onboard

A structured interview command for startup founders that builds a detailed business profile through one question at a time across 14 topics.

In plain words
What is it for?
Use it to document a startup's product, customers, business situation, and other planning context in the project's .anty files.
Why use it?
It gathers the context needed for more informed strategy and actions instead of relying on brief or incomplete answers. It can resume an unfinished interview from the first missing topic.

Command

Part of the anty plugin — 24 skills, 11 commands, 4 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/voxtechnologies/anty-framework/onboard
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/anty-framework

Or install anty, the plugin that ships this one along with the rest of its 24 skills, 11 commands, 4 agents.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,533 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 $0.00011 $0.02533
Opus 5 $0.00005 $0.01267
Sonnet 5 $0.00002 $0.00507
Haiku 4.5 $0.00001 $0.00253

Measured 3d ago against content hash 2801fb662a5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboard 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • onboard — 100% identical, 0 lines differ
commands/onboard.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/anty:onboard — QUEST-Based Conversational Interview

Purpose

Conduct a structured conversational interview with the startup founder to build complete business context. Uses QUEST (Questioning to Understand, Explore, and Synthesize Thinking) methodology to extract deep, actionable intelligence across 14 topics.

Before Starting

  1. Check if .anty/business-context.yaml already exists.

    • If it exists and is complete (all 14 topics covered), inform the user: "Your business context is already complete. To re-run onboarding, delete .anty/business-context.yaml and run /anty:onboard again."
    • If it exists but is partial (some topics missing), inform the user which topics are complete and resume from the first incomplete topic: "I see you've already covered [completed topics]. Let's continue from [next topic]."
    • If it does not exist, create the .anty/ directory if needed and start fresh.
  2. Ensure .anty/config.yaml exists. Create it with defaults if not.

QUEST Methodology Rules

Follow these rules strictly for EVERY question:

  • One question at a time. Never ask multiple questions in a single message.
  • Downward then upward. Start with concrete/specific questions (downward), then move to abstract/strategic questions (upward) within each topic.
  • "Tell me..." openers. Begin questions with "Tell me about...", "Walk me through...", "Describe..." — open invitations, not yes/no gates.
  • Echo questions. After the user answers, reflect back key concepts before moving on: "So when you say [X], you mean [Y]?" This confirms understanding and makes the user feel heard.
  • Empathic neutrality. Never judge answers as good or bad. Acknowledge without evaluating: "That's clear" or "I understand" — never "Great answer!" or "That's concerning."
  • Concept identification. When the user describes something that maps to a known framework, name it: "What you're describing sounds like [framework]. Let me ask a bit more about that."
  • Resolution imbalance detection. If the founder gives extremely detailed answers on one topic but vague answers on another, note this pattern. After 3+ topics, if imbalance is detected, gently redirect: "You've given me rich detail on [topic A]. I'd like to explore [topic B] with similar depth — tell me more about..."

Read the full file on GitHub · 254 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. 3d ago First seen · 254 lines · 11 tokens per session scan A 2801fb662a5a

Subscribe to this mod's changes

onboard is a command published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 2,533 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 2026-08-31.