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 vasilyu1983/AI-Agents-public --skill software-realtimegit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/software-realtime)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/software-realtime"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/software-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.
<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/software-realtime"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/software-realtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 132 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00035 | $0.03928 |
| Opus 5 | $0.00017 | $0.01964 |
| Sonnet 5 | $0.00007 | $0.00786 |
| Haiku 4.5 | $0.00003 | $0.00393 |
Grade A, and why
software-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 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real-Time Systems
Use this skill for transport choice, collaborative-state design, presence models, reconnection behavior, and multi-node real-time scaling. It owns SSE, WebSocket, CRDT, and managed real-time decisions, not generic backend APIs or frontend-only state management.
Quick Reference
| Task | Use |
|---|---|
| Transport selection | references/transport-selection.md |
| Collaboration, presence, and recovery | references/collaboration-patterns.md |
| Vendor traps and version-pinned gotchas | references/april-vendor-traps.md |
| Edge platforms, CRDT picks, channel limits | references/edge-realtime.md |
| WebSocket smoke test (ping/pong + reconnect) | scripts/ws_smoke_test.py |
| Source map | data/sources.json |
When to Use This Skill
- Choose between SSE, WebSocket, managed real-time, or CRDT collaboration.
- Design chat, live dashboards, notifications, presence, or collaborative editing.
- Plan reconnection, backpressure, offline queues, and connection lifecycle.
- Scale WebSocket or collaboration infrastructure across multiple nodes.
Route Elsewhere
- Request-response APIs or background jobs: use software-backend.
- System-level event architecture: use software-architecture-design.
- Frontend state-management-only questions: use software-frontend.
- Mobile push-notification delivery: use software-mobile.
- Streaming AI response UX: use software-ai-integration.
Defaults
- Default to SSE for one-way text/event streaming.
- Default to WebSocket for bidirectional interactive flows.
- Default to CRDTs for collaborative editing and keep awareness separate from document state.
- Treat presence as its own data model with throttling and expiry rules.
- Design reconnects, idempotency, and slow-consumer handling before worrying about horizontal scale.
What ships with it
12 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.
- agents/openai.yaml 312 B
- data/sources.json 4.5 KB
- evals/evals.json 6.1 KB
- learnings.consolidated.md 593 B
- learnings.md 509 B
- references/april-vendor-traps.md 15 KB
- references/collaboration-patterns.md 693 B
- references/distributed-systems-applied.md 41 KB
- references/edge-realtime.md 8.8 KB
- references/transport-selection.md 7.1 KB
- scripts/check_ws_smoke.py 7.9 KB runs code
- scripts/ws_smoke_test.py 5.5 KB runs code
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 · 215 lines · 35 tokens per session scan A 41eb1d558a5e
software-realtime is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 3,928 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
dev-nextjs
Next.js development (App Router, Server Components, caching, streaming). Trigger when the user works with Next.js, modifies app/, pages/, next.config, or talks about RSC, Server Actions, Route Handlers, middleware.
nextjs-app-router
Next.js App Router patterns including server components, route handlers, middleware, parallel routes, intercepting routes, streaming, and caching strategies. Use when the user is building with Next.js 13+/14+/15+, asking about the App Router, server components vs client components, route handlers, Next.js middleware…
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
architecture-patterns
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or…
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.