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 vvedantb/eva --skill ui-recording-timelinegit clone --depth 1 https://github.com/vvedantb/evaWrote 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/vvedantb/eva/ui-recording-timeline)<a href="https://agentmods.dev/skills/vvedantb/eva/ui-recording-timeline"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/ui-recording-timeline/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/vvedantb/eva/ui-recording-timeline"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/ui-recording-timeline.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 | $0.00118 | $0.02203 |
| Opus 5.5 | $0.00047 | $0.00881 |
| Sonnet 5.5 | $0.00024 | $0.00441 |
| Haiku 4.5 | $0.00012 | $0.00220 |
Grade A, and why
ui-recording-timeline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI recording timeline
Produces a self-contained folder with index.html and the video. The video fills the window. Below it are a one-line caption and a thin timeline (phase colors, paint ticks, hover thumbnails, scrubbing). Change regions flash on the video at each paint, and a paint list drawer opens with l.
Everything needed is in this skill directory:
scripts/timeline.py: one CLI with all the steps. Dependencies are declared inline, anduv runinstalls them.assets/template.html: the page.buildinjects the data into it.
Requirements: ffmpeg/ffprobe and uv on PATH. Chrome or Chromium is needed only for preview.
Below, T means uv run <this skill dir>/scripts/timeline.py. Define it as a shell function, not a variable: zsh doesn't word-split variables. Use the absolute path of the skill directory:
T(){ uv run "/abs/path/to/ui-recording-timeline/scripts/timeline.py" "$@"; }
WD is the output folder. If the user's project has conventions for where research or collateral goes, follow them; otherwise put WD next to the video as <video-stem>-timeline/.
Workflow
1. Extract and find candidate paints
T extract /path/to/recording.mp4 WD # copies video, writes meta.json (frame timestamps; VFR is fine)
T candidates WD # table of frames that differ from the previous frame
Each row has the frame index, time, % changed, kind (change / full / cursor?), and the normalized bbox. Small cursor-like changes are hidden (use --all to show them).
2. Look at the frames, then decide what counts as a paint
Never label from the table alone. Look at the frames:
T sheet WD --frames 0,4,14,26,61 --name overview # labelled contact sheets -> WD/sheets/*.jpg
T sheet WD --frames 18,19 --crop 0,0,0.25,0.15 --name zoom # zoom into a small change
Read the sheet images with the image viewer. Make sure to include the frame before each candidate, so you can see what changed.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 125 lines · 118 tokens per session scan A 33b70a5293f3
ui-recording-timeline is a skill published in the GitHub repository vvedantb/eva (101 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 2,203 once invoked, about $0.0005 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 2026-10-13.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
frontend-visual-qa
Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI…
waitlist-page
A simple waitlist page for collecting email addresses from people interested in a new product or early-access release.