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 cenconq25/claude-code-app-studio --skill soak-testgit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/cenconq25/claude-code-app-studio/soak-test)<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/soak-test"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/soak-test/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/cenconq25/claude-code-app-studio/soak-test"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/soak-test.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 | $0.00048 | $0.01872 |
| Opus 5 | $0.00024 | $0.00936 |
| Sonnet 5 | $0.00010 | $0.00374 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
soak-test 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Soak Test
Most mobile bugs are not visible in a 5-minute test. This skill produces a written protocol that a human runs over hours (or overnight) to surface slow-burn issues: leaks, watchdog kills, queue overflow, network recovery, push-during-background, and battery cost.
This skill writes a protocol document. It does not execute the soak.
Phase 1: Inputs
Parse arguments:
--duration=Nh— total session length. Default 4 hours; release-gate recommends 8 hours overnight on a charger.--scenario=<name>— pick from a known list:idle,core-loop,background-mix,network-flap,push-storm,low-memory-device. Default: a balanced mix.
If no scenario is provided, propose options via AskUserQuestion.
Read the current milestone and recent bug history to choose the device matrix:
production/milestones/— current target platforms.production/qa/bugs/— recent S1/S2 bugs grouped by symptom (crashes, ANRs, freezes, memory).
Phase 2: Pick the Devices
Read .claude/docs/technical-preferences.md for Target Platforms. Propose
a soak device set:
- 1 Tier A device per platform (representative high-end).
- 1 Tier C device per platform (representative low-end / low-RAM).
- 1 device known to have reproduced a recent S1/S2.
A single soak run should cover at least one iPhone, one Android, and one constrained device. Confirm with the user.
Phase 3: Choose Observability Tools
The protocol references these tools by platform:
- iOS: Instruments (Allocations, Leaks, Time Profiler), Console.app for logs, MetricKit reports, Xcode Memory Graph.
- Android: Android Profiler (Memory, CPU, Network, Energy), Logcat,
StrictMode, ANR traces under
/data/anr/, perfetto. - Cross-platform telemetry: Sentry, Firebase Crashlytics, Datadog RUM, custom analytics.
- Battery: iOS Settings -> Battery; Android adb
dumpsys batterystats.
Ask which tools are wired into the build. A soak with no telemetry is a blind soak — propose adding telemetry first.
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 · 238 lines · 48 tokens per session scan A 92dde8afbc83
soak-test is a skill published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 1,872 once invoked, about $0.0002 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 2026-09-03.
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.
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.
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…