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 sharing-resultsgit 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/sharing-results)<a href="https://agentmods.dev/skills/oxbshw/watch-skill/sharing-results"><img src="https://agentmods.dev/badge/skills/oxbshw/watch-skill/sharing-results.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.00369 |
| Opus 5 | $0.00037 | $0.00185 |
| Sonnet 5 | $0.00015 | $0.00074 |
| Haiku 4.5 | $0.00007 | $0.00037 |
Grade A, and why
sharing-results 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.
What it actually says
Sharing results
An analysis that lives only in this chat dies with it. The viewer turns an analyzed video into a single HTML file anyone can open — no server, no internet, no Watch Skill install on the other end.
Generate the page
watch-skill viewer <video_id-or-source> [-o <path>]
The file contains, self-contained (frames inlined as data URIs, zero external requests):
- a timeline with key-frame cards and timestamps,
- the transcript and all on-screen text (OCR),
- every question asked about the video so far, with its answer, confidence badge, and the exact timestamped evidence cited.
Answer questions FIRST, then generate. The page includes cached answers, so ask what the user cares about before rendering — a viewer generated before any questions holds only frames and transcript.
Hand-off patterns
- Bug ticket: run
watch-skill extract bug-reportfirst, then the viewer — the ticket gets the structured report, the viewer link gives reviewers the evidence. - Review request: send the file itself (it is one .html, typically well under a few hundred KB); it opens in any browser, RTL text renders correctly, nothing phones home.
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.
- yesterday Changed 76708a343a81
- 8d ago First seen · 42 lines · 75 tokens per session scan A f8565925de19
sharing-results is a skill published in the GitHub repository oxbshw/watch-skill (337 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 369 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.
Other skills, from other repositories
vision-multimodal
A skill that adds image, video, audio, document, and screenshot understanding to a text-only model. It includes tasks such as reading text from images, locating objects, transcribing speech, and analyzing media.
glmv-pdf-to-ppt
Convert a PDF (research paper, report, or any document) into a polished multi-slide HTML presentation with a structured outline JSON and summary markdown. Trigger this skill when the user mentions making slides or a PPT from a PDF — in Chinese or English.
glmv-pdf-to-web
Convert a PDF (research paper, technical report, or project document) into a beautiful single-page academic/project website with a structured outline JSON. Trigger this skill when the user wants to make a paper page, project homepage, or academic website from a PDF — in Chinese or English.
glmocr-formula
Official skill for recognizing and extracting mathematical formulas from images and PDFs into LaTeX format using ZhiPu GLM-OCR API. Supports complex equations, inline formulas, and formula blocks. Use this skill when the user wants to extract formulas, convert formula images to LaTeX, or OCR mathematical expressions.
glmocr-sdk
A Python SDK and command-line tool for extracting text and structured content from images, PDFs, and scanned documents using GLM-OCR.
glmocr-handwriting
Official skill for recognizing handwritten text from images using ZhiPu GLM-OCR API. Supports various handwriting styles, languages, and mixed handwritten/printed content. Use this skill when the user wants to read handwritten notes, convert handwriting to text, or OCR handwritten documents.