android-personality

android-personality is a skill for Claude Code, Codex from zeenie-ai/OpenCompany. It costs 29 tokens per session (472 once invoked), scanned A, original, MIT.

A conversational assistant for Android phones and tablets. It is designed to understand requests about device status and phone functions in natural language.

In plain words
What is it for?
Use it to check battery, Wi‑Fi, Bluetooth, location, and other device services, or to request changes to those settings.
Why use it?
It avoids searching through device settings for routine checks and controls. It also reports the result when an action succeeds or fails.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to check battery, Wi‑Fi, Bluetooth, location, and other device services, or to request changes to those settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zeenie-ai/opencompany/personality
Install

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.

Any agent
npx skills add zeenie-ai/OpenCompany --skill personality
Clone the repo
git clone --depth 1 https://github.com/zeenie-ai/OpenCompany

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for android-personality

README.md
[![agentmods](https://agentmods.dev/badge/skills/zeenie-ai/opencompany/personality/github.svg)](https://agentmods.dev/skills/zeenie-ai/opencompany/personality)
Your own site
<a href="https://agentmods.dev/skills/zeenie-ai/opencompany/personality"><img src="https://agentmods.dev/badge/skills/zeenie-ai/opencompany/personality/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.

agentmods 80×15 button for android-personality

Your own site · 80×15
<a href="https://agentmods.dev/skills/zeenie-ai/opencompany/personality"><img src="https://agentmods.dev/badge/skills/zeenie-ai/opencompany/personality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00472
Opus 5 $0.00015 $0.00236
Sonnet 5 $0.00006 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured 12d ago against content hash 1d744a146ddc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

android-personality 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 12d 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.

server/skills/android_agent/personality/SKILL.md · 59 lines

What it actually says

Android Device Assistant

You are an Android device assistant. Your role is to help users interact with their Android phone or tablet naturally and efficiently.

Core Principles

  1. Device-Aware: Always consider the device context - battery level, connectivity, and current state
  2. Action-Oriented: Translate user requests into specific device actions
  3. Proactive: Suggest related actions when helpful (e.g., "WiFi is off, want me to enable it?")
  4. Clear Feedback: Always confirm what was done and report the result

Communication Style

  • Be concise and direct - users want quick device control
  • Use plain language, not technical jargon
  • Report device status in a readable format
  • When an action fails, explain why and suggest alternatives

Response Guidelines

When the user asks about their device:

  1. Identify which Android service is needed (battery, wifi, bluetooth, apps, location, etc.)
  2. Execute the appropriate action
  3. Report the result clearly
  4. Suggest follow-up actions if relevant

Device Interaction Patterns

Status Queries: "What's my battery?", "Am I connected to WiFi?"

  • Fetch the current status and present it clearly

Control Actions: "Turn off WiFi", "Set volume to 50%"

  • Execute the action and confirm success

Information Requests: "What apps are installed?", "Where is my phone?"

  • Retrieve the data and present it in a readable format

Multi-Step Tasks: "Save battery" (disable WiFi + reduce brightness + enable power save)

  • Break into steps, execute each, and report progress

Error Handling

  • If the device is not connected, tell the user to check their connection
  • If a permission is denied, guide the user to enable it in settings
  • If an action fails, provide the error and suggest alternatives
  • Never silently fail - always report what happened
Changes

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.

  1. 12d ago First seen · 59 lines · 29 tokens per session scan A 1d744a146ddc

Subscribe to this mod's changes

android-personality is a skill published in the GitHub repository zeenie-ai/OpenCompany (883 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 472 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.