Borrowing it
Nothing to install: this file belongs to OmerLapidot/lg-tv-mcp. 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/OmerLapidot/lg-tv-mcp/main/.claude/skills/verify/SKILL.mdgit 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/verify)<a href="https://agentmods.dev/skills/omerlapidot/lg-tv-mcp/verify"><img src="https://agentmods.dev/badge/skills/omerlapidot/lg-tv-mcp/verify/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/verify"><img src="https://agentmods.dev/badge/skills/omerlapidot/lg-tv-mcp/verify.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 | $0.00033 | $0.00478 |
| Opus 5 | $0.00016 | $0.00239 |
| Sonnet 5 | $0.00007 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
verify 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 10d 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.
What it actually says
Verifying lg-tv-mcp
The surface is the stdio MCP server (server/index.js). Drive it with the MCP
client SDK the same way test/helpers.mjs does — never import server modules
directly.
Against the real TV
Spawn the server with the default environment; it reads the paired config from
~/Library/Application Support/lg-tv-mcp/config.json (no pairing prompt if
clientKey is present):
import { Client } from '<repo>/node_modules/@modelcontextprotocol/sdk/dist/esm/client/index.js';
import { StdioClientTransport } from '<repo>/node_modules/@modelcontextprotocol/sdk/dist/esm/client/stdio.js';
const client = new Client({ name: 'verify-client', version: '0.0.0' });
await client.connect(new StdioClientTransport({
command: process.execPath, args: ['<repo>/server/index.js'], env: process.env,
}));
await client.callTool({ name: 'get_status', arguments: {} });
Gotchas:
- Call
get_statusfirst; if the TV is off,power_on+ ~15s boot, and restore the original power state when done. - The subpath imports (
@modelcontextprotocol/sdk/client/index.js) only resolve from inside the repo; from a scratchpad script use the fullnode_modules/.../dist/esm/...paths as above. - Tool results: JSON in
content[0].text(+structuredContent), exceptscreenshot, which returns a base64imageblock (960x540 JPEG). DRM video planes (Netflix playback) capture as black; UI renders fine.
Against the fake TV
test/fixtures/fake-tv.mjs simulates SSAP over plain ws and serves capture
JPEGs over HTTP on the same port. Point the server at it with
LG_TV_URL=<tv.url> and LG_TV_DATA_DIR=<tempdir with seeded config> —
see withTv() in test/controls.test.js.
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.
- 10d ago First seen · 44 lines · 33 tokens per session scan A b754a8e2608f
verify is a skill published in the GitHub repository OmerLapidot/lg-tv-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 478 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 skills, from other repositories
jetson-video-pipeline
Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact artifact handoffs.
atf-testing
Build ServiceNow Automated Test Framework tests and suites — impersonation, form steps, assertions, server-side script steps, test parameters, and execution via snowcreateatftest / snowexecuteatftest.
gstack-qa
QA lead with real browser testing. Tests your app, finds bugs, fixes them with atomic commits, generates regression tests. Use when the user says "QA", "test this", "find bugs", "exploratory test", "QA this", or "test the app".
mixed-signal-cosim
Run mixed-signal co-simulation — digital gate-level Verilog + analog behavioral models together. Use when the user says "mixed-signal sim", "co-simulation", "digital-analog integration test", or at Step A9 of the analog track.
tabnexus-mcp-evals
Generate, validate, and run isolated Codex-to-TabNexus MCP evaluations with a curated 600-query dataset, executable gold tool labels, safety checks, and best-of-three stability scoring. Use when testing TabNexus MCP tool coverage, Agent behavior, regression quality, destructive-action safety, prompt changes, or a…
blazemeter-private-locations
Comprehensive guide for BlazeMeter Private Locations, including Radar Agent, installation (Docker, Kubernetes, Helm), configuration, management, and troubleshooting. Use when working with Private Locations for (1) Installing agents (Docker, Kubernetes, Helm Chart), (2) Configuring Radar Agent for API Monitoring, (3)…