claude-scaffold: Command for Claude Code

.claude/commands/new-project.md

new-project is a command for Claude Code from pyramidheadshark/claude-scaffold. It costs 0 tokens per session (777 once invoked), scanned A, original, MIT.

A command for creating a new Python project from the claude-scaffold template. It sets up project files, development documentation, Claude Code configuration, and Git version control after asking for project choices.

In plain words
What is it for?
Use it to initialize projects with selected infrastructure, frontend, agent-pipeline, CI/CD, and deployment options.
Why use it?
It removes the repeated setup work involved in starting a project with a consistent structure and development workflow.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is pyramidheadshark/claude-scaffold's own configuration. It tells Claude Code how to work on claude-scaffold 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 claude-scaffold configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pyramidheadshark/claude-scaffold. 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/pyramidheadshark/claude-scaffold/main/.claude/commands/new-project.md
Clone the repo
git clone --depth 1 https://github.com/pyramidheadshark/claude-scaffold

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/pyramidheadshark/claude-scaffold/new-project/github.svg)](https://agentmods.dev/commands/pyramidheadshark/claude-scaffold/new-project)
Your own site
<a href="https://agentmods.dev/commands/pyramidheadshark/claude-scaffold/new-project"><img src="https://agentmods.dev/badge/commands/pyramidheadshark/claude-scaffold/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/pyramidheadshark/claude-scaffold/new-project"><img src="https://agentmods.dev/badge/commands/pyramidheadshark/claude-scaffold/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 777 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 $0.00777
Opus 5 $0.00000 $0.00388
Sonnet 5 $0.00000 $0.00155
Haiku 4.5 $0.00000 $0.00078

Measured 9d ago against content hash 21cc62e6e5c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/new-project

Initializes a new project from the claude-scaffold template.

What This Command Does

  1. Creates the full project directory structure
  2. Copies and customizes template files (pyproject.toml, Dockerfile, etc.)
  3. Initializes design-doc.md and dev/status.md
  4. Sets up .claude/ directory with skills and hooks
  5. Runs uv init and git init

Instructions for Claude Code

Ask the developer for:

  • Project name (will be used as directory name and Python package name)
  • Brief description (one sentence)
  • Infrastructure tier: Docker Compose / K8s-ready / GPU
  • Does it need a frontend? (HTMX or none)
  • Does it need an agent pipeline? (LangGraph or none)
  • CI/CD profile (choose one):
    • minimal — lint + typecheck + test (CLI tools, data scripts, scrapers — no Docker)
    • fastapi — + docker-build (standard FastAPI service)
    • fastapi-db — + postgres service + alembic migration check + docker-build
    • ml-heavy — + HuggingFace model cache + bandit security scan + docker-build
  • Deploy target (choose one): none / yc (Yandex Cloud Serverless Container) / vps (SSH + docker-compose)

Then execute in order:

1. Create structure

mkdir -p {project-name}/src/{project_name}/{api/routers,api/pages,core,services,adapters/{llm,storage,db},models}
mkdir -p {project-name}/tests/{unit/{core,services},integration,features/steps}
mkdir -p {project-name}/{dev/active,infra/{packer,terraform},notebooks,.github/workflows,.claude/{skills,hooks,agents,commands}}
touch {project-name}/src/{project_name}/__init__.py
touch {project-name}/tests/__init__.py
touch {project-name}/data/.gitkeep
touch {project-name}/models/.gitkeep

2. Copy and customize templates

Copy from claude-scaffold/templates/:

  • design-doc.md → project root (replace {Project Name} with actual name)
  • status.mddev/status.md (initialize Phase 0 as active)
  • Dockerfile → project root (replace project_name placeholder)
  • docker-compose.yml → project root (skip if CI profile is minimal)
  • github-actions/{ci_profile}.yml.github/workflows/ci.yml
  • If deploy target is not none: github-actions/deploy/{deploy_target}.yml.github/workflows/deploy.yml

Read the full file on GitHub · 78 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. 9d ago First seen · 78 lines · 0 tokens per session scan A 21cc62e6e5c2

Subscribe to this mod's changes

new-project is a command published in the GitHub repository pyramidheadshark/claude-scaffold (4 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 777 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 2026-08-31.