init

init is a command for Claude Code from nguyennguyenit/MultiClaude. It costs 11 tokens per session (2,532 once invoked), scanned A, original, MIT.

A reverse-engineering command that creates project documentation by examining an existing codebase. It can document business rules, user interfaces, API routes, and database structure across one or more repositories.

In plain words
What is it for?
Use it to initialize documentation for existing frontend and backend projects, shared libraries, or multiple services. It is intended for established codebases, not new projects from scratch.
Why use it?
It helps teams understand and maintain software that was built without reliable documentation. A monorepo is one repository containing multiple parts of a project; separate repositories and microservices are supported too.

Command for Claude Code

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/nguyennguyenit/multiclaude/init
Clone the repo
git clone --depth 1 https://github.com/nguyennguyenit/MultiClaude

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 init

README.md
[![agentmods](https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/init.svg)](https://agentmods.dev/commands/nguyennguyenit/multiclaude/init)
Your own site
<a href="https://agentmods.dev/commands/nguyennguyenit/multiclaude/init"><img src="https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/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 2,532 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 $0.02532
Opus 5 $0.00005 $0.01266
Sonnet 5 $0.00002 $0.00506
Haiku 4.5 $0.00001 $0.00253

Measured 5d ago against content hash 289bd9bb1a32, 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 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.

.claude/commands/ipa/init.md · 452 lines

How it starts

The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Generate IPA-standard documentation from an existing codebase that has no docs.

This is the entry point for applying IPA workflow to running projects.

Output:

  • docs/SRD.md - Inferred from business logic
  • docs/UI_SPEC.md - Extracted from UI components
  • docs/API_SPEC.md - Extracted from API routes
  • docs/DB_DESIGN.md - Extracted from database schema

Input

Supported Structures

1. Monorepo (single path or current dir):

/ipa:init
/ipa:init ./my-project

2. Separate FE/BE repos:

/ipa:init ./frontend ./backend

3. Microservices (multiple repos):

/ipa:init ./user-service ./order-service ./payment-service

4. Mixed paths:

/ipa:init ~/projects/my-fe ~/projects/my-be ~/projects/shared-lib

When to Use

Situation Use This?
Existing project, no docs ✅ Yes
Existing project, has some docs ✅ Yes (will merge/enhance)
Separate FE/BE repos ✅ Yes (pass both paths)
Microservices ✅ Yes (pass all service paths)
New project from scratch ❌ No (use /ipa:all)
After implementing tasks ❌ No (use /ipa-docs:sync)

Workflow

Step 0: Parse Input Paths

If multiple paths provided:

/ipa:init ./frontend ./backend
        ↓
┌─────────────────────────────────────────┐
│ Paths detected:                         │
│ - ./frontend → FE (React/Vue/etc.)      │
│ - ./backend → BE (NestJS/FastAPI/etc.)  │
└─────────────────────────────────────────┘

For microservices:

/ipa:init ./user-svc ./order-svc ./payment-svc
        ↓
┌─────────────────────────────────────────┐
│ Services detected:                      │
│ - user-svc → User Service               │
│ - order-svc → Order Service             │
│ - payment-svc → Payment Service         │
│                                         │
│ API_SPEC will group by service          │
│ DB_DESIGN will show per-service schemas │
└─────────────────────────────────────────┘

Read the full file on GitHub · 452 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. 5d ago First seen · 452 lines · 0 tokens per session scan A 289bd9bb1a32

Subscribe to this mod's changes

init is a command published in the GitHub repository nguyennguyenit/MultiClaude (22 stars, last pushed 24d ago), licensed MIT. It adds 11 tokens to every session and 2,532 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.