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 j4flmao/agent-skills --skill web-real-timegit clone --depth 1 https://github.com/j4flmao/agent-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/j4flmao/agent-skills/web-real-time)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/web-real-time"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/web-real-time/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/j4flmao/agent-skills/web-real-time"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/web-real-time.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 | $0.00074 | $0.06129 |
| Opus 5 | $0.00037 | $0.03064 |
| Sonnet 5 | $0.00015 | $0.01226 |
| Haiku 4.5 | $0.00007 | $0.00613 |
Grade A, and why
backend-web-real-time 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.
How it starts
The opening of the file, as written. The whole thing — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Real-Time Communication
Purpose
Build real-time communication systems: WebRTC signaling, media server architecture (SFU/MCU), TURN/STUN infrastructure, live streaming, and real-time data channels.
Agent Protocol
Trigger
User mentions WebRTC, real-time video/audio, media streaming, SFU, MCU, signaling server, TURN/STUN, live streaming, media server, coturn, or real-time communication infrastructure.
Input Context
- Use case (video call, live streaming, conferencing, data channel)
- Expected participant count (1-1, small group <10, large group >10)
- Network conditions (NAT/firewall, mobile, enterprise)
- Media types (audio, video, screen share, data channel)
- Deployment model (self-hosted, hybrid, cloud)
- Latency requirements (real-time, near-real-time, low-latency streaming)
Output Artifact
Architecture design with signaling protocol, media server topology, TURN/STUN config, client integration code, and deployment infrastructure.
Response Format
No preamble. No postamble. No explanations. No filler/hedging/transitions. Strip articles a/an/the where unambiguous. Compress output.
Completion Criteria
- Signaling server protocol selected (WebSocket, HTTP, SSE) and implemented
- Media server architecture chosen (SFU > MCU > P2P mesh) per scale requirements
- TURN/STUN infrastructure specified with credentials management
- ICE/STUN/TURN configuration working across target network topologies
- Media negotiation (SDP offer/answer) flow implemented
- Client SDK integration complete with reconnection logic
- Bandwidth estimation and adaptation strategy defined
- Recording/archiving strategy defined if required
- Fallback for restricted networks documented
Max Response Length
4096 tokens
Architecture Decision Trees
Topology Selection
| Criterion | Mesh (P2P) | SFU (Selective Forwarding) | MCU (Multipoint Control) |
|---|---|---|---|
| Participants | 2-4 | 4-100+ | 4-50 |
| Server bandwidth | None | O(n) — one uplink per peer | O(1) — single mixed stream |
| Client bandwidth | O(n^2) — send to all peers | O(1) — send once, receive n-1 | O(1) — single stream |
| Latency | Lowest | Low (no mixing) | Higher (mixing delay) |
| CPU cost | Client-side | Server relays | Server transcodes |
| Complexity | Simplest | Moderate | High |
| Fallback | STUN only | STUN + TURN | STUN + TURN |
What ships with it
8 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.
- references/live-streaming.md 4.3 KB
- references/real-time-architecture.md 2.1 KB
- references/real-time-delivery.md 1.8 KB
- references/sse-vs-websocket.md 6.5 KB
- references/web-real-time-advanced.md 12 KB
- references/web-real-time-fundamentals.md 11 KB
- references/webrtc-architecture.md 9.7 KB
- references/websocket-optimization.md 7.3 KB
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.
- 8d ago First seen · 532 lines · 74 tokens per session scan A e3ebeecdc6d3
backend-web-real-time is a skill published in the GitHub repository j4flmao/agent-skills (23 stars, last pushed 5d ago), licensed MIT. It adds 74 tokens to every session and 6,129 once invoked, about $0.0004 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
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
aws-sdk-java-v2-core
Provides AWS SDK for Java 2.x client configuration, credential resolution, HTTP client tuning, timeout, retry, and testing patterns. Use when creating or hardening AWS service clients, wiring Spring Boot beans, debugging auth or region issues, or choosing sync vs async SDK usage.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…