agent-zero

A setup guide for connecting the Watch Skill service to Agent Zero, an AI agent application, through the Model Context Protocol.

In plain words
What is it for?
Use it to install the service with uvx or from source, add its MCP configuration in Agent Zero, and test it with a YouTube video.
Why use it?
It explains how to install, configure, and smoke-test the connection so Agent Zero can access the watch-related tools.

Agent

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/agent-zero
Clone the repo
git clone --depth 1 https://github.com/oxbshw/watch-skill
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 506 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 $0.00000 $0.00506
Opus 5 $0.00000 $0.00253
Sonnet 5 $0.00000 $0.00101
Haiku 4.5 $0.00000 $0.00051

Measured yesterday against content hash 20f953eb3294, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-zero 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 yesterday.

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/agent-zero.md · 67 lines

What it actually says

Watch Skill in Agent Zero

Status: doc-verified ☑ — config matches the official Agent Zero MCP docs; not executed here.

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

Agent Zero's Settings UI → MCP → external servers takes the standard mcpServers JSON (persisted to tmp/settings.json under "mcp_servers"):

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

Agent Zero queries the server on startup and injects the tool list into its system prompt, so the tools are visible to the agent immediately.

Smoke test (3 steps)

  1. New chat: "Watch https://www.youtube.com/watch?v=aqz-KE-bpKQ and tell me what happens at 0:10."
  2. Watch the tool router pick watch_video.
  3. Follow up: "what color is the bird?" — should route to ask_video, no re-processing.

Notes

  • Agent Zero usually runs dockerized. Run the MCP server inside the same container (or use watch-skill serve --http on the host and configure a remote streaming-HTTP entry instead) so frame paths in reports are readable where the agent runs, and mount ~/.watch-skill/ if the container is ephemeral.
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. yesterday First seen · 67 lines · 0 tokens per session scan A 20f953eb3294

Subscribe to this mod's changes

agent-zero is an agent published in the GitHub repository oxbshw/watch-skill (320 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 506 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.