claude-desktop

claude-desktop is an agent for coding agents from oxbshw/watch-skill. It costs 0 tokens per session (480 once invoked), scanned A, original, MIT.

Setup and configuration instructions for connecting the watch-skill video tool to Claude Desktop, an app for chatting with an AI assistant. The guide includes installation, configuration, and a basic connection test.

In plain words
What is it for?
Use it to install watch-skill, add it to Claude Desktop, and verify that the server responds to the app.
Why use it?
It explains where Claude Desktop stores tool settings and how to add the video server without losing existing configuration.

Agent

Part of the watch-skill plugin — 10 skills, 1 command, 27 agents, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add agents/oxbshw/watch-skill/claude-desktop
Clone the repo
git clone --depth 1 https://github.com/oxbshw/watch-skill

Or install watch-skill, the plugin that ships this one along with the rest of its 10 skills, 1 command, 27 agents, 1 MCP server.

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 claude-desktop

README.md
[![agentmods](https://agentmods.dev/badge/agents/oxbshw/watch-skill/claude-desktop.svg)](https://agentmods.dev/agents/oxbshw/watch-skill/claude-desktop)
Your own site
<a href="https://agentmods.dev/agents/oxbshw/watch-skill/claude-desktop"><img src="https://agentmods.dev/badge/agents/oxbshw/watch-skill/claude-desktop.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00480
Opus 5 $0.00000 $0.00240
Sonnet 5 $0.00000 $0.00096
Haiku 4.5 $0.00000 $0.00048

Measured 5d ago against content hash dd1958c38c9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

claude-desktop 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 5d 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.

docs/agents/claude-desktop.md · 58 lines

What it actually says

Watch Skill in Claude Desktop

Status: machine-configured ◐watch-skill setup wrote this config on a real machine (existing keys preserved, backup taken) and the server command answered MCP initialize; a full in-app session was not run.

Install

uvx --from "watch-skill[standard]" watch-skill doctor

uvx fetches the package on first use and needs no checkout. Prefer a permanent install? pipx install "watch-skill[standard]", then use "command": "watch-skill", "args": ["serve"] in the config below.

git clone https://github.com/oxbshw/watch-skill && cd watch-skill
uv sync --extra all
uv run watch-skill doctor

Then run watch-skill setup, which writes the config pointing at your checkout rather than the published package.

Configure

Edit %APPDATA%\Claude\claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "watch-skill": {
      "command": "uvx",
      "args": ["--from", "watch-skill[standard]", "watch-skill", "serve"]
    }
  }
}

Tip: watch-skill setup (see the 2-minute install) detects Claude Desktop and writes this for you, backing up the existing file.

Smoke test (3 steps)

  1. Fully quit and restart Claude Desktop (tray icon too), then check the tools icon (🔨) lists watch-skill.
  2. Ask: "Watch https://www.youtube.com/watch?v=aqz-KE-bpKQ with watch-skill — what happens at 0:10?"
  3. Follow up: "Search my videos for 'butterfly'" — should hit search_videos.
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. 5d ago First seen · 58 lines · 0 tokens per session scan A dd1958c38c9d

Subscribe to this mod's changes

claude-desktop is an agent published in the GitHub repository oxbshw/watch-skill (333 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 480 tokens. 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.