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 aiya000/dotfiles --skill record-android-app-demogit clone --depth 1 https://github.com/aiya000/dotfilesWrote 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/aiya000/dotfiles/record-android-app-demo)<a href="https://agentmods.dev/skills/aiya000/dotfiles/record-android-app-demo"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/record-android-app-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/aiya000/dotfiles/record-android-app-demo"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/record-android-app-demo.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 | $0.00060 | $0.02192 |
| Opus 5.5 | $0.00024 | $0.00877 |
| Sonnet 5.5 | $0.00012 | $0.00438 |
| Haiku 4.5 | $0.00006 | $0.00219 |
Grade A, and why
record-android-app-demo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
record-android-app-demo
Drive the app with adb while screenrecord runs, then cut the result into an inline GIF and a
linked mp4.
The screen belongs to the user
- Never press HOME or RECENTS, and never switch apps, to arrange a nicer background. Whatever is on the device is the background of the demo, and the user may have chosen it deliberately. Ask before changing it
- Ask before
pm clear. It wipes whatever the user had stored in the app. A demo that starts from an empty state usually needs it, so ask first, and keep a screenshot of the current state - Agree on what the demo should show before recording. Re-recording is cheap; re-deciding is not
Environment
-
The device is usually on wireless adb, and the address changes between sessions.
adb devices; when it lists none, ask the user for the address from 設定 → 開発者向けオプション → ワイヤレスデバッグ -
A foldable has two displays.
adb shell cmd display get-displaysprints each one'suniqueId "local:<id>", andscreencapneeds that id:$ adb shell screencap -d 4630947123231501204 -p > shot.png # Z Fold8, inner screenThe outer screen of the same device is
4630947004648141459 -
adb shell wm sizegives the pixel size to record at, andwm densitythe dp scale (px = dp * density / 160), which is how tap coordinates are worked out from the layout -
Claude Code blocks a foreground
sleep, and a hook rejectsgrep/findanywhere in a command. So put every sleep inside theadb shellscript (it runs on the device), and filterdumpsysoutput locally withrginstead of piping it through the device'sgrep
Recording
-
Start
screenrecordas a background Bash task:$ adb shell screenrecord --size 1248x1972 --bit-rate 8M --time-limit 60 /sdcard/part1.mp4--sizeis not optional on a foldable. Without it the file comes out 2448 wide with the screen sitting in a corner of a mostly black canvas. Use whatwm sizereported- It takes 2-3 seconds before it is really capturing. Lead in with a sleep, and trim later
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.
- 1mo ago First seen · 176 lines · 60 tokens per session scan A 41da49b36fcc
record-android-app-demo is a skill published in the GitHub repository aiya000/dotfiles (21 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 2,192 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
restart__pull_request
A pull-request restart workflow for replacing a messy review with a new pull request containing one clean commit and a summary of the earlier discussion.
rescue__pull_request_review
An automated workflow for handling GitHub pull-request review comments, applying requested code changes, committing them, and pushing them back.
submit__pull_request
An automated pull-request submission workflow. A pull request is a request for a code change to be reviewed and merged; this workflow writes its explanation, creates it, watches its automated checks, and fixes failed checks.
write__pull_request
A workflow for writing a pull request description, the explanation attached to a proposed code change for review. It analyses the changes and commit history.
monitor__ci_status
An automated monitor for GitHub Actions, the service that runs checks such as tests after code changes. It watches all checks after a pull request or a push to a pull-request branch and can invoke a failure-recovery process.
monitor__pull_request_conflict
An automated check for GitHub pull requests, which are proposed code changes awaiting review or merging.