creating-a-new-project

creating-a-new-project is a skill for Claude Code, Codex from karashiiro/agent-skills. It costs 35 tokens per session (1,655 once invoked), scanned A, original, Unlicense.

A project-setup guide for creating new applications, repositories, packages, or workspaces such as a monorepo, which is one repository containing multiple related projects.

In plain words
What is it for?
Use it before starting a project or adding a package to find and run the appropriate official generator, then customize its output.
Why use it?
It prevents hand-written boilerplate from drifting away from the official setup conventions of a framework or platform.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before starting a project or adding a package to find and run the appropriate official generator, then customize its output.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karashiiro/agent-skills/creating-a-new-project
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.

Any agent
npx skills add karashiiro/agent-skills --skill creating-a-new-project
Clone the repo
git clone --depth 1 https://github.com/karashiiro/agent-skills

Made for: Claude Code, Codex.

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 creating-a-new-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/karashiiro/agent-skills/creating-a-new-project/github.svg)](https://agentmods.dev/skills/karashiiro/agent-skills/creating-a-new-project)
Your own site
<a href="https://agentmods.dev/skills/karashiiro/agent-skills/creating-a-new-project"><img src="https://agentmods.dev/badge/skills/karashiiro/agent-skills/creating-a-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 creating-a-new-project

Your own site · 80×15
<a href="https://agentmods.dev/skills/karashiiro/agent-skills/creating-a-new-project"><img src="https://agentmods.dev/badge/skills/karashiiro/agent-skills/creating-a-new-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,655 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 $0.00035 $0.01655
Opus 5 $0.00017 $0.00827
Sonnet 5 $0.00007 $0.00331
Haiku 4.5 $0.00003 $0.00166

Measured 10d ago against content hash 19face3b3e09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

creating-a-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 10d 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.

creating-a-new-project/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating a New Project

Overview

Always search for and use official project generators or scaffolding tools before writing project boilerplate by hand. Generators encode community best practices, produce standardized structure, and stay current with ecosystem conventions.

When to Use

  • Creating a new application, library, package, or repository
  • Setting up a new workspace or monorepo
  • Adding a new package to an existing monorepo
  • Bootstrapping any project where a create-*, init, or new command likely exists

Core Pattern

STOP before writing any config or boilerplate files. Follow this order:

  1. Search for the official scaffolding tool for the framework/language/platform
  2. Run the generator with appropriate options (use non-interactive flags — see below)
  3. Customize the generated output to fit the specific needs

Never hand-write files that a generator would produce (package.json, tsconfig.json, Cargo.toml, pyproject.toml, Dockerfile templates, CI configs, etc.) unless no generator exists.

Handling Interactive Generators

Most generators prompt interactively by default. Since CLI agents cannot respond to interactive prompts, always use non-interactive flags to specify all options upfront.

Strategy:

  1. Check the generator's --help output for non-interactive flags
  2. Specify the template/preset and all required options via CLI flags
  3. If no non-interactive mode exists, ask the user to run the generator themselves

Non-Interactive Flags by Generator

Generator Key Flags Example
Vite --template, --no-interactive npm create vite@latest my-app -- --template react-ts --no-interactive
Next.js --yes, --ts, --app, --tailwind, --src-dir, --eslint npx create-next-app@latest my-app --yes --ts --app
Nuxt --template, --no-modules, --packageManager npm create nuxt@latest my-app -- --no-modules --packageManager=pnpm
SvelteKit --no-add-ons, --no-install, --add npx sv create my-app --no-add-ons --no-install
Astro -y / --yes, --template npm create astro@latest my-app -- --template minimal -y
React Router --template (required) npx create-react-router@latest my-app --template remix-run/react-router-templates/default
Expo --yes, --template npm create expo my-app -- --yes --template blank
Tauri --template npm create tauri-app@latest my-app -- --template react
Electron Forge --template npx create-electron-app@latest my-app --template webpack
Turborepo -m, --skip-install npx create-turbo@latest my-monorepo -m pnpm
Nx --interactive=false, --preset npx create-nx-workspace@latest myorg --preset=empty --interactive=false --nxCloud skip
Rust Already non-interactive cargo new my-project
Go Already non-interactive go mod init github.com/user/my-module
Python (uv) Already non-interactive uv init my-project
.NET Already non-interactive dotnet new webapi -n MyProject

Read the full file on GitHub · 110 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. 10d ago First seen · 110 lines · 35 tokens per session scan A 19face3b3e09

Subscribe to this mod's changes

creating-a-new-project is a skill published in the GitHub repository karashiiro/agent-skills (2 stars, last pushed 4mo ago), licensed Unlicense. It adds 35 tokens to every session and 1,655 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories