ralph-init

ralph-init is a command for coding agents from Samin12/claude-course. It costs 11 tokens per session (498 once invoked), scanned A, original, MIT.

A command that creates the files and folders for a new Ralph Marketer project, an automated SaaS marketing-writing workflow.

In plain words
What is it for?
Use it to initialize a project with Ralph templates, sample database data, draft and published-content folders, and JavaScript utilities.
Why use it?
It removes the manual setup needed for the task list, progress tracking, content folders, database, and supporting scripts.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the ralph-wiggum-marketer plugin — 1 skill, 4 commands, 1 hook 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/samin12/claude-course/ralph-init
Clone the repo
git clone --depth 1 https://github.com/Samin12/claude-course

Or install ralph-wiggum-marketer, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 1 hook.

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 ralph-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/samin12/claude-course/ralph-init.svg)](https://agentmods.dev/commands/samin12/claude-course/ralph-init)
Your own site
<a href="https://agentmods.dev/commands/samin12/claude-course/ralph-init"><img src="https://agentmods.dev/badge/commands/samin12/claude-course/ralph-init.svg" alt="Measured on agentmods" height="20"></a>
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 498 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 5.1 $0.00011 $0.00498
Opus 5 $0.00005 $0.00249
Sonnet 5 $0.00002 $0.00100
Haiku 4.5 $0.00001 $0.00050

Measured 5d ago against content hash c210958accbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ralph-init 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 5d 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.

skills/ralph-wiggum-marketer/commands/ralph-init.md · 70 lines

What it actually says

Initialize Ralph the Marketer

Set up a new Ralph Marketer copywriting project in the current directory.

What This Does

  1. Creates the directory structure for Ralph
  2. Copies template files (prd.json, progress.txt, prompt.md)
  3. Sets up the content database with sample data
  4. Creates content directories (drafts/, published/)

Setup Steps

# Create directories
mkdir -p scripts/ralph content/{drafts,published} data src/{db,content}

# Copy database scripts from plugin
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT}"
cp "$PLUGIN_ROOT/scripts/src/db/init.js" src/db/
cp "$PLUGIN_ROOT/scripts/src/db/seed.js" src/db/
cp "$PLUGIN_ROOT/scripts/src/db/status.js" src/db/
cp "$PLUGIN_ROOT/scripts/src/db/query.js" src/db/
cp "$PLUGIN_ROOT/scripts/src/content/list.js" src/content/
cp "$PLUGIN_ROOT/scripts/src/test.js" src/

# Copy Ralph templates
cp "$PLUGIN_ROOT/templates/prd.json" scripts/ralph/
cp "$PLUGIN_ROOT/templates/progress.txt" scripts/ralph/
cp "$PLUGIN_ROOT/templates/prompt.md" scripts/ralph/

# Copy package.json if it doesn't exist
if [ ! -f package.json ]; then
  cp "$PLUGIN_ROOT/templates/package.json" .
fi

# Create .gitkeep files
touch content/drafts/.gitkeep content/published/.gitkeep data/.gitkeep

# Initialize git if needed
if [ ! -d .git ]; then
  git init
fi

# Install dependencies
npm install

# Initialize and seed database
npm run db:reset

echo "✅ Ralph Marketer initialized!"
echo ""
echo "Next steps:"
echo "  1. Edit scripts/ralph/prd.json with your content tasks"
echo "  2. Run /ralph-marketer to start the loop"

After Initialization

The user should:

  1. Customize scripts/ralph/prd.json with their specific content tasks
  2. Optionally modify the seed data in src/db/seed.js with their own trends/research/communications
  3. Run /ralph-marketer to start the autonomous content creation loop
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. 5d ago First seen · 70 lines · 11 tokens per session scan A c210958accbc

Subscribe to this mod's changes

ralph-init is a command published in the GitHub repository Samin12/claude-course (20 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 498 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 2026-08-30.