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 ArisGuimera/MobiAI-Core --skill mobiai-reproduce-buggit clone --depth 1 https://github.com/ArisGuimera/MobiAI-CoreWrote 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/arisguimera/mobiai-core/mobiai-reproduce-bug)<a href="https://agentmods.dev/skills/arisguimera/mobiai-core/mobiai-reproduce-bug"><img src="https://agentmods.dev/badge/skills/arisguimera/mobiai-core/mobiai-reproduce-bug/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/arisguimera/mobiai-core/mobiai-reproduce-bug"><img src="https://agentmods.dev/badge/skills/arisguimera/mobiai-core/mobiai-reproduce-bug.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 | $0.00029 | $0.01048 |
| Opus 5 | $0.00015 | $0.00524 |
| Sonnet 5 | $0.00006 | $0.00210 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
mobiai-reproduce-bug 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 13d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reproduce Bug
Interact with a running mobile app on a device/emulator/simulator to reproduce a reported bug.
When to Use
- Before fixing a bug, to confirm it exists and capture evidence
- To verify a fix by re-running the reproduction steps
- When a user says "try to reproduce this on the emulator"
Two Modes
Reproduce Mode
Explore the app to find and trigger the bug. You have freedom to navigate, try different paths, and investigate.
Verify Mode
After a fix is applied, re-run the exact same steps from the original reproduction. Only check if the original bug still occurs — don't explore other features or treat unrelated behavior as bugs.
Workflow
Step 1: Detect Platform
Check which platform the project targets and load the appropriate device skill:
- Android → load
mobiai-android-deviceskill - iOS → load
mobiai-ios-deviceskill - Flutter → load
mobiai-android-deviceormobiai-ios-devicedepending on the target platform - React Native → load
mobiai-android-deviceormobiai-ios-devicedepending on the target platform
Step 2: Plan Reproduction Steps
Before interacting with the device:
- Read the bug report — extract explicit reproduction steps if provided
- Explore source code to understand the app's navigation:
- Find the relevant screen/feature in the source code
- Read layout files, string resources, or Compose/SwiftUI views
- Understand what setup or data the feature needs
- Generate a step-by-step plan with element-based targeting:
- Prefer targeting by text label, resource ID, or accessibility label
- Use coordinates only as a fallback for swipe gestures
Step 3: Execute on Device
Follow these mandatory rules:
- Dump UI before every action. Always inspect the screen state before interacting.
- One action at a time. Every tap/swipe must be followed by a UI dump to see the result.
- Never guess coordinates. Always read them from the UI hierarchy dump.
- Check logs after every action. Transient dialogs and errors may not appear in UI dumps but will be in the device logs.
- Handle unexpected screens. Dismiss dialogs, handle permission requests, deal with loading states.
What ships with it
1 file 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.
- 13d ago First seen · 108 lines · 29 tokens per session scan A 714dd936fa7c
mobiai-reproduce-bug is a skill published in the GitHub repository ArisGuimera/MobiAI-Core (453 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 1,048 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ios-fix
Autonomous iOS bug fixer. (gstack).
google-mobile-ads-validate
Validates a project's Google Mobile Ads (GMA) SDK integration for iOS, Android, or Unity projects. Use when conducting a full pre-launch audit of an app that integrates GMA SDK or when validating any individual GMA SDK integration checks, such as when validating ad unit IDs and ad formats, SKAdNetwork IDs, mediation…
competition-ios-runtime
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for IPA runtime analysis, Frida hooks, Objective-C or Swift method tracing, Keychain inspection, SSL pinning bypass, URL scheme handling, and iOS request-signing recovery. Use when the user asks to hook an IPA, trace Objective-C or Swift…
swiftui-performance-audit
SwiftUI performance: render, scroll, CPU/memory, updates, layout, Instruments.
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
node-connect
Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale…