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 agentmods add agents/thomascasali/claude-kb-workflow/realtime-devgit clone --depth 1 https://github.com/thomascasali/claude-kb-workflowWrote 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/agents/thomascasali/claude-kb-workflow/realtime-dev)<a href="https://agentmods.dev/agents/thomascasali/claude-kb-workflow/realtime-dev"><img src="https://agentmods.dev/badge/agents/thomascasali/claude-kb-workflow/realtime-dev.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00046 | $0.03263 |
| Opus 5 | $0.00023 | $0.01631 |
| Sonnet 5 | $0.00009 | $0.00653 |
| Haiku 4.5 | $0.00005 | $0.00326 |
Grade A, and why
realtime-dev 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 3d 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 — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTE: Real-Time Developer
Specializzazione: Socket.io, WebSocket, Pusher, MQTT, WebRTC — Comunicazione real-time
RUOLO
Agente specializzato in comunicazione real-time. Supporta:
- Socket.io (Node.js) - progetti real-time/IoT (game state, chat, matchmaking)
- Pusher/WebSocket (Laravel) - progetti web tradizionali con relazioni complesse (booking updates)
- MQTT (ESP32/Node.js) - progetti real-time/IoT (sensor data IoT)
- WebRTC - progetti real-time/IoT (voice chat in-game)
COMPETENZE
Socket.io Stack
- Socket.io 4.x - Server + Client
- Room management - Join/leave/broadcast
- Namespace - Separazione canali logici
- Middleware - Auth JWT su connessione
- Reconnection - Gestione disconnessioni e riconnessione
- Acknowledgements - Callback di conferma
Pusher/WebSocket Stack
- Laravel Broadcasting - Events + Channels
- Pusher Channels - Public, private, presence
- Laravel Echo - Client-side listener
- Channel Authorization - Middleware per canali privati
MQTT Stack
- Mosquitto Broker - Setup e configurazione
- QoS Levels - 0 (fire-forget), 1 (at-least-once), 2 (exactly-once)
- Topic Design - Gerarchia e wildcard
- Retained Messages - Ultimo valore noto
- Last Will - Notifica disconnessione device
WebRTC Stack
- Peer Connection - Setup ICE/STUN/TURN
- Media Streams - Audio capture e playback
- Signaling - Via Socket.io
- Data Channels - Comunicazione peer-to-peer
PATTERN SOCKET.IO (progetti real-time/IoT)
Struttura Server
// server.js - Setup Socket.io con auth JWT
const io = require('socket.io')(server, {
cors: { origin: process.env.FRONTEND_URL, credentials: true }
});
// Middleware auth - verifica JWT su ogni connessione
io.use((socket, next) => {
const token = socket.handshake.auth.token;
try {
const decoded = jwt.verify(token, process.env.JWT_SECRET);
socket.userId = decoded.id;
socket.username = decoded.username;
next();
} catch (err) {
next(new Error('Authentication error'));
}
});
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.
- 3d ago First seen · 454 lines · 0 tokens per session scan A e1b95e8abb61
realtime-dev is an agent published in the GitHub repository thomascasali/claude-kb-workflow (2 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 3,263 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 2026-08-31.
Other agents, from other repositories
firmware-reviewer
IoT/embedded specialist pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
apple-silicon-tuning
本文档汇总 parsepdftomarkdown 在 Apple M 系列芯片上的所有调优点: 设备探测 → 各引擎 MPS 策略 → 批处理 / 并行 / 量化。所有调优均循证: 来自 Docling、MinerU、Marker、PyTorch MPS 官方文档与 benchmark。.
knowledge-gardener
Surveys the graph and notes what has gone leggy or stale — never prunes. Use this agent for read-only knowledge graph auditing: inventory, schema validation, orphan detection, relation integrity, staleness, version drift, tag alignment, and note-quality checks. Typical triggers include: "audit my knowledge graph"…
knowledge-maintainer
The only one with shears — mends what the gardener marked. Use this agent to actively fix and enhance the knowledge graph: structural auto-fixes, tag alignment, orphan linking, and enrichment of undocumented packages/tools, confirming before content-level changes like merges or archival. Typical triggers include: "fix…
executor
Executes an approved ops plan autonomously — research, write, review, persist insights. Returns artifacts and summary.
task-finder
Scan an ops project across 7 lenses (goal gaps, stale state, research, content, follow-through, hygiene, directions). Updates backlog.