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 agentmods add skills/craftos-dev/craftbot/user-profile-interviewnpx skills add CraftOS-dev/CraftBot --skill user-profile-interviewgit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote 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/craftos-dev/craftbot/user-profile-interview)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/user-profile-interview"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/user-profile-interview.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.01881 |
| Opus 5 | $0.00008 | $0.00941 |
| Sonnet 5 | $0.00003 | $0.00376 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade A, and why
user-profile-interview 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Profile Interview
Conduct a friendly, natural conversational interview to understand the user's work, life goals, and how CraftBot can help them.
Context
The user has already provided the following during setup (hard onboarding):
- Name, location, timezone
- Language preference
- Communication tone (casual/formal/friendly/professional)
- Proactivity level (low/medium/high)
- Approval settings
- Preferred notification platform
These are saved in agent_file_system/USER.md. Do NOT re-ask these questions.
Objective
Extract and document:
- Job/role and typical workday
- Life goals and aspirations
- Personality observations
- How CraftBot can specifically help them
Critical Rules
- NEVER use scripted or static phrases. Every question must feel natural, unique, and conversational. Do NOT copy example phrases verbatim — they are only there to show the spirit of what to ask.
- Adapt your tone to match the user's communication style and energy level.
- Read the room — if the user gives short answers, keep your questions short too. Don't push.
- The entire interview should be 3-4 exchanges maximum, not a long interrogation.
Interview Flow
Phase 1: Greeting + Job/Role
First, read agent_file_system/USER.md to get the user's name and existing info.
Greet them warmly by name in your own words. Then ask about their career/role/typical day in one question.
Examples of the SPIRIT (rephrase, never copy):
- "Tell me about your work, what's your role and what does a normal day look like?"
- "I'd love to hear about what you do, walk me through your role and a typical day?"
Collect:
- Job/Role: Their profession, responsibilities, daily workflow
Acknowledge their answer warmly before moving on.
Phase 2: Life Goals Exploration (adaptive)
Ask about their life goals and aspirations in your own words. Be natural, not scripted. DO NOT overwhelm the user with too many questions in one message.
Ask for life goal:
- "What are your biggest life goals or aspirations right now, both professional and personal?"
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 First seen · 189 lines · 16 tokens per session scan A 8faa225bc9a9
user-profile-interview is a skill published in the GitHub repository CraftOS-dev/CraftBot (380 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 1,881 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 2026-09-03.
Other skills, from other repositories
turix-mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.
browser-control
Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…
macos-control
Control macOS GUI applications via mouse automation, keyboard input, screenshots, image recognition, and AppleScript execution. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, scroll, drag, or locate images on screen.
open-record-replay
Record a user-demonstrated macOS workflow with the Open Record/Replay CLI, inspect the captured event stream, prepare a skill evidence package, and hand it to the host agent's native skill creator. Use when the user asks the agent to watch them perform a task, record a workflow, or create/refine a reusable Computer…
artifact-storage-policy
管理 Codex 交付物的專案識別、Google Drive／GitHub 路由、檔名、儲存位置與回讀驗證；凡工作報告、外部保存、交付成果或新 repository 選擇涉及遠端儲存時使用。.
model-worker-routing
Route a task to the existing Ox Alpha worker only when the user explicitly names Ox Alpha; preserve normal Codex behavior for all other tasks.