interview

interview is a command for coding agents from gmickel/flow-next. It costs 16 tokens per session (1,033 once invoked), scanned A, original, MIT.

A command that asks detailed questions to refine a specification, task, or specification file, covering technical or business concerns.

In plain words
What is it for?
Use it to clarify architecture, data models, APIs, edge cases, scope, motivation, and measurable outcomes.
Why use it?
It exposes missing decisions, constraints, and acceptance criteria before implementation.

Command

Part of the flow-next plugin — 33 skills, 30 commands, 25 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 commands/gmickel/flow-next/interview
Clone the repo
git clone --depth 1 https://github.com/gmickel/flow-next

Or install flow-next, the plugin that ships this one along with the rest of its 33 skills, 30 commands, 25 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 interview

README.md
[![agentmods](https://agentmods.dev/badge/commands/gmickel/flow-next/interview.svg)](https://agentmods.dev/commands/gmickel/flow-next/interview)
Your own site
<a href="https://agentmods.dev/commands/gmickel/flow-next/interview"><img src="https://agentmods.dev/badge/commands/gmickel/flow-next/interview.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,033 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 $0.00016 $0.01033
Opus 5 $0.00008 $0.00517
Sonnet 5 $0.00003 $0.00207
Haiku 4.5 $0.00002 $0.00103

Measured yesterday against content hash da75e9d9640c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

plugins/flow-next/commands/interview.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPORTANT: This command MUST invoke the skill flow-next-interview

The ONLY purpose of this command is to call the flow-next-interview skill. You MUST use that skill now.

User input: $ARGUMENTS

Pass the user input to the skill. The skill handles the interview logic.

Optional flags

Scope (added in 1.1.0)

  • --scope=technical (default) — runs the technical pass only. Writes tech-owned sections (Architecture & Data Models, API Contracts, Edge Cases & Constraints, verifiable acceptance criteria). Preserves any populated business sections byte-for-byte. Reads business sections when present and cites them in the opener; silent when absent. This IS the 1.0.2 single-pass behavior — preserving as default means zero breaking change for solo devs.
  • --scope=business — runs the business pass only. Writes biz-owned sections (Goal & Context, Boundaries, ### Motivation under ## Decision Context, outcome acceptance criteria). Preserves technical-section bodies byte-for-byte; writes placeholder *Pending technical-scope interview pass.* ONLY under empty tech sections. BEFORE drafting biz questions, runs a project-docs investigation (README.md, CHANGELOG.md, STRATEGY.md, GLOSSARY.md, knowledge/decisions/, .flow/specs/ index, docs/); items resolved by docs land in ## Resolved via Project Docs and the user is NOT asked about things the project docs already define.
  • --scope=both — runs the business pass first, then the technical pass in the same skill invocation. Same merge contract applies in each phase; auxiliary sections preserved across both.
  • --biz — short alias for --scope=business.
  • --tech — short alias for --scope=technical.

Conflicting flags (--biz --tech, --scope=business --tech, --scope=foo) error cleanly with an explicit "conflicting scope flags" or "invalid --scope value" message. R-IDs in ## Acceptance Criteria are append-only across scope passes — never renumbered, never replaced.

Doc-aware (existing)

Read the full file on GitHub · 44 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. yesterday First seen · 44 lines · 16 tokens per session scan A da75e9d9640c

Subscribe to this mod's changes

interview is a command published in the GitHub repository gmickel/flow-next (690 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 1,033 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.