Borrowing it
Nothing to install: this file belongs to GabrielGoldsteinAnidea/HA-Websocket-Stripper. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GabrielGoldsteinAnidea/HA-Websocket-Stripper/main/CLAUDE.mdgit clone --depth 1 https://github.com/GabrielGoldsteinAnidea/HA-Websocket-StripperWrote 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/instructions/gabrielgoldsteinanidea/ha-websocket-stripper/claude-md)<a href="https://agentmods.dev/instructions/gabrielgoldsteinanidea/ha-websocket-stripper/claude-md"><img src="https://agentmods.dev/badge/instructions/gabrielgoldsteinanidea/ha-websocket-stripper/claude-md/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/instructions/gabrielgoldsteinanidea/ha-websocket-stripper/claude-md"><img src="https://agentmods.dev/badge/instructions/gabrielgoldsteinanidea/ha-websocket-stripper/claude-md.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 | $0.02977 | $0.02977 |
| Opus 5 | $0.01489 | $0.01489 |
| Sonnet 5 | $0.00595 | $0.00595 |
| Haiku 4.5 | $0.00298 | $0.00298 |
Grade A, and why
HA-Websocket-Stripper CLAUDE.md 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 9d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA WebSocket Stripper — project context
What this is / why it exists
Home Assistant Lovelace dashboards on a large instance (here ~3,600 entities) load
slowly because, at startup, the frontend pulls every entity over the websocket
(get_states + a full subscribe_entities) plus the entity/device/area registries, on
top of the frontend JS bundles and every HACS custom-card module.
For wall-panel / kiosk dashboards (a fridge screen, etc.) that only show a handful of entities, that firehose is pure waste. This project makes those dashboards load fast without changing how they look, by serving the real HA frontend through a reverse proxy that trims the entity websocket to just the entities each dashboard uses.
Why this approach (history — don't re-litigate)
We first tried a lighter path: a long-poll backend + a hand-written approximated renderer that redrew cards in plain HTML. It loaded fast but the owner wants pixel-perfect fidelity, and re-implementing Mushroom/button-card/clock-weather/etc. is a losing battle. So we pivoted to: run HA's real frontend, just strip the websocket. That approximation approach was abandoned; this repo is the chosen direction.
A pure "reuse only the card-rendering JS" idea isn't viable: HA's core cards live inside the compiled frontend bundle and can't be loaded standalone. The realistic way to get the real cards + a trimmed subscription is this reverse proxy.
Mechanism
HTTP: everything proxies straight to HA untouched (frontend bundles, /auth/*,
registries, lovelace/config, /hacsfiles/*, camera proxy, …).
WebSocket (/api/websocket): the proxy terminates the browser socket, opens its own
socket to HA, and relays both ways, modifying only:
subscribe_entitieswith no filter → injectentity_ids = <allowlist>so HA streams only those entities (trims at the source);- the
get_statesresult → filtered to the allowlist.
Everything else (auth handshake, registry calls, config, events) passes through, so the real frontend renders your real cards — just without the all-entities firehose. The browser relays its own user token in the ws auth; the proxy doesn't touch auth.
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.
- 9d ago First seen · 181 lines · 2,977 tokens per session scan A 36fd5a57f387
HA-Websocket-Stripper CLAUDE.md is an instructions file published in the GitHub repository GabrielGoldsteinAnidea/HA-Websocket-Stripper (45 stars, last pushed 13d ago), licensed MIT. It adds 2,977 tokens to every session, about $0.0149 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 2026-08-30.
Other instructions, from other repositories
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.