What is project-init?

A command that starts a new project using the Multi-Agent Squad system, which coordinates several specialized coding agents. It gathers project details, creates folders and agents, and can set up Git repositories.

Starting projects, choosing a monorepo or multiple repositories, creating frontend and backend folders, deploying specialized agents, and making initial Git commits.

It replaces manual project setup with a guided process that records the project structure, automation needs, and agent roles.

project-init — Command by bijutharakan

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/bijutharakan/multi-agent-squad/project-init

Clone the repo

git clone --depth 1 https://github.com/bijutharakan/multi-agent-squad

Made for: Claude Code.

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 572 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00572
Opus 5	$0.00000	$0.00286
Sonnet 5	$0.00000	$0.00114
Haiku 4.5	$0.00000	$0.00057

Measured 2d ago against content hash 4e0de75d0c19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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 2d 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/project-init.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Initialization Command

Initialize a new project with the Multi-Agent Squad orchestration system.

Command Aliases

/project
/create-project
/project-init
"Start a new project"
"Initialize project"

Process Flow

1. Pre-Check

Check if PROJECT.md exists
If exists, read current project state
If not, start interactive setup

2. Interactive Setup

Gather information through conversation:

Project type and description
Code organization (monorepo/multi-repo)
Task tracking preferences
Automation needs
Integration requirements

3. Directory Creation

Create clear structure under project/ folder:

project/
├── frontend/     # Frontend code
├── backend/      # Backend code
├── services/     # Microservices
└── docs/         # Project documentation

4. Agent Deployment

Create specialized agents in category folders:

.claude/agents/engineering/
.claude/agents/product/
.claude/agents/architecture/
.claude/agents/quality/
.claude/agents/specialized/

5. Git Setup

Initialize repositories
Optionally connect to remote (GitHub/GitLab)
Create initial commits

6. Project Summary

Show exactly what was created:

File tree with ✨ for new files
Agent count and types
Configured integrations
Automation level

7. Status Update

Create PROJECT_STATUS.md with:

Initialization summary
What was set up
Next steps checklist

8. Next Actions Menu

Present numbered options:

Create requirements/epics
Design architecture
Set up environment
Start sprint planning
Configure CI/CD
Custom request

Important Rules

Clear Segregation: Project files go in project/, system files stay in .claude/
Show Results: Display tree of created files
Git Integration: Ask about remote repositories
Status Tracking: Always update PROJECT_STATUS.md
Next Steps: Provide actionable options
Agent Delegation: Use specialized agents for tasks

Error Handling

Read the full file on GitHub · 95 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.

2d ago First seen · 95 lines · 0 tokens per session scan A 4e0de75d0c19

Subscribe to this mod's changes

project-init is a command published in the GitHub repository bijutharakan/multi-agent-squad (86 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 572 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.

Backend and APIs Frontend Git and workflow

project-init