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.
npx skills add oxbshw/watch-skill --skill watchgit clone --depth 1 https://github.com/oxbshw/watch-skillWrote 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.
[](https://agentmods.dev/skills/oxbshw/watch-skill/watch)<a href="https://agentmods.dev/skills/oxbshw/watch-skill/watch"><img src="https://agentmods.dev/badge/skills/oxbshw/watch-skill/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.
<a href="https://agentmods.dev/skills/oxbshw/watch-skill/watch"><img src="https://agentmods.dev/badge/skills/oxbshw/watch-skill/watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
- Socket pass
- Snyk warn
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.01338 |
| Opus 5.5 | $0.00028 | $0.00535 |
| Sonnet 5.5 | $0.00014 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
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 1mo 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.
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.doctorauto-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-skillitself is not on PATH:pip install watch-skill(oruv 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 60bounds 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-onlyskips frames entirely (fastest; no video download when captions exist).--max-frames Ntightens the token budget (default: duration-tiered, hard cap 100, max 2 fps).
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.
- 1mo ago Changed 0a7b7a5be76f
- 1mo ago Changed d8c074579a4b
- 1mo ago Changed 5e0d9e9ed67d
- 2mo ago First seen · 125 lines · 71 tokens per session scan A 5b86badd6ad0
watch is a skill published in the GitHub repository oxbshw/watch-skill (544 stars, last pushed 5d ago), licensed MIT. It adds 71 tokens to every session and 1,338 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
multimodal-stable-diffusion
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
screenpipe-workflow-maintenance
Investigate and review evidence-backed workflows with Screenpipe tools and shared drafts.
render-html-report
Produce a human-facing visual report — a chart, dashboard, scorecard, or styled summary — that renders as a live page in the screenpipe viewer instead of plain text. Use when the task asks for a visual/graphical output rather than a plain note; do NOT use for plain text or raw data (prefer a markdown note for those).
cerul
Search local videos by meaning, exact words or reference image, analyze scenes, cut short clips by intent, and export clips using the cerul CLI.
video-sop
Edit the attached Screenpipe video project, inspecting its real screenshots and preserving the source instructions.
screenpipe-chats
Search what was said in existing screenpipe, Codex, Claude, Cursor, and Gemini CLI chats, then continue or steer one exact chat when the user explicitly asks. Use for requests about finding another agent conversation, recalling what an agent said, or sending work to one.