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 ruizrica/agent-pi --skill qa-scrollgit clone --depth 1 https://github.com/ruizrica/agent-piWrote 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/ruizrica/agent-pi/qa-scroll)<a href="https://agentmods.dev/skills/ruizrica/agent-pi/qa-scroll"><img src="https://agentmods.dev/badge/skills/ruizrica/agent-pi/qa-scroll.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.01730 |
| Opus 5 | $0.00048 | $0.00865 |
| Sonnet 5 | $0.00019 | $0.00346 |
| Haiku 4.5 | $0.00010 | $0.00173 |
Grade A, and why
qa-scroll scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(agent-device:*) Bash(agent-browser:*) Bash(xcrun:*) Bash(node:*) Bash(curl:*) Bash(npx:*) Read How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qa-scroll
QA test skill for verifying scroll-based media feeds — video autoplay, scroll navigation, mute/unmute toggle, and playback progression. Uses the dual-driver architecture (CDP + agent-device) to test media feeds in native mobile apps.
What It Tests
| Test | Method | Assertion |
|---|---|---|
| First video autoplays | CDP player state query | player.playing === true, currentTime > 0 |
| Video progress advances | CDP currentTime check after delay | currentTime increased between checks |
| Scroll to next video | CDP scroll hook or agent-device swipe | New video starts playing |
| Mute toggle | CDP player.muted = !player.muted |
Mute state flips |
| Unmute toggle | CDP player.muted = !player.muted |
Mute state flips back |
| Scroll continuity | Multiple swipes | Each new video autoplays |
| Final route check | CDP cdp_get_route |
Still on the feed screen |
Setup Guard (Automatic)
The skill includes a setup guard that runs before every test. It checks and auto-fixes:
| Check | What it does if missing |
|---|---|
| iOS Simulator booted | Boots it or auto-detects a booted one |
| Dev server running | Starts it in background, waits up to 60s |
| App in foreground | Launches via xcrun simctl launch |
| CDP target available | Polls /json endpoint for up to 30s |
| CDP connection functional | Sends eval 1+1, retries 3x |
| Navigation module ID valid | Auto-scans Metro modules with caching |
| Error overlay | Suppresses LogBox errors via CDP |
Configuration
Before running, set your app-specific values in qa.config.sh or qa.config.local.sh:
# Required
export APP_BUNDLE_ID="com.yourapp.dev"
export PROJECT_DIR="/path/to/your/project"
# Video player (for expo-video apps)
export VIDEO_PLAYER_CLASS="VideoPlayer" # Class to look for
export GLOBAL_PLAYERS_VAR="__qaVideoPlayers" # Global tracking variable
# Screen names (for CDP navigation)
export SCREEN_EXPLORE="ExploreScreen" # Your feed screen name
# Optional: if your app has a feed scroll hook
export GLOBAL_FEED_VAR="__qaFeedState" # Feed state debug hook name
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.
- 8d ago First seen · 183 lines · 97 tokens per session scan A 8c4405857140
qa-scroll is a skill published in the GitHub repository ruizrica/agent-pi (267 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,730 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
android_ui_verification
Automated end-to-end UI testing and verification on an Android Emulator using ADB.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
agent-device
Automates Apple-platform apps (iOS, tvOS, macOS), Android devices, and Amazon Vega OS TV apps in Vega Virtual Devices. Use when navigating apps, taking snapshots/screenshots where supported, driving TV remotes, tapping, typing, scrolling, extracting UI info, collecting evidence, or planning agent-device CLI commands.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
eas-simulator
EAS service (paid). Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Read before running any eas simulator: commands - it has the current syntax for this experimental API. Use whenever the user needs a simulator they can't run locally - 'run my app on a cloud simulator', 'use eas…