Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add OXI-717/ai-native-toolkit/plugin install screencastWrote 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/oxi-717/ai-native-toolkit/screencast)<a href="https://agentmods.dev/skills/oxi-717/ai-native-toolkit/screencast"><img src="https://agentmods.dev/badge/skills/oxi-717/ai-native-toolkit/screencast.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 | $0.00133 | $0.00845 |
| Opus 5 | $0.00067 | $0.00423 |
| Sonnet 5 | $0.00027 | $0.00169 |
| Haiku 4.5 | $0.00013 | $0.00085 |
Grade A, and why
screencast 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 6d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
screencast
Record a browser e2e flow into a polished demo mp4. Engine lives in ${CLAUDE_PLUGIN_ROOT:-.}/engine; scenarios and videos are written into the current project under ./screencast/.
Workflow
1. Doctor / install guard (idempotent)
ENGINE="${CLAUDE_PLUGIN_ROOT:-.}/engine"
command -v ffmpeg >/dev/null || { echo "ffmpeg required: brew install ffmpeg"; exit 1; }
[ -d "$ENGINE/node_modules" ] || (cd "$ENGINE" && npm install)
ls ~/.cache/ms-playwright/chromium-* >/dev/null 2>&1 || (cd "$ENGINE" && npx playwright install chromium)
ffmpeg is reported, never auto-installed. Re-running is safe.
2. Recon (default)
Drive the target flow live via Playwright MCP: browser_navigate → browser_snapshot → browser_click. Capture:
- exact selectors (prefer role+name; fall back to CSS),
- navigation behaviour per click: same-tab vs popup/new-tab (
followPopup/switchToNewTab), - iframes (
switchToFrame), file inputs (uploadFile), - a stable interactive selector to
waitForafter eachgoto(hydration), - whether the page has a
position:fixed/stickytop header — if so setchrome: false, - whether any URL or field carries a secret (keep it out of captions; visible env values need
mask: true).
If MCP is unavailable or the app isn't running, author the scenario from the user's described steps and note the lower confidence. Do not use AskUserQuestion/TaskCreate/Team APIs in scripts.
3. Generate scenario
Write ./screencast/<name>-<YYYY-MM-DD>/scenario.yaml (see ${CLAUDE_PLUGIN_ROOT:-.}/engine/examples/checkout.yaml and scenario.schema.json). Use env: for creds (referenced as $VAR), dnsOverride only if DNS is flaky, idempotent: false on side-effecting clicks, chrome: false for fixed-header sites.
4. Render
bash "$ENGINE/make-video.sh" ./screencast/<name>-<date>/scenario.yaml
# add --allow-js only if the scenario has reviewed js: steps; --keep to retain webm/frames
5. Verify
MP4=./screencast/<name>-<date>/out/<name>.mp4
ffprobe -v error -show_entries format=duration -of csv=p=0 "$MP4"
ffmpeg -y -loglevel error -ss <t> -i "$MP4" -frames:v 1 -update 1 /tmp/sc_frame.png
Read the frame, confirm the flow + captions + address-bar transitions look right; iterate on the scenario and re-render.
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.
- 6d ago First seen · 53 lines · 133 tokens per session scan A d242a57f76a0
screencast is a skill published in the GitHub repository OXI-717/ai-native-toolkit (7 stars, last pushed 13d ago), licensed MIT. It adds 133 tokens to every session and 845 once invoked, about $0.0007 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
v8-jit
V8 JIT optimization patterns for writing high-performance JavaScript in Next.js server internals. Use when writing or reviewing hot-path code in app-render, stream-utils, routing, caching, or any per-request code path. Covers hidden classes / shapes, monomorphic call sites, inline caches, megamorphic deopt, closure…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.