agentic-engineering-framework: Command for Claude Code

.claude/commands/new-project.md

new-project is a command for Claude Code from DimitriGeelen/agentic-engineering-framework. It costs 0 tokens per session (574 once invoked), scanned A, original, Apache-2.0.

A guided command for starting a new software project with the Agentic Engineering Framework. It asks for the project location and AI provider, checks prerequisites, initializes Git when needed, and runs the framework setup.

In plain words
What is it for?
Use it to create or initialize a project, verify its path and framework health, set the AI provider, and report what setup files were created.
Why use it?
It removes the need to remember the setup sequence and checks for common problems before initialization. It also warns when a project may already be configured.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

This is DimitriGeelen/agentic-engineering-framework's own configuration. It tells Claude Code how to work on agentic-engineering-framework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentic-engineering-framework configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DimitriGeelen/agentic-engineering-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DimitriGeelen/agentic-engineering-framework/master/.claude/commands/new-project.md
Clone the repo
git clone --depth 1 https://github.com/DimitriGeelen/agentic-engineering-framework

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 new-project

README.md
[![agentmods](https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/new-project/github.svg)](https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/new-project)
Your own site
<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/new-project"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/new-project/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for new-project

Your own site · 80×15
<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/new-project"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/new-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 574 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00574
Opus 5.5 $0.00000 $0.00230
Sonnet 5.5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured 1mo ago against content hash 1f97379fad6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

new-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 1mo 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/new-project.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/new-project - Initialize New Project

Guided onboarding for setting up a new project with the Agentic Engineering Framework.

Step 1: Gather Info

Ask the user (using AskUserQuestion with two questions):

  1. Project path — "What is the path to your project directory?"
    • Options: "Current directory", "Enter path"
  2. AI provider — "Which AI provider will you use?"
    • Options: "Claude (Recommended)", "Cursor", "Generic (any provider)"

Map provider answers: "Claude" → claude, "Cursor" → cursor, "Generic" → generic.

Step 2: Verify Prerequisites

Run in parallel:

  1. fw doctor — check framework health
  2. ls {project_path} — verify path exists (create with mkdir -p if not)
  3. Check if path already has .framework.yaml — warn if re-initializing

If fw doctor shows failures, stop and help fix them first.

Step 3: Initialize Git (if needed)

Check if the project directory has a git repo:

git -C {project_path} rev-parse --git-dir 2>/dev/null

If not, initialize:

git init {project_path}

Step 4: Run fw init

fw init {project_path} --provider {provider}

Report what was created. If init fails, diagnose and fix.

Step 5: Verify Setup

cd {project_path}
fw doctor

Report results. All checks should pass. Fix any failures before proceeding.

Step 6: Start First Session

cd {project_path}
fw context init

Step 7: Create First Task

Ask the user: "What's the first thing you want to work on?"

Then run:

cd {project_path}
fw work-on "{user_description}" --type build

Print confirmation:

Project initialized and ready!
- Path: {project_path}
- Provider: {provider}
- First task: T-XXX ({task_name})

You're all set. Start coding!

Rules

  • This skill is for NEW projects only. For existing projects, use fw work-on.
  • Always create a git repo before running fw init (it requires git hooks).
  • If the directory doesn't exist, create it with mkdir -p.
  • If re-initializing an existing project, warn the user and require confirmation.
  • Run fw doctor both before (framework check) and after (project check) init.
  • The skill ends by creating the first task — the user should be ready to work immediately.

Read the full file on GitHub · 89 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. 1mo ago First seen · 89 lines · 0 tokens per session scan A 1f97379fad6e

Subscribe to this mod's changes

new-project is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (18 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 574 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 2026-09-04.