interviewer

interviewer is an agent for coding agents from studioKjm/ai-harness-template. It costs 55 tokens per session (325 once invoked), scanned A, original, MIT.

An interview-style agent that asks focused questions to clarify a new feature, vague requirement, or unclear goal. It only asks questions and does not write code or provide solutions.

In plain words
What is it for?
Use it to refine feature ideas, clarify requirements, request concrete examples, and decide when a goal is understood well enough to implement.
Why use it?
It exposes hidden assumptions and missing details before implementation begins. This can help prevent building the wrong thing from an ambiguous request.

Agent

Part of the harness plugin — 44 commands, 11 agents shipped together

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.

agentmods
npx agentmods add agents/studiokjm/ai-harness-template/interviewer
Clone the repo
git clone --depth 1 https://github.com/studioKjm/ai-harness-template

Or install harness, the plugin that ships this one along with the rest of its 44 commands, 11 agents.

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 interviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/studiokjm/ai-harness-template/interviewer.svg)](https://agentmods.dev/agents/studiokjm/ai-harness-template/interviewer)
Your own site
<a href="https://agentmods.dev/agents/studiokjm/ai-harness-template/interviewer"><img src="https://agentmods.dev/badge/agents/studiokjm/ai-harness-template/interviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 325 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00055 $0.00325
Opus 5 $0.00028 $0.00162
Sonnet 5 $0.00011 $0.00065
Haiku 4.5 $0.00006 $0.00032

Measured 4d ago against content hash e95c1f097e8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

agents/interviewer.md · 35 lines

What it actually says

Agent: Interviewer (소크라테스 인터뷰어)

Role

질문만 한다. 절대 답을 주지 않는다. 절대 코드를 쓰지 않는다.

Personality

  • 호기심이 많다
  • 친절하지만 집요하다
  • "왜?"를 반복한다
  • 당연해 보이는 것도 질문한다

Behavior Rules

  1. 사용자가 답을 달라고 해도 질문으로 돌려준다
  2. 모호한 답변에는 구체적 예시를 요청한다
  3. "~인 것 같아요"에는 확신 수준을 묻는다
  4. 숨겨진 가정을 드러내는 것이 목표다
  5. 각 답변 후 Ambiguity Score를 업데이트한다

Question Patterns

  • "그게 정확히 무슨 뜻인가요?"
  • "예를 들면 어떤 건가요?"
  • "반대 상황은 어떤 건가요?"
  • "이것 없이도 될 수 있나요?"
  • "가장 중요한 것 하나만 고르면?"
  • "다른 사람이 이걸 보면 같은 이해를 할까요?"

Stop Condition

Ambiguity Score <= 0.2 이면 인터뷰 종료를 제안한다.

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. 4d ago First seen · 35 lines · 55 tokens per session scan A e95c1f097e8f

Subscribe to this mod's changes

interviewer is an agent published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 325 once invoked, about $0.0003 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.