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 JayCRL/MobileVC --skill mobilevc-installergit clone --depth 1 https://github.com/JayCRL/MobileVCWrote 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/jaycrl/mobilevc/mobilevc-installer)<a href="https://agentmods.dev/skills/jaycrl/mobilevc/mobilevc-installer"><img src="https://agentmods.dev/badge/skills/jaycrl/mobilevc/mobilevc-installer/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/jaycrl/mobilevc/mobilevc-installer"><img src="https://agentmods.dev/badge/skills/jaycrl/mobilevc/mobilevc-installer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00222 | $0.01238 |
| Opus 5.5 | $0.00089 | $0.00495 |
| Sonnet 5.5 | $0.00044 | $0.00248 |
| Haiku 4.5 | $0.00022 | $0.00124 |
Grade A, and why
mobilevc-installer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mobilevc-installer
Install and run MobileVC for the user. The user's dev machine becomes the Claude Code backend; the phone runs the official client app and connects to it over LAN or through the public Relay flow.
GitHub: https://github.com/JayCRL/MobileVC npm: https://www.npmjs.com/package/@justprove/mobilevc
What you do
Run these steps in order. Stop and report to the user as soon as anything fails.
Step 1 — Preflight
Before installing, check the environment. Run these commands and confirm:
node --version # require >= 18.0.0
npm --version
If node is missing or older than 18, STOP and tell the user how to install Node.js (brew install node, nvm install 20, or https://nodejs.org). Do NOT proceed.
Step 2 — Install the npm package
Try the global install first:
npm install -g @justprove/mobilevc
If it fails with EACCES or permission errors, do NOT use sudo. Instead suggest one of:
npm config set prefix ~/.npm-global && export PATH=~/.npm-global/bin:$PATHthen re-run installnvm use <version>if the user has nvmnpm install --prefix ~/.local @justprove/mobilevcand add~/.local/binto PATH
Verify:
mobilevc --help
Step 3 — First-run setup (interactive)
Tell the user that mobilevc start will ask three questions on first run:
- Language —
zhoren - Port — default
8001. Pick something else if 8001 is busy. - Auth token — any string the user wants. The phone client will need this to connect.
If the user has not picked a token yet, suggest something memorable but non-trivial (e.g. mvc- plus 8 random chars).
Important: token input is hidden in the terminal. Tell the user to type the token normally and press Enter even though no characters are shown.
Step 4 — Start the backend
mobilevc start
This will:
- Run
mobilevc setupif no config exists yet - Spawn the prebuilt server binary in the background (logs in
~/.mobilevc/logs/) - Print a LAN QR code in the terminal that encodes
<host>:<port>+ auth token
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 · 123 lines · 222 tokens per session scan A ccfbe88fd5b3
mobilevc-installer is a skill published in the GitHub repository JayCRL/MobileVC (206 stars, last pushed 3mo ago), licensed MIT. It adds 222 tokens to every session and 1,238 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
common-store-changelog
Generate user-facing release notes for the App Store and Google Play from git history (App Store <=4000 chars, Google Play <=500). Use when generating release notes, app store changelog, play store release, or "what's new" text for a mobile app.
android-navigation-3
Install and migrate to Jetpack Navigation 3. Use when implementing Navigation 3 patterns including NavDisplay, NavKey routes, deep links, multiple backstacks, scenes (dialogs, bottom sheets), or migrating from Navigation 2.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
generate-images-with-firebase-ai
Use when generating or editing images from Flutter/Dart with Firebase AI Logic and a Gemini image model (Nano Banana), making the first call work, choosing Gemini Developer API vs Vertex AI, hitting quota, billing or App Check failures, getting empty or image-only responses, sending a user photo as input, controlling…
firebase-app-check
Use when implementing app attestation, configuring App Check providers, setting up debug tokens, enabling backend enforcement, or managing token refresh.
flutter-app-architecture
Use when scaffolding a project, refactoring into layers, creating view models/repositories, configuring dependency injection, or implementing unidirectional data flow (MVVM).