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 Akakaui/visual-browser-agent --skill video-evidence-reviewgit clone --depth 1 https://github.com/Akakaui/visual-browser-agentWrote 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/akakaui/visual-browser-agent/video-evidence-review)<a href="https://agentmods.dev/skills/akakaui/visual-browser-agent/video-evidence-review"><img src="https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/video-evidence-review/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/akakaui/visual-browser-agent/video-evidence-review"><img src="https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/video-evidence-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00865 |
| Opus 5 | $0.00017 | $0.00432 |
| Sonnet 5 | $0.00007 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
video-evidence-review 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Evidence Review Skill
When to Use
Use this skill to analyze recordings without blowing up context:
- Long interaction captures (over 30 seconds)
- Locating a specific event inside a long recording
- Building storyboards of multi-step flows
- Verifying what happened during an automated session
Core Principle
A recording is an INDEXABLE DATASET, not one giant prompt. Never feed an entire recording through review at once - chunk it, index it, then zoom in selectively.
Instructions
Step 1 - Chunking
Split the recording into 30-120 second windows:
- Fixed-size chunks are fine for uniform captures
- Prefer natural boundaries (navigations, idle gaps) when known
- Assign stable IDs:
chunk-001,chunk-002, ...
Step 2 - Three Review Levels
Escalate detail only where it pays off:
- Thumbnail index (always): one frame per chunk → cheap map of where things happen
- Selected frames: pull individual frames only from relevant chunks
- Full clip replay: ONLY for ambiguous or high-value events
If pass 1 (thumbnail index) finds nothing relevant, NEVER escalate to reviewing the whole recording - report "no relevant events found" and stop.
Frame Selection Policy
When sampling frames inside a chunk:
- Static interval (no visual change): keep ONE frame for the stretch
- Scene change (cut, navigation, modal): keep three frames - just BEFORE the cut, AT the cut, and one AFTER things stabilize
- Fast motion: sample densely around that window only, sparsely elsewhere
Storyboard Concept
Assemble reviewed frames into a storyboard artifact:
- Ordered keyframes carrying chunk ID + timestamp
- One-line caption per frame describing state/action
- The storyboard doubles as a shareable summary and an index back into the raw recording
Output
{
"recording": "clips/checkout-flow.webm",
"chunks": [
{ "id": "chunk-003", "window": "60-150s", "relevant": true },
{ "id": "chunk-004", "window": "150-210s", "relevant": false }
],
"keyframes": [
{
"chunkId": "chunk-003",
"timestamp": "96.5s",
"reason": "scene-change",
"caption": "Payment modal opens after Pay click"
}
],
"conclusion": "Checkout succeeds; one transient error toast at 148s self-clears."
}
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.
- 10d ago First seen · 102 lines · 35 tokens per session scan A 745b8685611a
video-evidence-review is a skill published in the GitHub repository Akakaui/visual-browser-agent (0 stars, last pushed 16d ago), licensed MIT. It adds 35 tokens to every session and 865 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
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…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.