websocket-realtime

websocket-realtime is a skill for Claude Code, Codex from hoangatg/ai-agent-toolkit. It costs 39 tokens per session (814 once invoked), scanned A, original, MIT.

Real-time communication guidance for sending updates between browsers and servers as events happen. It covers WebSockets, server-sent events, peer-to-peer connections, and related tools.

In plain words
What is it for?
Use it for chat, notifications, live dashboards, collaboration, video or audio features, and multiplayer functionality.
Why use it?
It helps you choose how an application should deliver live updates instead of repeatedly asking the server for new data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for chat, notifications, live dashboards, collaboration, video or audio features, and multiplayer functionality.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hoangatg/ai-agent-toolkit/websocket-realtime
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 hoangatg/ai-agent-toolkit --skill websocket-realtime
Clone the repo
git clone --depth 1 https://github.com/hoangatg/ai-agent-toolkit

Made for: Claude Code, Codex.

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 websocket-realtime

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/websocket-realtime/github.svg)](https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/websocket-realtime)
Your own site
<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/websocket-realtime"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/websocket-realtime/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 websocket-realtime

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/websocket-realtime"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/websocket-realtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 814 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 $0.00039 $0.00814
Opus 5 $0.00019 $0.00407
Sonnet 5 $0.00008 $0.00163
Haiku 4.5 $0.00004 $0.00081

Measured 8d ago against content hash 71bee8a05210, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

websocket-realtime 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 8d 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.

.agent/skills/websocket-realtime/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WebSocket & Real-time

When polling isn't fast enough, push.


1. Technology Selection

Technology Direction Best For
WebSocket Bidirectional Chat, gaming, collaboration
SSE (Server-Sent Events) Server → Client Notifications, live feeds
Long Polling Simulated push Legacy browser support
WebRTC Peer-to-peer Video, audio, P2P data
WebTransport Bidirectional (HTTP/3) Next-gen, bleeding edge

Decision Matrix

Need bidirectional? → WebSocket
Server push only?  → SSE (simpler, auto-reconnect)
P2P media?         → WebRTC
Legacy support?    → Long Polling (fallback)

2. WebSocket Patterns

Libraries

Library Ecosystem Features
Socket.io Node.js Rooms, namespaces, fallback
ws Node.js (raw) Lightweight, no overhead
Pusher/Ably Managed Hosted, scaled for you
Supabase Realtime Supabase Postgres changes live

Room/Channel Pattern

Concept Purpose
Rooms Group connections by context (chat room, game)
Namespaces Separate concerns (chat vs notifications)
Broadcasting Send to all in room except sender

3. Scaling WebSockets

Challenge Solution
Sticky sessions Load balancer affinity
Multi-server Redis pub/sub adapter
Connection limits Horizontal scaling + connection pooling
State sync CRDT or operational transforms

4. Reliability Patterns

Pattern Purpose
Heartbeat/Ping Detect dead connections
Auto-reconnect Exponential backoff on disconnect
Message queue Buffer during disconnection
Acknowledgments Confirm message delivery
Idempotency Handle duplicate messages

5. Live Collaboration

Pattern Use Case
CRDT Conflict-free concurrent editing
OT (Operational Transform) Google Docs-style collaboration
Last Write Wins Simple, some data loss OK

Read the full file on GitHub · 120 lines

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. 8d ago First seen · 120 lines · 39 tokens per session scan A 71bee8a05210

Subscribe to this mod's changes

websocket-realtime is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 814 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.