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 UCSC-VLAA/VisualClaw --skill video-sequence-comprehensiongit clone --depth 1 https://github.com/UCSC-VLAA/VisualClawWrote 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/ucsc-vlaa/visualclaw/video-sequence-comprehension)<a href="https://agentmods.dev/skills/ucsc-vlaa/visualclaw/video-sequence-comprehension"><img src="https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/video-sequence-comprehension.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00040 | $0.00266 |
| Opus 5 | $0.00020 | $0.00133 |
| Sonnet 5 | $0.00008 | $0.00053 |
| Haiku 4.5 | $0.00004 | $0.00027 |
Grade A, and why
video-sequence-comprehension 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 7d 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.
What it actually says
Comprehend Complete Action Sequences in Videos
- Identify all key frames: Examine each image/frame sequentially to map out every distinct action step.
- Track action order: Note the temporal sequence of actions—what happens first, second, third, etc.
- Match full sequences: Compare the complete action sequence observed against all options, not just the first matching action.
- Verify endpoint: Ensure the final state in the video matches the conclusion described in the correct answer option.
- Cross-check details: Pay attention to specific objects, tools, and methods used (e.g., "rinses" vs. "puts in dryer").
Example: In the dog mat scenario, frames show: pickup → sink wash → rinse off. Option (E) matches this complete sequence. Option (B) incorrectly ends with "dryer," which is not shown.
Anti-pattern: Selecting an option because it mentions the first action (washing) without verifying the final action matches the video.
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.
- 7d ago First seen · 18 lines · 40 tokens per session scan A 5726d192138e
video-sequence-comprehension is a skill published in the GitHub repository UCSC-VLAA/VisualClaw (55 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 266 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.
Other skills, from other repositories
ppt-generation
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
video-generation
Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.
ideation
Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.
json-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.