init-project

init-project is a command for coding agents from sangrokjung/claude-forge. It costs 8 tokens per session (992 once invoked), scanned A, original, MIT.

An interactive command that prepares a new software project by detecting its technology and structure, then generating CLAUDE.md, spec.md, and prompt_plan.md files. These files describe project guidance, feature requirements, and implementation phases.

In plain words
What is it for?
Use it when starting or organizing a Next.js, Vite, Go, Python, or Rust project, especially when you need initial coding rules, a feature specification, and a phased work plan.
Why use it?
It gives an initially unstructured project a documented starting point based on its existing files and your answers about the project.

Command

Part of the claude-forge plugin — 33 skills, 39 commands, 17 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/sangrokjung/claude-forge/init-project
Clone the repo
git clone --depth 1 https://github.com/sangrokjung/claude-forge

Or install claude-forge, the plugin that ships this one along with the rest of its 33 skills, 39 commands, 17 agents.

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-project

README.md
[![agentmods](https://agentmods.dev/badge/commands/sangrokjung/claude-forge/init-project.svg)](https://agentmods.dev/commands/sangrokjung/claude-forge/init-project)
Your own site
<a href="https://agentmods.dev/commands/sangrokjung/claude-forge/init-project"><img src="https://agentmods.dev/badge/commands/sangrokjung/claude-forge/init-project.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 992 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 $0.00008 $0.00992
Opus 5 $0.00004 $0.00496
Sonnet 5 $0.00002 $0.00198
Haiku 4.5 $0.00001 $0.00099

Measured 5d ago against content hash f7af01b84d67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init-project 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.

commands/init-project.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/init-project - 프로젝트 초기화 (v6)

프로젝트 초기화 체크리스트. 최초 1회 실행하여 CLAUDE.md, spec.md, prompt_plan.md를 대화형으로 생성한다.

0단계: 파라미터 파싱

$ARGUMENTS에서 플래그를 파싱한다.

플래그 설명
[프로젝트명] 프로젝트 이름 (없으면 디렉토리명 사용)
--type [type] 프로젝트 유형 강제 지정 (next/vite/go/python/rust)

1단계: 프로젝트 환경 감지

현재 디렉토리에서 프로젝트 정보를 자동으로 수집한다.

수집 항목:
  1. package.json / go.mod / Cargo.toml / pyproject.toml -> 기술 스택
  2. .git 존재 여부 -> Git 초기화 상태
  3. README.md -> 프로젝트 설명
  4. 기존 CLAUDE.md -> 이미 초기화 여부
  5. 디렉토리 구조 -> 아키텍처 패턴

기존 CLAUDE.md가 있으면 사용자에게 덮어쓰기/병합/취소를 확인한다.

2단계: CLAUDE.md 생성

수집된 정보와 사용자 입력을 기반으로 CLAUDE.md를 생성한다.

포함 항목

# [프로젝트명]

## 개요
[프로젝트 설명]

## 기술 스택
- [감지된 기술 스택]

## 빌드 & 테스트
- 빌드: [npm run build / go build / ...]
- 테스트: [npm test / go test / ...]
- 린트: [eslint / golangci-lint / ...]

## 디렉토리 구조
[주요 디렉토리와 역할]

## 코딩 컨벤션
[감지된 컨벤션 또는 사용자 입력]

3단계: spec.md 생성

기능 명세 템플릿을 생성한다.

템플릿

# [프로젝트명] - 기능 명세

## Feature 1: [기능명]
### 요구사항
1. [요구사항]
### API 명세
- [엔드포인트 정의]
### 데이터 모델
- [모델 정의]
### 비즈니스 로직
- [핵심 로직]

사용자에게 주요 기능을 대화형으로 물어보고 작성한다.

4단계: prompt_plan.md 생성

구현 계획을 Phase별로 생성한다.

템플릿

# [프로젝트명] - 구현 계획

## Phase 1: [단계명]
- [ ] [작업 1]
- [ ] [작업 2]

## Phase 2: [단계명]
- [ ] [작업 1]
- [ ] [작업 2]

## 의존성
- Phase 2는 Phase 1 완료 후 진행

spec.md의 기능을 기반으로 Phase를 자동 분해한다.

5단계: .gitignore 확인

.gitignore에 다음 항목이 포함되어 있는지 확인하고, 없으면 추가를 제안한다.

# Claude Code (v6 Post-Dev Workflow)
.claude/handoff.md
.claude/checkpoints/
.claude/web-checklist-state.json

6단계: 출력

════════════════════════════════════════════════════════════════
 Init Project v6
════════════════════════════════════════════════════════════════

프로젝트: [프로젝트명]
기술 스택: [감지된 스택]

생성 완료:
  CLAUDE.md       ([N]줄)
  spec.md         ([N]줄)
  prompt_plan.md  ([N]줄)

.gitignore 업데이트: [추가됨/이미 포함]

디렉토리 구조:
  project/
    CLAUDE.md
    spec.md
    prompt_plan.md
    .claude/
      handoff.md       (gitignore)
      checkpoints/     (gitignore)

다음 단계:
  1. spec.md에 기능 명세 상세 작성
  2. prompt_plan.md에 구현 계획 구체화
  3. /orchestrate 로 작업 시작

════════════════════════════════════════════════════════════════

Read the full file on GitHub · 151 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 · 151 lines · 8 tokens per session scan A f7af01b84d67

Subscribe to this mod's changes

init-project is a command published in the GitHub repository sangrokjung/claude-forge (825 stars, last pushed yesterday), licensed MIT. It adds 8 tokens to every session and 992 once invoked, about $0.0000 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.