roedyrustam/vibes-plug/realtime-collaboration-expert)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/realtime-collaboration-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/realtime-collaboration-expert/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/roedyrustam/vibes-plug/realtime-collaboration-expert"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/realtime-collaboration-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.01299 |
| Opus 5 | $0.00024 | $0.00649 |
| Sonnet 5 | $0.00010 | $0.00260 |
| Haiku 4.5 | $0.00005 | $0.00130 |
Grade A, and why
realtime-collaboration-expert 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 6d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real-Time Collaboration Expert / Ahli Kolaborasi Real-Time
English
Description
Expert guide for implementing multiplayer, real-time collaboration features in web applications. Covers Conflict-free Replicated Data Types (CRDTs) like Yjs/Automerge, WebSockets, WebRTC, and Managed services like Liveblocks or Pusher.
Instructions
- CRDTs for State: Use CRDTs (e.g.,
yjsorautomerge) instead of Operational Transformation (OT) for handling distributed state and concurrent document editing smoothly. - Connection Resiliency: Always implement automatic reconnection logic with exponential backoff for WebSockets. Handle offline states gracefully by syncing local changes once reconnected.
- Presence & Awareness: Implement presence indicators (who is online, cursor positions) separated from the core document state to reduce bandwidth and storage overhead.
- Security in Real-time: Authenticate and authorize every WebSocket connection upon establishment and validate all incoming socket messages to prevent malicious payloads.
- Scale: Be mindful of message broadcasting limits. Use Redis Pub/Sub or similar message brokers when scaling WebSocket servers across multiple instances.
Implementation Checklist
- Choose a CRDT library (Yjs/Automerge) and a corresponding provider (WebSockets, WebRTC, Liveblocks).
- Initialize the shared document state and bind it to the frontend UI components (e.g., ProseMirror, Monaco).
- Implement presence (awareness) to broadcast cursor positions and active user lists.
- Handle offline states by buffering local changes and syncing upon reconnection.
Example: Yjs with WebSocket Provider
import * as Y from 'yjs'
import { WebsocketProvider } from 'y-websocket'
// 1. Initialize a shared Yjs document
const ydoc = new Y.Doc()
// 2. Connect to the WebSocket room
const provider = new WebsocketProvider('ws://localhost:1234', 'my-room-name', ydoc)
// 3. Share state (e.g., an array of chat messages)
const yarray = ydoc.getArray('messages')
yarray.observe(event => {
console.log('Messages updated:', yarray.toArray())
})
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.
- 6d ago First seen · 100 lines · 48 tokens per session scan A 7a9b19e41987
realtime-collaboration-expert is a skill published in the GitHub repository roedyrustam/vibes-plug (50 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 1,299 once invoked, about $0.0002 per session on Opus 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
sdlc-spec-slice-writer
Use to write focused implementation SPEC slices for UI, API, data, admin, permissions, directory, observability, or release.
dev-fullstack-feature
Use when the requested feature genuinely spans at least two delivery layers such as frontend, backend, API, data, scripts, or tests. Do not expand a single-layer change into a full-stack workflow.
algolia-search
Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuningUse when "adding search to, algolia, instantsearch, search api, search functionality, typeahead, autocomplete search, faceted search, search index, search as you type, algolia, search, instantsearch…
fullstack-coder
Full-stack implementation agent that writes complete, production-ready code following an approved architecture and schema. Triggers on: write the code, implement features, build the app, code the MVP, generate codebase.
performance-optimization
Profile and optimize web performance, Core Web Vitals, and backend latencies. Bootstrap on demand.
auth-web-cloudbase
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.