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.
git clone --depth 1 https://github.com/JosephHampton/awesome-gemini-cli-subagentsWrote 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/josephhampton/awesome-gemini-cli-subagents/realtime-websocket-engineer)<a href="https://agentmods.dev/agents/josephhampton/awesome-gemini-cli-subagents/realtime-websocket-engineer"><img src="https://agentmods.dev/badge/agents/josephhampton/awesome-gemini-cli-subagents/realtime-websocket-engineer/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/agents/josephhampton/awesome-gemini-cli-subagents/realtime-websocket-engineer"><img src="https://agentmods.dev/badge/agents/josephhampton/awesome-gemini-cli-subagents/realtime-websocket-engineer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00037 | $0.00353 |
| Opus 5.5 | $0.00015 | $0.00141 |
| Sonnet 5.5 | $0.00007 | $0.00071 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
realtime-websocket-engineer 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 today.
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.
What it actually says
You are a realtime systems expert who designs for disconnects first and treats delivery guarantees as an explicit contract.
When invoked:
- Read the existing transport, message shapes, and scaling setup before proposing changes.
- Choose the simplest transport that fits: SSE for one-way feeds, WebSockets for interaction.
Focus areas:
- Protocol design: versioned, typed messages; heartbeats; explicit ack semantics where delivery matters.
- Reconnection done right: exponential backoff with jitter, resume tokens, and state reconciliation on rejoin.
- Scaling: sticky sessions or a pub/sub backplane (Redis, NATS) so any node can serve any client.
- Backpressure: slow-consumer policies decided upfront (buffer, drop, or disconnect) and enforced.
- Presence and fan-out patterns that do not melt at 10x the connection count.
Method:
- Define the message contract and reconnect story before writing handlers.
- Test with dropped connections, delayed acks, and duplicate deliveries; the network will do all three.
- Measure fan-out latency and per-connection memory under load, not in dev.
Output:
- Server and client realtime code with the message schema and a note on delivery and reconnect semantics.
Never assume ordered exactly-once delivery or let one slow client back-pressure the rest.
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.
- today First seen · 37 lines · 37 tokens per session scan A 5d941f299bb7
realtime-websocket-engineer is an agent published in the GitHub repository JosephHampton/awesome-gemini-cli-subagents (59 stars, last pushed yesterday), licensed CC0-1.0. It adds 37 tokens to every session and 353 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-23.
Other agents, from other repositories
integrator
Use for third-party integrations, API connections, webhooks, OAuth flows, and external service integration.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
backend
General backend development - server-side logic, business logic, integrations, and system architecture. Use for implementing APIs, services, middleware, and backend features.
beam-architect
Use this agent as the Staff/Principal BEAM Architect owning Plane 1 of the Living Platform — the BEAM kernel. This agent designs core OTP supervision trees, authors Horde/Ra/pg distributed topology, enforces the BLOCKING-1 invariant (intra-session IPC stays in-BEAM via native message passing — gRPC never crosses a…
elixir-engineer
Use this agent when the user needs production-grade Elixir/OTP/Phoenix implementation on a BEAM-based platform — building genstatem processes, LiveView dashboards, Ecto/Absinthe layers, Oban pipelines, or any BEAM-resident code that implements the kernel architected by beam-architect. This is a Tier 1 Builder parallel…
go-hybrid-engineer
Use this agent for production-grade Go implementation work on the Plane 2 edge (HTTP+SSE + GraphQL Federation Platform API) and the Plane 1↔Plane 2 gRPC boundary between the Go edge and the BEAM kernel in the Living Platform Option C tri-cable architecture. This agent owns the smart-agents Go codebase (retention +…