init

A first-run setup command that creates Forge's project state files and helps choose between founder mode and product-management mode. It copies templates without overwriting existing files and routes the project to the next command.

In plain words
What is it for?
Use it when adding Forge to a project for the first time, especially when the project is empty or you need to choose whether to validate an idea or ship an existing product.
Why use it?
It removes the manual work of preparing Forge and explains the setup choice in plain language for new users.

Command

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/dormstern/forge/init
Clone the repo
git clone --depth 1 https://github.com/dormstern/forge
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,674 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 $0.00066 $0.01674
Opus 5 $0.00033 $0.00837
Sonnet 5 $0.00013 $0.00335
Haiku 4.5 $0.00007 $0.00167

Measured yesterday against content hash a45eb79eea0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

commands/init.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forge:init — First-run setup

Execution mode: direct. This command has explicit steps below — execute them in order. Do not enter plan mode, do not write a plan file, do not call ExitPlanMode. The framework already did the planning; you just run the steps.

You are setting up Forge in the user's project for the first time. This is the user's first impression of Forge. Clarity, warmth, and idiot-proof framing beat technical accuracy. Save methodology terminology for after the mode is picked.

Behavior

Step 1 — Detect the situation

  • --founder flag passed OR user said "pre-PMF" / "validating" / "early stage" → Founder mode, skip to Step 3.
  • --pm flag passed OR user said "shipping" / "post-PMF" / "have users" → PM mode, skip to Step 3.
  • No flag, directory has package.json and README.md → Default to PM mode (the user already has a product). Skip to Step 3.
  • No flag, directory is empty (no package.json, no README, no source) → Run Step 2 (the welcome question).

Step 2 — First-run welcome question (CRITICAL — no jargon)

Use AskUserQuestion with this EXACT framing:

Header (chip label, max 12 chars): Forge setup

Question: "Welcome to Forge. Two ways to use it — which describes you?"

Options (3 options, no "Other" — system adds it):

  1. Label: Validating an idea (Recommended) Description: "You have an idea but aren't sure yet who'd pay for it or why they'd choose you. Forge will help you find real users, attack your assumptions, and decide what's worth building. Next: /forge:scout."

  2. Label: Shipping a product Description: "You already have users — paying or design partners. You want discipline around what to build next, what to kill, and how to catch features drifting off-strategy. Next: /forge:harvest."

  3. Label: Both Description: "Scaffold both sets so you can poke around. Useful if you'll start by validating and graduate to shipping in the same repo."

Read the full file on GitHub · 115 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 · 115 lines · 66 tokens per session scan A a45eb79eea0f

Subscribe to this mod's changes

init is a command published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 1,674 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 2026-08-31.