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-test-flowsgit 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-test-flows)<a href="https://agentmods.dev/skills/ruizrica/agent-pi/qa-test-flows"><img src="https://agentmods.dev/badge/skills/ruizrica/agent-pi/qa-test-flows/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/ruizrica/agent-pi/qa-test-flows"><img src="https://agentmods.dev/badge/skills/ruizrica/agent-pi/qa-test-flows.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 | $0.00105 | $0.01572 |
| Opus 5 | $0.00053 | $0.00786 |
| Sonnet 5 | $0.00021 | $0.00314 |
| Haiku 4.5 | $0.00011 | $0.00157 |
Grade A, and why
qa-test-flows 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 9d 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.
| CDP timeout | Check dev server is running: `curl $DEV_SERVER_HEALTH` | How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qa-test-flows
Automated UI test flow framework using a dual-driver architecture: CDP for navigation/state control and agent-device for screenshots/visual assertions in native apps, plus agent-browser for web app testing. This is a zero-framework approach — bash scripts orchestrate the entire test lifecycle with no Detox, Maestro, or Appium dependencies.
Key Innovation: CDP + agent-device + agent-browser
Native mobile apps with complex gesture handlers (full-screen video players, swipe-based feeds) often make coordinate-based tapping unreliable. We solve this by connecting directly to the React Native Hermes runtime via Metro's CDP WebSocket, giving us:
- Direct navigation control via
navigationRef.current.navigate()— no touch coordinates needed - Runtime state inspection — check current route, user state, storage
- Module access via Metro's
__r()require — load any app module at runtime - Screenshots & visual verification via agent-device (best-in-class for simulators)
- Web app testing via agent-browser when the same app has a web version
When to Use
- Smoke testing before submission or release builds
- Regression testing after navigation or feature changes
- Flow verification (auth, navigation, data entry, checkout)
- Platform parity checks (iOS vs Android)
- Pre-PR validation of multi-screen flows
- State persistence verification
Test Architecture
Dual Driver System
| Driver | Purpose | Use For |
|---|---|---|
| CDP (WebSocket) | Navigation, state queries, JS execution | React Native apps (Hermes runtime) |
| agent-device | Screenshots, coordinate taps, swipes, accessibility | Native app simulators/emulators |
| agent-browser | Full browser automation, DOM interaction | Web apps, PWAs, browser testing |
Test Flow Format
All test flows follow a consistent bash template:
#!/bin/bash
source "$(dirname "$0")/../../lib/test-helpers.sh"
source "$(dirname "$0")/../../lib/cdp-helpers.sh"
TEST_NAME="my-flow"
setup_test "$TEST_NAME"
# Step 1: Navigate
step "Navigate to target screen"
cdp_navigate "TargetScreen"
sleep 2
take_screenshot "01-target-screen"
assert_screenshot "01-target-screen"
# Step 2: Interact
step "Perform action"
tap 200 400
sleep 1
take_screenshot "02-after-action"
# Step 3: Verify
step "Verify result"
route=$(cdp_get_route)
log_info "Route: $route"
teardown_test
What ships with it
5 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.
- 9d ago First seen · 178 lines · 105 tokens per session scan A 414157c1e36e
qa-test-flows is a skill published in the GitHub repository ruizrica/agent-pi (266 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,572 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-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
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.
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.
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…
flutter-add-integration-test
Configures Flutter Driver for app interaction and converts MCP actions into permanent integration tests. Use when adding integration testing to a project, exploring UI components via MCP, or automating user flows with the integrationtest package.