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 curiositech/some_claude_skills --skill websocket-streaminggit clone --depth 1 https://github.com/curiositech/some_claude_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/curiositech/some_claude_skills/websocket-streaming)<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/websocket-streaming"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/websocket-streaming/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/curiositech/some_claude_skills/websocket-streaming"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/websocket-streaming.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 | $0.00087 | $0.01310 |
| Opus 5 | $0.00044 | $0.00655 |
| Sonnet 5 | $0.00017 | $0.00262 |
| Haiku 4.5 | $0.00009 | $0.00131 |
Grade A, and why
websocket-streaming 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebSocket Streaming
Real-time bidirectional communication between DAG execution engines and dashboards. Typed event protocols, connection management, and React hook integration.
When to Use
✅ Use for:
- Streaming DAG node state changes to a visualization dashboard
- Sending human gate decisions from dashboard to execution engine
- Live cost ticker and progress updates during execution
- Bi-directional communication (not just server → client)
❌ NOT for:
- One-way server → client updates (consider SSE, simpler)
- REST API design (use
api-architect) - Polling-based status checks (WebSocket replaces polling)
Event Protocol
Server → Client Events
type ServerEvent =
| { type: 'node_state'; node_id: string; status: NodeStatus; output?: any; metrics?: NodeMetrics }
| { type: 'edge_active'; from: string; to: string }
| { type: 'dag_mutated'; mutation: DAGMutation }
| { type: 'cost_update'; spent: number; budget: number; remaining: number }
| { type: 'execution_complete'; results: Record<string, any> }
| { type: 'human_gate_waiting'; node_id: string; presentation: GatePresentation }
| { type: 'error'; node_id?: string; message: string };
Client → Server Events
type ClientEvent =
| { type: 'human_decision'; node_id: string; decision: 'approve' | 'reject' | 'modify'; feedback?: string }
| { type: 'pause_execution' }
| { type: 'resume_execution' }
| { type: 'cancel_execution' };
React Hook: useDAGStream
import { useEffect, useRef, useCallback } from 'react';
export function useDAGStream(dagId: string, store: DAGStore) {
const wsRef = useRef<WebSocket | null>(null);
const reconnectAttempt = useRef(0);
const connect = useCallback(() => {
const ws = new WebSocket(`/api/dags/${dagId}/stream`);
ws.onopen = () => { reconnectAttempt.current = 0; };
ws.onmessage = (event) => {
const msg = JSON.parse(event.data) as ServerEvent;
switch (msg.type) {
case 'node_state':
store.updateNodeData(msg.node_id, {
status: msg.status, output: msg.output, metrics: msg.metrics,
});
break;
case 'cost_update':
store.setCostState({ spent: msg.spent, budget: msg.budget });
break;
case 'dag_mutated':
store.applyMutation(msg.mutation);
break;
case 'execution_complete':
store.setExecutionComplete(msg.results);
break;
}
};
ws.onclose = () => {
// Reconnect with exponential backoff (max 30s)
const delay = Math.min(1000 * 2 ** reconnectAttempt.current, 30000);
reconnectAttempt.current++;
setTimeout(connect, delay);
};
wsRef.current = ws;
}, [dagId, store]);
useEffect(() => { connect(); return () => wsRef.current?.close(); }, [connect]);
// Send client events
const send = useCallback((event: ClientEvent) => {
wsRef.current?.send(JSON.stringify(event));
}, []);
return { send };
}
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 · 174 lines · 87 tokens per session scan A 18d4373e25db
websocket-streaming is a skill published in the GitHub repository curiositech/some_claude_skills (221 stars, last pushed 6d ago), licensed MIT. It adds 87 tokens to every session and 1,310 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
nextjs-app-router
Full end-to-end tRPC setup for Next.js App Router. Covers route handler with fetchRequestHandler (GET + POST exports), TRPCProvider with QueryClientProvider, createTRPCOptionsProxy for RSC prefetching, HydrateClient/HydrationBoundary for hydration, useSuspenseQuery for Suspense, and server-side callers.
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
with-tanstack-query
Compose Angular Query with signal-owned Table filtering, sorting, and pagination state using reactive query options, manual row-model boundaries, direct query data, server counts, and valid injection context.
langbot-dev
Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth…
trigger-realtime-and-frontend
Trigger.dev client/frontend surface: subscribe to runs in realtime (runs.subscribeToRun and the @trigger.dev/react-hooks hook useRealtimeRun), consume metadata and AI/text streams in React (useRealtimeStream), trigger tasks from the browser (useTaskTrigger, useRealtimeTaskTrigger), and mint scoped frontend credentials…
sanity-live-cache-components
Integrates Sanity Live with Next.js Cache Components in next-sanity v13+ apps. Sets up sanityFetch, a shared cachedSanity 'use cache' boundary, , Visual Editing, Presentation Tool, draft mode handling, and the three-layer (Page/Dynamic/Cached) component pattern with explicit perspective/stega prop-drilling. Sequences…