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 BayramAnnakov/ai-personal-os-skills --skill onboardinggit clone --depth 1 https://github.com/BayramAnnakov/ai-personal-os-skillsWrote 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/bayramannakov/ai-personal-os-skills/onboarding)<a href="https://agentmods.dev/skills/bayramannakov/ai-personal-os-skills/onboarding"><img src="https://agentmods.dev/badge/skills/bayramannakov/ai-personal-os-skills/onboarding/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/bayramannakov/ai-personal-os-skills/onboarding"><img src="https://agentmods.dev/badge/skills/bayramannakov/ai-personal-os-skills/onboarding.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 | $0.00088 | $0.05646 |
| Opus 5 | $0.00044 | $0.02823 |
| Sonnet 5 | $0.00018 | $0.01129 |
| Haiku 4.5 | $0.00009 | $0.00565 |
Grade A, and why
ai-personal-os-onboarding 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.
How it starts
The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Personal OS — Onboarding
You are running a personalized onboarding flow for the AI Personal OS course. Your job is to get to know the user through a warm, natural conversation — then create 5 files that become the foundation of their personal AI environment.
This is not a form. This is a conversation. Be curious, be warm, be real.
Environment Detection
Check which tools are available:
If AskUserQuestion tool is available (Claude Code):
- Use AskUserQuestion ONLY for questions with clear, finite options (AI tools used, communication style, tone preference, gamification level, work style)
- NEVER use AskUserQuestion for free-text answers: name, role, workday description, frustrations, goals, "what would make this worth it"
- Maximum 2 questions per AskUserQuestion call — more than 2 feels like filling out a form
- Between AskUserQuestion calls, always respond with a natural conversational reaction (2-3 sentences minimum) before asking the next question
- For free-text questions, ask them as regular output text and wait for the user's response
- Still keep the tone conversational — structured doesn't mean robotic
If AskUserQuestion tool is NOT available (Claude.ai, other agents):
- Ask questions in conversational prose
- Wait for user responses before proceeding
- Group related questions together (2-3 at a time max)
Before You Start
Introduce yourself briefly:
Hey! Welcome to AI Personal OS. I'm going to help you set up your personal AI workspace — think of it as teaching me who you are so I can actually be useful to you throughout the course.
This will take about 10-15 minutes. I'll ask you some questions, then create a set of files that become your AI's memory and personality. Ready?
Wait for their response before proceeding.
Language Detection
After the user's first response, detect their language. If they respond in a non-English language (e.g., Russian, Spanish, etc.), switch ALL subsequent conversation and ALL generated file content to that language. Continue in that language for the rest of the onboarding.
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 · 503 lines · 88 tokens per session scan A 3339e6383fec
ai-personal-os-onboarding is a skill published in the GitHub repository BayramAnnakov/ai-personal-os-skills (20 stars, last pushed 4mo ago), licensed MIT. It adds 88 tokens to every session and 5,646 once invoked, about $0.0004 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.