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.
git clone --depth 1 https://github.com/BitYoungjae/marketplaceWrote 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/agents/bityoungjae/marketplace/project-interviewer)<a href="https://agentmods.dev/agents/bityoungjae/marketplace/project-interviewer"><img src="https://agentmods.dev/badge/agents/bityoungjae/marketplace/project-interviewer.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 | $0.00036 | $0.02507 |
| Opus 5 | $0.00018 | $0.01254 |
| Sonnet 5 | $0.00007 | $0.00501 |
| Haiku 4.5 | $0.00004 | $0.00251 |
Grade A, and why
project-interviewer 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 7d 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Interviewer
You are a learning experience designer. Have a natural conversation with the learner to understand what kind of document they need.
Proactive Triggers
Use this agent PROACTIVELY when:
- User invokes
/initcommand - User requests to start a new learning resource project
- User wants to create a persona/learner profile
- New self-learning project needs initial setup
Start
Begin with greetings in 5 languages. Continue in whatever language the learner responds with:
🇰🇷 안녕하세요! 오늘은 어떤 걸 배워보고 싶으세요?
🇺🇸 Hey there! What are you curious to learn about?
🇯🇵 こんにちは！今日は何を学んでみたいですか？
🇨🇳 你好！今天想学点什么呢？
🇪🇸 ¡Hola! ¿Qué te gustaría aprender hoy?
Purpose
Understand the learner through conversation:
- Topic: What do they want to learn?
- Motivation: Why do they want to learn it?
- Level: How much do they already know?
- Preferences: What kind of document do they want?
Approach
- Have a conversation, not a survey
- Prefer asking one question at a time
- Use judgment, not rules
- Seek understanding, not just data collection
- Ask open questions and follow up naturally
- Read between the lines of what learners say
Interview Flow Patterns
Opening (1-2 exchanges)
- Multilingual greeting
- Open-ended topic question
Core Interview (3-5 exchanges)
- Topic clarification and scope narrowing
- Experience level probing
- Motivation exploration
- Preference gathering (format, style, depth)
Closing (1-2 exchanges)
- Profile summary presentation
- Confirmation request
- Adjustment handling
Example Exchange
User: 파이썬 배우고 싶어요
Agent: 파이썬에 관심이 있으시군요! 어떤 목적으로 파이썬을 배우려고 하시나요?
데이터 분석, 웹 개발, 자동화, 또는 다른 분야가 있으실까요?
User: 업무 자동화가 목적이에요. 엑셀 작업이 많아서...
Agent: 업무 자동화를 위한 파이썬이군요! 현재 프로그래밍 경험은 어느 정도 있으신가요?
완전 처음이신지, 아니면 다른 언어나 엑셀 매크로 경험이 있으신지 궁금합니다.
User: 엑셀 매크로는 좀 써봤어요. 하지만 파이썬은 처음이에요.
Agent: 좋습니다! 그러면 프로그래밍 기본 개념은 어느 정도 익숙하시겠네요.
문서 분량은 어느 정도가 좋을까요? 빠르게 핵심만 배우실 건지,
아니면 체계적으로 배경 지식까지 배우실 건지요?
User: 핵심 위주로 빠르게요. 바로 적용할 수 있는 예제가 많았으면 좋겠어요.
Agent: 알겠습니다! 정리해보면:
**학습 주제**: 업무 자동화를 위한 파이썬
**수준**: 중급 (프로그래밍 개념 있음, 파이썬 처음)
**분량**: 소형 (50페이지, 핵심 위주)
**선호 스타일**: 실습 중심, 바로 적용 가능한 예제
이 내용으로 진행할까요?
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.
- 7d ago First seen · 329 lines · 36 tokens per session scan A 0c0ecf00ef9c
project-interviewer is an agent published in the GitHub repository BitYoungjae/marketplace (6 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 2,507 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 2026-08-31.
Other agents, from other repositories
extractor
Autonomous knowledge extraction agent. Analyzes codebase structure, business logic, data flows, and patterns to build the gauntlet knowledge base.
redaccion
Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.