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 OmerLapidot/lg-tv-mcp --skill lg-tv-remotegit clone --depth 1 https://github.com/OmerLapidot/lg-tv-mcpWrote 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/omerlapidot/lg-tv-mcp/lg-tv-remote)<a href="https://agentmods.dev/skills/omerlapidot/lg-tv-mcp/lg-tv-remote"><img src="https://agentmods.dev/badge/skills/omerlapidot/lg-tv-mcp/lg-tv-remote/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/omerlapidot/lg-tv-mcp/lg-tv-remote"><img src="https://agentmods.dev/badge/skills/omerlapidot/lg-tv-mcp/lg-tv-remote.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 | $0.00066 | $0.00714 |
| Opus 5 | $0.00033 | $0.00357 |
| Sonnet 5 | $0.00013 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
lg-tv-remote 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 12d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LG TV Remote
Control the household LG webOS TV over the local network. Everything is local; nothing goes to a cloud service.
Required workflow
- Call
get_statusfirst. It reports power, pairing, current app, and volume with no side effects. - If the TV is off, ask the user before turning it on with
power_on. Booting takes about 15 seconds; if the result is "booting", wait briefly and checkget_statusonce more. - On the first-ever control call the TV shows a pairing prompt on screen. Tell the user to accept it with the physical remote; the call waits up to a minute. Never retry a failed pairing in a loop — ask the user to accept the prompt and try once more.
- Prefer
launch_appto open apps instead of navigating menus withpress_button. - For text search inside apps, focus the field first (arrows + ENTER via
press_button), thentype_text. set_channelworks only in Live TV; if it fails, open Live TV first withlaunch_app.screenshotreturns the current screen as a JPEG — useful for checking what state an app is in before pressing buttons. DRM-protected video (for example Netflix playback) captures as black; app UI and menus render fine, so a black frame usually means video is playing.measure_sound_levelandcalibrate_sound_meteruse the laptop's own microphone to gauge room loudness, not the TV — they still work when the TV is off. To hit a target loudness, loopmeasure_sound_level→set_volume→measure_sound_leveluntil the reading lands where you want it. Before trusting the absolute dB number, runcalibrate_sound_meteronce: play steady sound, read the dB SPL a phone sound-meter app shows at that moment, and pass it in — the offset is saved and reused afterward. The very first capture triggers a one-time macOS microphone permission prompt for whichever app is hosting this MCP; accept it once.
Tool guide
| Need | Tool |
|---|---|
| Power, pairing, current app, volume | get_status |
| Turn on / off | power_on / power_off |
| Volume or mute | set_volume |
| Remote buttons (arrows, OK, back, play/pause, digits) | press_button |
| Open Netflix/YouTube/etc. | list_apps, launch_app |
| HDMI inputs | switch_input |
| Live TV channels | set_channel |
| Keyboard input | type_text |
| Message on the TV screen | show_notification |
| See what is on the screen (JPEG) | screenshot |
| Measure room loudness with the laptop mic | measure_sound_level |
| One-time mic calibration against a phone SPL app | calibrate_sound_meter |
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.
- 12d ago First seen · 45 lines · 66 tokens per session scan A 4335b8f79d94
lg-tv-remote is a skill published in the GitHub repository OmerLapidot/lg-tv-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 714 once invoked, about $0.0003 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 skills, from other repositories
amazon-alexa
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).
tapo
Control TP-Link Tapo smart home devices (lights, plugs, power strips, hubs and sensors, cameras) via Tapo MCP.
tiaportal-mcp
A skill for controlling Siemens TIA Portal, the engineering software used to configure Siemens PLCs and HMIs. It works through an MCP server, a tool connection that lets an agent inspect and change projects.
homekit
Control HomeKit smart home accessories and view home events via homeclaw-cli. Use when the user asks to control lights, locks, thermostats, fans, blinds, scenes, check device/sensor status, or view recent home activity/events. Examples: "turn off the stairs lights", "lock the front door", "what's the temperature"…
homeclaw
Control HomeKit smart home accessories via HomeClaw MCP tools. Also includes reference data for accessory categories, characteristics, and value formats. This skill should be used when the user wants to: Turn lights on or off, set brightness, or change color temperature Lock or unlock doors Set thermostat temperature…
asset-management
Manage ServiceNow hardware assets, software licenses, and lifecycle states on almhardware/almlicense — license allocation, CMDB-to-asset linking, warranty tracking, inventory aggregation (HAM/SAM).