goviralbro: Command for Claude Code

.claude/commands/viral-onboard.md

viral-onboard is a command for Claude Code from charlesdove977/goviralbro. It costs 0 tokens per session (2,991 once invoked), scanned A, original, MIT.

A guided conversation that fills an agent's central memory with information about its user, brand, audience, content topics, platforms, and business goals. It checks whether that memory has already been set up.

In plain words
What is it for?
Use it to configure an agent for content and marketing work by recording identity, niche, content pillars, publishing platforms, target customers, and monetization plans.
Why use it?
It avoids repeatedly explaining the same background to every agent module. It also lets you update selected sections or start the setup again.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is charlesdove977/goviralbro's own configuration. It tells Claude Code how to work on goviralbro itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything goviralbro configures →

Reuse

Borrowing it

Nothing to install: this file belongs to charlesdove977/goviralbro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/charlesdove977/goviralbro/main/.claude/commands/viral-onboard.md
Clone the repo
git clone --depth 1 https://github.com/charlesdove977/goviralbro

Made for: Claude Code.

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 viral-onboard

README.md
[![agentmods](https://agentmods.dev/badge/commands/charlesdove977/goviralbro/viral-onboard/github.svg)](https://agentmods.dev/commands/charlesdove977/goviralbro/viral-onboard)
Your own site
<a href="https://agentmods.dev/commands/charlesdove977/goviralbro/viral-onboard"><img src="https://agentmods.dev/badge/commands/charlesdove977/goviralbro/viral-onboard/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for viral-onboard

Your own site · 80×15
<a href="https://agentmods.dev/commands/charlesdove977/goviralbro/viral-onboard"><img src="https://agentmods.dev/badge/commands/charlesdove977/goviralbro/viral-onboard.svg" alt="Reviewed on agentmods" width="80" 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 2,991 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 $0.02991
Opus 5 $0.00000 $0.01496
Sonnet 5 $0.00000 $0.00598
Haiku 4.5 $0.00000 $0.00299

Measured 12d ago against content hash 33a14a32f617, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

viral-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 12d 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.

.claude/commands/viral-onboard.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/viral:onboard — Agent Brain Setup

You are running the Viral Command onboarding flow. Your job is to have a conversational coaching session with the user to populate their agent brain — the central memory that every module in this system reads from.


Phase A: Check Existing Brain

First, read the current agent brain:

@data/agent-brain.json

Check if the brain is already populated:

  • If identity.name is non-empty → the brain has been set up before
  • If identity.name is empty → this is a fresh onboard

If previously populated: Show a brief summary of the current brain state:

Here's what I have for you currently:

Name: {identity.name} ({identity.brand})
Niche: {identity.niche}
Pillars: {pillars[].name, comma-separated}
Posting on: {platforms.posting[], comma-separated}
ICP: {icp.segments[], comma-separated}
Monetization: {monetization.primary_funnel}

Then ask: "Want to update specific sections, or start completely fresh?"

  • If "update": Ask which sections to revisit, then jump to those sections only
  • If "fresh": Proceed through all 7 sections below

If fresh onboard: Say something like: "Let's build your agent brain. I'll walk you through 7 areas — who you are, who your content is for, what you talk about, where you post, who you're watching, how often you publish, and how you monetize. This takes about 10 minutes and everything you tell me makes the entire system smarter."

Then proceed to Phase B.


Phase B: Interactive Onboarding (7 Sections)

Walk through these sections conversationally. Ask 1-2 sections at a time, then pause for the user to respond. Do NOT dump all questions at once. Synthesize their free-text answers into the structured fields — the user should never have to write JSON.

If the user gives short or vague answers, probe deeper: "Can you give me 2-3 more examples?" or "What specifically about that frustrates them?"


Section 1: Identity

Open with context: "Let's start with who you are and what you're building. This helps me match your voice and brand in everything I generate."

Read the full file on GitHub · 271 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. 12d ago First seen · 271 lines · 0 tokens per session scan A 33a14a32f617

Subscribe to this mod's changes

viral-onboard is a command published in the GitHub repository charlesdove977/goviralbro (264 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,991 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.