interview-me

A structured interview skill that asks the user one question at a time to uncover unstated preferences and constraints before implementation.

In plain words
What is it for?
Use it when requirements are ambiguous or the user asks to be interviewed, with questions prioritized by their effect on the solution.
Why use it?
It reduces the risk of silently guessing decisions that could change the design or architecture of the work.

Skill for Claude CodeCodex

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 skills/orenluxy/fable-method/interview-me
Any agent
npx skills add orenluxy/fable-method --skill interview-me
Clone the repo
git clone --depth 1 https://github.com/orenluxy/fable-method

Made for: Claude Code, Codex.

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 499 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 $0.00069 $0.00499
Opus 5 $0.00034 $0.00249
Sonnet 5 $0.00014 $0.00100
Haiku 4.5 $0.00007 $0.00050

Measured 2d ago against content hash c5d8f7e4a2f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interview-me 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.

skills/interview-me/SKILL.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interview Me

Purpose: convert the user's unknown knowns (implicit preferences and constraints they have but didn't state) into known knowns — cheaply, before implementation makes them expensive.

Rules

  1. One question per message. Never batch. The user's answer to question N should be allowed to change question N+1.

  2. Prioritize by architectural impact. Ask first the questions whose answers would change the structure of the solution. Cosmetic and naming questions come last or not at all. Before asking anything, internally rank your candidate questions by: "if the answer surprises me, how much of the design changes?"

  3. Every question must be paired with your current best guess. Format: state the question, then "My default if you don't care: X, because Y." This lets the user answer with one word ("default") and keeps the interview fast.

  4. Hard cap: 7 questions. If you have more than 7, your top 7 by architectural impact. If you genuinely can't get below 7, that's a signal the task should be split — say so.

  5. Stop early. The moment remaining questions are all low-impact, say "Remaining questions are cosmetic — I'll use sensible defaults and log them in IMPLEMENTATION_NOTES.md" and end the interview.

  6. Close with a contract. After the last answer, output a short summary: decisions made, defaults assumed, and the rewritten task statement. Ask for a single confirmation before implementing.

Mid-implementation use

This skill also applies DURING implementation: when you hit an unknown whose resolution would change already-written code by more than ~20 lines, pause and ask rather than guess. For smaller unknowns, take the conservative option and log it under Deviations in IMPLEMENTATION_NOTES.md (see the implementation-notes skill).

Anti-patterns

  • Twenty trivia questions is failure. Fewer, sharper questions win.
  • Asking questions whose answers are discoverable in the codebase or via search is failure. Look first, ask only what only the user knows.

Read the full file on GitHub · 32 lines

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. 2d ago First seen · 32 lines · 69 tokens per session scan A c5d8f7e4a2f5

Subscribe to this mod's changes

interview-me is a skill published in the GitHub repository orenluxy/fable-method (1 stars, last pushed 26d ago), licensed MIT. It adds 69 tokens to every session and 499 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 2026-08-31.