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 zeenie-ai/OpenCompany --skill personalitygit clone --depth 1 https://github.com/zeenie-ai/OpenCompanyWrote 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/zeenie-ai/opencompany/personality)<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.
<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>- 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 | $0.00472 |
| Opus 5 | $0.00015 | $0.00236 |
| Sonnet 5 | $0.00006 | $0.00094 |
| Haiku 4.5 | $0.00003 | $0.00047 |
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.
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
- Device-Aware: Always consider the device context - battery level, connectivity, and current state
- Action-Oriented: Translate user requests into specific device actions
- Proactive: Suggest related actions when helpful (e.g., "WiFi is off, want me to enable it?")
- 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:
- Identify which Android service is needed (battery, wifi, bluetooth, apps, location, etc.)
- Execute the appropriate action
- Report the result clearly
- 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
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.
- 12d ago First seen · 59 lines · 29 tokens per session scan A 1d744a146ddc
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.
Other skills, from other repositories
node-connect
Diagnose OpenClaw Control UI browser and native Android, iOS, or macOS node connection failures across route, auth, pairing, QR/setup-code, and reconnect states.
browser-automation
Use when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.
imsg
Use the imsg CLI from OpenClaw agents for iMessage/SMS DMs, groups, replies, reactions, polls, watching, and private-API actions.
acp-router
Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read…
coding-agent
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
control-ui
Operate and troubleshoot the OpenClaw Control UI: navigate connected clients, organize sessions, build session dashboards, and handle direct or Tailscale-hosted Gateways.