Borrowing it
Nothing to install: this file belongs to vvedantb/eva. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vvedantb/eva/main/.claude/skills/eva-feature-demo/SKILL.mdgit 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/eva-feature-demo)<a href="https://agentmods.dev/skills/vvedantb/eva/eva-feature-demo"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/eva-feature-demo/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/eva-feature-demo"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/eva-feature-demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 83 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium MCP Rug Pull · line 176 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.03164 |
| Opus 5 | $0.00059 | $0.01582 |
| Sonnet 5 | $0.00024 | $0.00633 |
| Haiku 4.5 | $0.00012 | $0.00316 |
Grade A, and why
eva-feature-demo 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eva feature screencast
One unbroken recording of one feature actually working, plus a tweet. The value is that it is real: real app, real data, real latency. No cuts, no music, no marketing captions.
Output — post the zoom cut. All at the repo root, already gitignored:
| File | What it is |
|---|---|
recordings/<slug>.webm |
raw take from agent-browser |
recordings/<slug>.actions.json |
action log (when/where each click and typing burst happened) |
recordings/<slug>-zoom.mp4 |
the artefact — camera, cursor, click rings, keystroke captions |
recordings/<slug>.mp4 |
plain straight conversion; fallback if the zoom looks wrong |
The render pass is the point of this skill. A raw agent-browser capture has no mouse cursor and
no visible typing — Playwright draws no pointer, and fill puts a whole sentence on screen in one
frame. Watched flat, the demo is a series of unexplained jumps. The render pass adds back exactly the
four things the capture cannot record, and nothing else:
| Added | Because |
|---|---|
| Camera zoom | pushes in on the target just before the action, back out to full frame after |
| Synthetic cursor | a real pointer, gliding target to target, dipping on each click |
| Click ring | a click has no visual effect of its own |
| Keystroke caption | types the text out at ~20 chars/sec, so keystrokes are readable |
All four come from the same action log, so the take script is the only place you describe the flow.
The zoom is the opposite rule from eva-launch-video, which is locked at zero zoom. There the
shots are static screenshots and any zoom hides UI. Here the zoom is motivated by an action and
always returns to the full frame, so nothing is permanently hidden.
What ships with it
4 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 · 209 lines · 118 tokens per session scan A cd3869e73335
eva-feature-demo 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 3,164 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
browser-video-recording
Create polished 60 fps 4:3 4K browser screen-recording style videos from Codex in-app browser captures, with browser-only crop, natural macOS cursor styling, deliberate click choreography, zoom-follow framing, ffprobe/thumbnail verification, and optional native recording compatibility checks. Use when the user asks to…
html-to-video-pipeline
Reliable HTML-to-MP4 rendering via headless browser recording (Playwright/Puppeteer) + ffmpeg — the ordering, gotchas, and verification steps you MUST get right or the output silently rots. Trigger whenever the user is building or debugging any pipeline that turns an HTML/CSS/JS page (single-file, multi-composition…
record-video
Record and upload a short browser interaction video artifact.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.