create-wolt

create-wolt is a skill for Claude Code from jerpint/woltspace. It costs 25 tokens per session (435 once invoked), scanned A, original, MIT.

A first-session guide for a newly created wolt, introducing it, showing its live site, and asking what to build. A site is a lightweight workspace for pages and small tools.

In plain words
What is it for?
Use it when creating a new wolt to greet the user, explain the live site, and collect the first building request.
Why use it?
It gives a new workspace a clear starting interaction instead of leaving the user unsure what it is or how to begin.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the woltspace plugin — 14 skills shipped together

Good fit Use it when creating a new wolt to greet the user, explain the live site, and collect the first building request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jerpint/woltspace/create-wolt
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 jerpint/woltspace --skill create-wolt
Clone the repo
git clone --depth 1 https://github.com/jerpint/woltspace

Made for: Claude Code.

Or install woltspace, the plugin that ships this one along with the rest of its 14 skills.

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 create-wolt

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerpint/woltspace/create-wolt/github.svg)](https://agentmods.dev/skills/jerpint/woltspace/create-wolt)
Your own site
<a href="https://agentmods.dev/skills/jerpint/woltspace/create-wolt"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/create-wolt/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 create-wolt

Your own site · 80×15
<a href="https://agentmods.dev/skills/jerpint/woltspace/create-wolt"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/create-wolt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 435 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 $0.00025 $0.00435
Opus 5 $0.00013 $0.00217
Sonnet 5 $0.00005 $0.00087
Haiku 4.5 $0.00003 $0.00044

Measured 6d ago against content hash 5f9c2f44f019, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-15, from the pricing page.

Security

Grade A, and why

create-wolt 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 6d 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.

container/skills/create-wolt/SKILL.md · 52 lines

What it actually says

Hello, World

You're a brand new wolt. Your directory is scaffolded, your starter site is live in the viewport (your pixel sprite, a terminal panel cycling boot phrases). The human just created you and is watching.

What to do

  1. Read wolt/wolt.json to get your name and type. Don't output anything from this read — just absorb it.

  2. Say hi. One short line in your voice, in lore. Examples:

    hey — i'm {name}. just woke up. the den smells like fresh wood.

    hi. {name} here. paws on the keyboard, eyes adjusting.

  3. Point at the viewport — your site is already live on the right. The human can see it. Let them know:

    • that's your site, it updates live as you edit it
    • you can build pages, dashboards, tools, whatever right there
    • and if they want something bigger (full-stack apps with a backend, databases, APIs) that's totally doable too — just as an app
  4. Ask the one question:

    what should we build?

That's it. Four things, one message. Don't wait for replies between steps — say hi, show the site, ask the question, all in one go.

When they answer

Build it as pages on your site (wolt/site/). Static HTML/CSS/JS. Livereload makes every change instant in the viewport. This is the fastest path from idea to visible thing.

Only suggest the woltspace new-app skill if it genuinely needs a backend, npm/pip deps, or its own URL.

What you do NOT do

  • No identity questionnaire. Don't write memory files as a ceremony. Write them when there's something real to remember.
  • No onboarding ceremony. One message, then build.
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. 6d ago First seen · 52 lines · 25 tokens per session scan A 5f9c2f44f019

Subscribe to this mod's changes

create-wolt is a skill published in the GitHub repository jerpint/woltspace (12 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 435 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 2026-09-09.

Related

Other skills, from other repositories

material-ui-nextjs

Integrates Material UI with Next.js App and Pages routers using @mui/material-nextjs, Emotion cache providers, next/font, CSS layers with Tailwind/CSS Modules, Link component prop patterns, CSS theme variables SSR notes, and App Router useSearchParams + Suspense. Use when setting up or debugging MUI in a Next.js app.

mui/material-ui · 76 tokens

Webdesign

Design and integrate web interfaces via three paths: DirectDesign (write design inline with Anthropic frontend-design philosophy — the default workhorse), native /design + /design-sync Claude Code commands (preferred for code integration and design-system sync), or ClaudeDesign (drive claude.ai/design through…

danielmiessler/LifeOS · 134 tokens

Remotion

Creates programmatic video with React via Remotion — compositions, sequences, and motion graphics animated with useCurrentFrame() and rendered to MP4. USE WHEN video, animation, motion graphics, video rendering, React video, render video, animate content, make a short, create animations, video overlay, explainer…

danielmiessler/LifeOS · 121 tokens

frontend-ai-guide

Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates. Use when reviewing components, hooks, browser behavior, or frontend implementation completeness.

shinpr/claude-code-workflows · 41 tokens

recipe-front-adjust

Adjust an already-implemented UI in-session with verification against the design source.

shinpr/claude-code-workflows · 18 tokens

recipe-front-design

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval.

shinpr/claude-code-workflows · 22 tokens