interview

interview is a command for Claude Code from smrafiz/claude-supercharger. It costs 0 tokens per session (367 once invoked), scanned A, original, MIT.

A requirements-interview command that asks questions before planning or writing code.

In plain words
What is it for?
Used to gather requirements through at least three and at most seven questions, then produce a requirements summary and continue with design or planning.
Why use it?
It prevents implementation from starting before the problem, users, success criteria, constraints, and scope are clear.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: names the AskUserQuestion tool.

Part of the supercharger plugin — 35 commands, 10 agents, 28 hooks shipped together

Good fit Used to gather requirements through at least three and at most seven…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/smrafiz/claude-supercharger/interview
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.

Clone the repo
git clone --depth 1 https://github.com/smrafiz/claude-supercharger

Made for: Claude Code.

Or install supercharger, the plugin that ships this one along with the rest of its 35 commands, 10 agents, 28 hooks.

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 interview

README.md
[![agentmods](https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/interview.svg)](https://agentmods.dev/commands/smrafiz/claude-supercharger/interview)
Your own site
<a href="https://agentmods.dev/commands/smrafiz/claude-supercharger/interview"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/interview.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00367
Opus 5 $0.00000 $0.00183
Sonnet 5 $0.00000 $0.00073
Haiku 4.5 $0.00000 $0.00037

Measured 6d ago against content hash 1a9aa54485a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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.

commands/interview.md · 47 lines

What it actually says

Gather requirements before planning: $ARGUMENTS

Do NOT write any code or create an implementation plan. This is a requirements gate.

Use the AskUserQuestion tool for EVERY question. Never ask questions as plain prose.

Rules:

  • One question at a time — wait for the answer before asking the next
  • Every question MUST include a recommended option, marked (recommended)
  • Ask until you have enough to write a clear requirements summary
  • Minimum 3 questions, maximum 7 — stop when scope is clear

Question sequence:

  1. What problem is being solved? (not what to build — what pain or gap)
  2. Who uses this and what do they need? (user, system, or both)
  3. What does success look like? (observable outcome, not implementation detail)
  4. What are the hard constraints? (must-nots, non-negotiables, existing systems to respect)
  5. What's out of scope? (what you explicitly will NOT do in this iteration) 6-7. Ask follow-up questions only if critical ambiguity remains.

On completion:

Output a requirements summary, then invoke the superpowers:brainstorming skill (or superpowers:writing-plans if the design is already clear).

Output format:

REQUIREMENTS SUMMARY

Problem: [one sentence — the actual pain or gap]

Users: [who and what they need]

Success criteria:
  - [observable outcome 1]
  - [observable outcome 2]

Constraints:
  - [hard constraint 1]
  - [hard constraint 2]

Out of scope:
  - [explicit exclusion 1]

Open questions: [any remaining ambiguity, or "none"]
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. 6d ago First seen · 47 lines · 0 tokens per session scan A 1a9aa54485a5

Subscribe to this mod's changes

interview is a command published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 367 tokens. 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.