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.
npx skills add karashiiro/agent-skills --skill creating-a-new-projectgit clone --depth 1 https://github.com/karashiiro/agent-skillsWrote 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.
[](https://agentmods.dev/skills/karashiiro/agent-skills/creating-a-new-project)<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.
<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>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 5.1 | $0.00035 | $0.01655 |
| Opus 5 | $0.00017 | $0.00827 |
| Sonnet 5 | $0.00007 | $0.00331 |
| Haiku 4.5 | $0.00003 | $0.00166 |
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.
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, ornewcommand likely exists
Core Pattern
STOP before writing any config or boilerplate files. Follow this order:
- Search for the official scaffolding tool for the framework/language/platform
- Run the generator with appropriate options (use non-interactive flags — see below)
- 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:
- Check the generator's
--helpoutput for non-interactive flags - Specify the template/preset and all required options via CLI flags
- 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 |
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.
- 10d ago First seen · 110 lines · 35 tokens per session scan A 19face3b3e09
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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.