agentmods.dev

tv-mcp: Instructions file for Claude Code

CLAUDE.md

tv-mcp CLAUDE.md is an instructions file for Claude Code from skdonthi/tv-mcp. It costs 773 tokens per session, scanned A, original, MIT.

Project instructions for tv-mcp, a tool for developing web apps on Samsung Tizen and LG webOS smart TVs.

In plain words
What is it for?
Use them when building, signing, installing, launching, or debugging TV apps on real Samsung or LG panels.
Why use it?
They give the coding agent the project’s architecture rules, hardware lessons, release process, and testing expectations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is skdonthi/tv-mcp's own configuration. It tells Claude Code how to work on tv-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tv-mcp configures →

not rated 6repo +2 3mo ago A scan 773 tokens original MIT
View source ↗ skdonthi/tv-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to skdonthi/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.

Copy the file
curl -O https://raw.githubusercontent.com/skdonthi/tv-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/skdonthi/tv-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for tv-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/skdonthi/tv-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/skdonthi/tv-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/skdonthi/tv-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/skdonthi/tv-mcp/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.

agentmods 80×15 button for tv-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/skdonthi/tv-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/skdonthi/tv-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 773 This file is loaded in full into every session.
When invoked 773 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00773 $0.00773
Opus 5.5 $0.00309 $0.00309
Sonnet 5.5 $0.00155 $0.00155
Haiku 4.5 $0.00077 $0.00077

Measured 2mo ago against content hash f2d34d36f7ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tv-mcp 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 2mo 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.

CLAUDE.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tv-mcp — agent context

MCP server for Smart TV app development: build/sign/install/launch/debug web apps on Samsung Tizen and LG webOS panels. TypeScript, ESM, Node ≥ 20.

Architecture rules

  • Two planes. Platform plane per vendor (src/drivers/* behind the TVDriver interface in src/types.ts) for what genuinely differs; shared CDP plane (src/cdp/bridge.ts) for screenshot/console/eval — both TVs are Chromium underneath. Never duplicate into a driver what CDP can do once.
  • Progressive disclosure. Tools live in tiers (see src/server.ts): tier 0 always visible, tier 1 enabled on device connect, tier 2 on debug launch. New tools must declare a tier. Tool descriptions stay one sentence; deep knowledge goes in src/docs.ts topics (served as MCP resources).
  • Errors are UI for agents. Every throw is a TVMcpError with a remedy that names the next action. "Failed" without a remedy does not merge.
  • Real hardware wins. When firmware behavior contradicts the vendor CLI docs, code to the firmware and record the finding in docs/KNOWLEDGE.md.

Hardware lessons already paid for (do not regress)

  • Tizen installs: sdb push + shell 0 vd_appinstall — the tizen install CLI fails silently on TV firmware.
  • pkgcmd/kill takes the package id (TvMcpTest0), not the full app id.
  • shell 0 debug hangs if the app is already running — kill (by pkgId) and clear stale port forwards first; always run it with a timeout.
  • Real TVs reject the generic SDK distributor cert; only Samsung-issued certificates (DUID-bound) install. doctor classifies profiles.
  • Samsung HG (hospitality) firmware disables the IP-remote service (ports 8001/8002); remote_key on those panels = eval_js synthetic KeyboardEvents fallback.

Release flow

Bump version in three places: package.json, server.json, src/server.ts (McpServer version). Update CHANGELOG.md (Keep a Changelog 1.1.0). Commit, then gh release create vX.Y.Z — the publish workflow (npm OIDC trusted publishing + MCP Registry) does the rest. Versions 0.1.0–0.3.0 are unpublished/burnt on npm; next public release starts at 0.4.1+.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 2mo ago First seen · 62 lines · 773 tokens per session scan A f2d34d36f7ea

Subscribe to this mod's changes

tv-mcp CLAUDE.md is an instructions file published in the GitHub repository skdonthi/tv-mcp (6 stars, last pushed 3mo ago), licensed MIT. It adds 773 tokens to every session, about $0.0031 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 2026-08-31.

Hardware and IoTWriting and docshospitalitymcpsmart-tvtizentizen-apptizen-os
Related

tv-mcp CLAUDE.md compared with instructions from other repositories

tv-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tv-mcp CLAUDE.mdskdonthi/tv-mcpInstructions file63mo agoMITA773Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode