project

A project setup and coordination command for a group of specialized coding agents. It checks for an existing project, asks questions for new ones, creates folders, and starts the agent workflow.

In plain words
What is it for?
Use it to start a project, continue work described in PROJECT.md, create project folders, deploy specialized agents, and begin coordinated development.
Why use it?
It gives a new or existing project a consistent structure and coordinates several agents from one starting command. A monorepo keeps multiple parts in one repository, while a multi-repo setup keeps them separate.

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/bijutharakan/multi-agent-squad/project
Clone the repo
git clone --depth 1 https://github.com/bijutharakan/multi-agent-squad

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 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 $0.00023 $0.00669
Opus 5 $0.00012 $0.00334
Sonnet 5 $0.00005 $0.00134
Haiku 4.5 $0.00002 $0.00067

Measured 2d ago against content hash 08479e95af7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Command

This is the main entry point for the Multi-Agent Squad orchestration system.

What This Command Does

Initiates the complete project setup and orchestration flow:

  1. Checks for existing project - Looks for PROJECT.md
  2. Interactive setup - Asks about your project if new
  3. Creates structure - Sets up directories based on your needs
  4. Deploys agents - Creates specialized AI agents
  5. Begins orchestration - Starts managing your development

Usage

Simply type:

  • /project

Or in natural language:

  • "Start a new project"
  • "Set up project"
  • "Begin orchestration"

What Happens

When you run this command, I'll:

  1. Check if this is a new or existing project

    • If PROJECT.md exists, I'll read it and continue orchestration
    • If not, I'll start the interactive setup
  2. Ask you key questions (for new projects):

    • What are you building?
    • New project or existing code?
    • Monorepo or multi-repo?
    • How do you track issues?
    • Any specialized needs?
  3. Create your project structure

    • projects/ for multi-repo setups
    • src/ for monorepos
    • docs/ for documentation
    • .claude/agents/ for your AI team
  4. Deploy specialized agents

    • Product Manager for requirements
    • Architect for system design
    • Engineers for implementation
    • QA for testing
    • DevOps for deployment
  5. Begin orchestration

    • Ready to manage features
    • Track progress
    • Coordinate development

Example Flow

You: /project

Me: Hello! I'm your Multi-Agent Squad Orchestrator. 
    I see this is a new project setup. What are you building?

You: A task management web app

Me: Great! Is this a brand new project or do you have existing code?

You: Brand new

Me: How would you like to organize your code?
    - Monorepo (all code in one repository)
    - Multi-repo (separate repositories)
    - Let me decide

You: Multi-repo

[Continues with setup...]

For Existing Projects

If you already have a PROJECT.md file:

Read the full file on GitHub · 116 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. 2d ago First seen · 116 lines · 23 tokens per session scan A 08479e95af7b

Subscribe to this mod's changes

project is a command published in the GitHub repository bijutharakan/multi-agent-squad (86 stars, last pushed 1y ago), licensed MIT. It adds 23 tokens to every session and 669 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.