watch

watch is a command for Claude Code from taoufik123-collab/claude-watch. It costs 37 tokens per session (154 once invoked), scanned A, original, MIT.

A video analysis tool that downloads a video, selects useful frames, extracts captions or a transcript, and helps answer questions about the content.

In plain words
What is it for?
Use it to review a video from a URL or local file, identify scene changes, study pacing, and answer content questions.
Why use it?
It lets an agent examine both what appears on screen and what is said, rather than relying on a video title or description.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the claude-watch plugin — 1 skill, 1 command, 1 hook shipped together

Good fit Use it to review a video from a URL or local file, identify scene changes, study pacing, and answer content questions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/taoufik123-collab/claude-watch/watch
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.

Clone the repo
git clone --depth 1 https://github.com/taoufik123-collab/claude-watch

Made for: Claude Code.

Or install claude-watch, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 hook.

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 watch

README.md
[![agentmods](https://agentmods.dev/badge/commands/taoufik123-collab/claude-watch/watch/github.svg)](https://agentmods.dev/commands/taoufik123-collab/claude-watch/watch)
Your own site
<a href="https://agentmods.dev/commands/taoufik123-collab/claude-watch/watch"><img src="https://agentmods.dev/badge/commands/taoufik123-collab/claude-watch/watch/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 watch

Your own site · 80×15
<a href="https://agentmods.dev/commands/taoufik123-collab/claude-watch/watch"><img src="https://agentmods.dev/badge/commands/taoufik123-collab/claude-watch/watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 154 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00037 $0.00154
Opus 5 $0.00018 $0.00077
Sonnet 5 $0.00007 $0.00031
Haiku 4.5 $0.00004 $0.00015

Measured 10d ago against content hash 832f2e4b08d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

watch 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • watch — 88% identical, 6 lines differ
commands/watch.md · 10 lines

What it actually says

Invoke the watch skill (defined in SKILL.md) with the user's arguments: $ARGUMENTS

Follow the skill's full pipeline: preflight setup check → download via yt-dlp → extract frames at auto-scaled fps → pull captions or Whisper transcript → Read each frame → answer the user grounded in frames and transcript. If the user provided no arguments, ask them for a video URL or local path before proceeding.

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. 10d ago First seen · 10 lines · 37 tokens per session scan A 832f2e4b08d6

Subscribe to this mod's changes

watch is a command published in the GitHub repository taoufik123-collab/claude-watch (792 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 154 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 2026-08-30.