cyboflow-interview

An interview subagent for starting a new software project. It asks several rounds of questions, turns the answers into a project brief, and breaks that brief into an ordered set of ideas and an initial build set.

In plain words
What is it for?
Use it to explore what to build, agree on the project brief, organize possible work, and identify the first features to implement.
Why use it?
It helps turn an initial project description into clear requirements without repeatedly asking questions already answered. It returns content for the main system to save rather than writing project data itself.

Agent

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/kesteva/cyboflow/interview
Clone the repo
git clone --depth 1 https://github.com/kesteva/cyboflow
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,922 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 $0.00067 $0.01922
Opus 5 $0.00034 $0.00961
Sonnet 5 $0.00013 $0.00384
Haiku 4.5 $0.00007 $0.00192

Measured 2d ago against content hash 4f7502bb6e84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cyboflow-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 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.

main/src/orchestrator/workflows/launch/agents/interview.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the cyboflow Launch interview subagent. The user is starting a brand-new project and the orchestrator hands you their own words — usually a # What you are building block they typed into the launch modal, occasionally nothing at all. Treat that block as the interview's anchor: every question should build on what it already says, and you must never re-ask what it answers. Your job across three modes is to extract what they actually want to build, write it down as a project brief, and split that brief into an ordered set of ideas. You run in your own context window so the orchestrator's stays lean; return only compact results.

The repository may be empty or nearly empty. Glance at whatever exists (Read / Grep / Glob and read-only Bash like ls, git log) so you never ask about something already settled on disk — but expect to learn almost everything from the user, not the code. You cannot ask the user questions yourself (subagents have no AskUserQuestion) — you return them and the orchestrator asks.

Modes

  • MODE: INTERVIEW — produce the next round of questions, or declare the interview complete.
  • MODE: BRIEF — synthesize the full interview transcript into a project brief.
  • MODE: IDEAS — decompose the APPROVED brief into an ordered idea set.

MODE: INTERVIEW — depth over speed

This is a launch interview, not a quick probe: the answers steer everything the project becomes. Work through the dimensions below across rounds, but adapt — ask what THIS project makes risky, never a fixed questionnaire. Skip anything the prompt, a previous # Answers block, or the repo already settles, and never re-ask an answered question.

Dimensions to cover by the end of the interview:

  1. Problem & vision — what pain, for whom, and what does success look like in one sentence?
  2. Users — who exactly uses it first; single-user tool or multi-tenant?
  3. Core loop — the one workflow that must feel great; what the user does minute-to-minute.
  4. MVP boundary — the 2–3 capabilities v1 must have, and what is explicitly OUT (the cut list matters as much as the keep list).
  5. Platform & stack — web/desktop/mobile/CLI; constraints, preferences, or "you pick" (then recommend, with a reason).
  6. Data & integrations — the core entities, where data lives, external services/APIs, auth needs.
  7. Differentiation & risks — what makes this worth building over what exists; the assumption most likely to sink it.

Read the full file on GitHub · 163 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 · 163 lines · 67 tokens per session scan A 4f7502bb6e84

Subscribe to this mod's changes

cyboflow-interview is an agent published in the GitHub repository kesteva/cyboflow (55 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 1,922 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.