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 using-mobiaigit 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/using-mobiai)<a href="https://agentmods.dev/skills/arisguimera/mobiai-core/using-mobiai"><img src="https://agentmods.dev/badge/skills/arisguimera/mobiai-core/using-mobiai/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/using-mobiai"><img src="https://agentmods.dev/badge/skills/arisguimera/mobiai-core/using-mobiai.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 | $0.00043 | $0.02976 |
| Opus 5 | $0.00022 | $0.01488 |
| Sonnet 5 | $0.00009 | $0.00595 |
| Haiku 4.5 | $0.00004 | $0.00298 |
Grade A, and why
using-mobiai 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 2d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
This is not negotiable. This is not optional. You cannot rationalize your way out of this.
Instruction Priority
MobiAI skills override default system-prompt behavior, but user instructions always take precedence:
- User's explicit instructions (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority
- MobiAI skills — override default behavior where they conflict
- Default system prompt — lowest priority
If a CLAUDE.md or user message conflicts with a skill's workflow, follow the user. The user is in control.
How to Access Skills
In Claude Code: Call the Skill tool with the skill name (e.g. Skill(mobiai-fix-issue)). The SKILL.md body is returned as the tool result — follow it directly. Never use the Read tool on SKILL.md files — that bypasses invocation and is not activation.
In Copilot CLI: Call the skill tool. Skills are auto-discovered from installed plugins.
In Gemini CLI: Call activate_skill with the skill name.
In Codex: Skills are discovered natively from the symlinked skills directory. See .codex/INSTALL.md.
In other environments: Check your platform's documentation for how skills are invoked.
Quick Decision Guide
Match the user's intent against the rows below. If any row matches even at 1% confidence — invoke that skill FIRST, before any other tool call.
| User intent | Skill to invoke |
|---|---|
| User reports a bug / shares a ticket (Jira, Linear, GitHub issues) | mobiai-fix-issue |
| User shares a commit SHA + says the fix didn't work, or asks whether a commit resolves a bug | mobiai-mobile-debugging (or mobiai-fix-issue if the ticket is still open) |
| User shares a crash, stack trace, or error | mobiai-analyze-crash |
| User mentions Firebase Crashlytics specifically | mobiai-crashlytics |
| User wants to reproduce a bug on device/emulator/simulator | mobiai-reproduce-bug |
| User asks to write or add tests | mobiai-write-tests |
| User asks for a code review | mobiai-review-code |
| User wants to commit, push, or open a PR (says "mergear", "push", "subir", "dale PR", "shipeá", "commit", "merge") | mobiai-create-pr |
| Interact with Android device/emulator (adb, screenshots, logcat) | mobiai-android-device |
| Build an Android project (Gradle, flavors, variants) | mobiai-android-build |
| Interact with iOS Simulator (simctl) | mobiai-ios-device |
| Build an iOS project (xcodebuild, schemes) | mobiai-ios-build |
| Working on a Kotlin Multiplatform project | mobiai-kmp |
| Working on a Flutter project | mobiai-flutter |
| Working on a React Native project | mobiai-react-native |
| Need to understand Android project structure | mobiai-android-architecture |
| Need to understand iOS project structure | mobiai-ios-architecture |
| Writing Android tests specifically | mobiai-android-testing |
| Writing iOS tests specifically | mobiai-ios-testing |
| Design a new feature with unclear intent or requirements (user still exploring what to build) | mobiai-mobile-brainstorming |
| Bug or unexpected behavior, need root cause | mobiai-mobile-debugging |
| Implementing a feature/fix with tests first | mobiai-mobile-tdd |
| User gives a defined task list (3+ items) or a multi-step spec — intent clear, "how" missing | mobiai-mobile-planning |
| About to claim work is done | mobiai-mobile-verification |
| Have a written plan to execute step by step | mobiai-mobile-executing-plans |
| 2+ independent tasks to parallelize (says "en paralelo", "orquestador", "agentes al mismo tiempo", "waves", "al mismo tiempo") | mobiai-mobile-parallel-agents |
| Executing a plan via subagents (says "ejecutá el plan", "implementalo", "arrancá con esto", "hacelo con agentes") | mobiai-mobile-executing-plans-with-subagents |
| Starting feature work in isolation | mobiai-mobile-worktrees |
| Implementation done, need to integrate | mobiai-mobile-finishing-branch |
| Creating a new MobiAI skill | mobiai-writing-skills |
| User asks about code impact, call graph, callers/callees, "where is X used", semantic exploration of the codebase | mobiai-graph |
| User asks about project decisions, bugfixes, workarounds, or "what did we decide last time" | mobiai-brain |
| SessionStart banner avisa que hay un MobiAI update disponible, o el usuario pide actualizar MobiAI | mobiai-update |
What ships with it
3 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.
- 2d ago Changed · +182 lines · +36 tokens per session 4c65b7b57e7f
- 10d ago First seen · 6 lines · 7 tokens per session scan A 83cc9f9cae4a
using-mobiai is a skill published in the GitHub repository ArisGuimera/MobiAI-Core (450 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 2,976 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…