gemini-cli

A setup guide for connecting Watch Skill, a tool that lets an AI inspect videos, to Gemini CLI, a command-line coding assistant.

In plain words
What is it for?
Use it to add Watch Skill to Gemini CLI and check that the video-watching tools are available.
Why use it?
It explains how to install and configure the connection, including a longer timeout needed for first-time processing of long videos.

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/gemini-cli
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 429 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00429
Opus 5 $0.00000 $0.00215
Sonnet 5 $0.00000 $0.00086
Haiku 4.5 $0.00000 $0.00043

Measured 2d ago against content hash d31e0aebbbe9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

gemini-cli scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Edit `~/.gemini/settings.json` (create it if missing):
docs/agents/gemini-cli.md · 57 lines

What it actually says

Watch Skill in Gemini CLI

Status: config verified against official docs, not machine-tested ☑ (Gemini CLI is not installed on the development machine — please report issues.)

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 ~/.gemini/settings.json (create it if missing):

{
  "mcpServers": {
    "watch-skill": {
      "command": "uvx",
      "args": ["--from", "watch-skill[standard]", "watch-skill", "serve"],
      "timeout": 600000
    }
  }
}

The generous timeout matters: first-time watch_video on a long video can exceed Gemini CLI's default tool timeout.

Smoke test (3 steps)

  1. gemini/mcp should list watch-skill and its tools.
  2. Prompt: "Use watch-skill to watch https://www.youtube.com/watch?v=aqz-KE-bpKQ and tell me what happens at 0:10."
  3. Follow up: "ask that video what appears at the end"ask_video.
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. 2d ago First seen · 57 lines · 0 tokens per session scan B d31e0aebbbe9

Subscribe to this mod's changes

gemini-cli is an agent published in the GitHub repository oxbshw/watch-skill (320 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 429 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.