watch

watch is a skill for Claude Code from oxbshw/watch-skill. It costs 71 tokens per session (1,340 once invoked), scanned A, original, MIT.

A command for watching videos from URLs, streams, or local files, then extracting useful evidence such as frames, visible text, and speech transcripts.

In plain words
What is it for?
Reviewing recorded meetings, screen captures, lectures, and generated videos; asking questions about their contents; and checking visual work through a capture-and-review loop.
Why use it?
It preserves the analysis in a searchable index so follow-up questions do not require processing the video again.

Skill for Claude Code

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

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 skills/oxbshw/watch-skill/watch
Any agent
npx skills add oxbshw/watch-skill --skill watch
Clone the repo
git clone --depth 1 https://github.com/oxbshw/watch-skill

Made for: Claude Code.

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 watch

README.md
[![agentmods](https://agentmods.dev/badge/skills/oxbshw/watch-skill/watch.svg)](https://agentmods.dev/skills/oxbshw/watch-skill/watch)
Your own site
<a href="https://agentmods.dev/skills/oxbshw/watch-skill/watch"><img src="https://agentmods.dev/badge/skills/oxbshw/watch-skill/watch.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,340 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 $0.00071 $0.01340
Opus 5 $0.00036 $0.00670
Sonnet 5 $0.00014 $0.00268
Haiku 4.5 $0.00007 $0.00134

Measured 6d ago against content hash 5b86badd6ad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

skills/watch/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/watch (Watch Skill)

You don't have a video input; this skill gives you one. It is a thin wrapper around the watch-skill CLI — all logic lives in the engine, so this skill works identically on every harness (Claude Code, Codex, Cursor, ...).

This is a drop-in upgrade of the classic claude-video /watch skill: same invocation shape, plus a persistent index (ask answers follow-ups without re-processing), OCR on frames, scene-aware sampling with perceptual dedup, local Whisper (offline by default, no API key needed), and THE LOOP (capture -> critique -> fix -> re-capture) for iterating on your own output.

Step 0 — Preflight (first invocation per session)

watch-skill doctor --json
  • Exit 0 → proceed silently. Do NOT announce that setup is fine.
  • Non-zero → the JSON lists each failing check with a fix. doctor auto-bootstraps ffmpeg and yt-dlp into a managed bin dir on Windows/macOS/ Linux; re-run once after it reports fixes. Only involve the user when a check still fails after remediation.
  • If watch-skill itself is not on PATH: pip install watch-skill (or uv tool install watch-skill), then re-run the doctor.

No API key is required for acquisition, transcription, OCR, indexing, or search: transcription falls back to local faster-whisper. Visual synthesis and verification can use the user's existing Anthropic, OpenAI, Gemini, or OpenRouter key, or an optional local Ollama model. The agent and provider are independent; see the configuring-vision skill. Cloud STT is opt-in (--cloud-stt) and only ever uploads extracted mono audio — the video file never leaves the machine.

Step 1 — Watch

Parse the user input into source + optional question, then:

watch-skill watch "<source>" [--start T --end T] [--max-frames N] [--transcript-only]
  • Any yt-dlp-supported site (1800+), direct media URLs, HLS/DASH manifests (--duration 60 bounds live streams), and local files all work.
  • --start / --end (SS, MM:SS, HH:MM:SS) switch to dense focused sampling of that window — use for "what happens at 2:30?" questions and for any video over ~10 minutes when the user cares about one section.
  • --timestamps T1,T2,... pins frames at transcript-flagged moments ("look here", "as you can see") that visual selection may miss.
  • --transcript-only skips frames entirely (fastest; no video download when captions exist).
  • --max-frames N tightens the token budget (default: duration-tiered, hard cap 100, max 2 fps).

Read the full file on GitHub · 125 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. 6d ago First seen · 125 lines · 71 tokens per session scan A 5b86badd6ad0

Subscribe to this mod's changes

watch is a skill published in the GitHub repository oxbshw/watch-skill (333 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,340 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

agent-vision

Visually verify rendered output before claiming a UI/visual task is done. Use whenever you generate or edit a visual artifact — frontend HTML/CSS/JSX, a generated chart or plot, an SVG/diagram, a PDF, or an exported image. AgentVision renders the artifact, "sees" it, and returns a machine-graded report (pass/warn/fail…

amitpatole/agent-vision · 101 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

captions-overlay

Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid. Load when adding captions/subtitles to a talking-head or launch video, when deciding whether…

heygen-com/hyperframes · 136 tokens

skill-release-gate

Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.

rohitg00/ai-engineering-from-scratch · 36 tokens

muapi-media-editing

Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.

SamurAIGPT/Generative-Media-Skills · 41 tokens

muapi-storyboard-to-cooking-video

Turn a single photo of a person into a 15-second cinematic pasta-making (or other cuisine) tutorial video. First builds a composite reference sheet (character + kitchen + 9-step action board), then animates the full cooking sequence with audio in a single continuous shot.

SamurAIGPT/Generative-Media-Skills · 64 tokens