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 jerpint/woltspace --skill woltspace-new-appgit clone --depth 1 https://github.com/jerpint/woltspaceWrote 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/jerpint/woltspace/woltspace-new-app)<a href="https://agentmods.dev/skills/jerpint/woltspace/woltspace-new-app"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/woltspace-new-app.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01343 |
| Opus 5 | $0.00018 | $0.00672 |
| Sonnet 5 | $0.00007 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
woltspace-new-app scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:{port}/ | head -20 How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New App Setup
An app is something you ship — an app, a tool, a service. It has its own server, dependencies, and manifest. It can be public. Apps live at wolts/apps/{name}/ and are served at /app/{name}/.
Apps are an escalation, not a default. Wolts should start with their site (wolt/site/) for lightweight work. Only create an app when the work needs its own server, dependencies, or is meant to be shared. Always confirm with the user before creating an app.
1. Confirm with the user
Before creating an app, make sure they want one:
"This sounds like it needs its own server/deps — want me to set it up as an app? Or keep it simple in your site for now?"
2. Create the directory
Apps live in the global apps directory (shared across all wolts):
mkdir -p /workspace/wolts/apps/{name}
cd /workspace/wolts/apps/{name}
3. Scaffold it
Based on the user's request, figure out stack and scaffold:
Simple HTML page:
# Just write the files — no deps needed
Vite + React/Vue/Svelte:
npm create vite@latest . -- --template react # or vue, svelte
npm install
Python + FastAPI:
uv init . && uv add fastapi uvicorn
Astro blog/site:
npm create astro@latest . -- --template blog
Clone a repo:
git clone <url> .
# Read the README, figure out deps, install them
4. Write woltspace.json
This is required — the platform only discovers apps that have woltspace.json. Without it, the app is invisible.
{
"name": "{name}",
"description": "What this app does",
"stack": "node",
"port": 4010,
"install": "npm install",
"start": "node server.js --port $PORT --host 0.0.0.0",
"keeper": "{your-wolt-name}",
"emoji": "🦊",
"public": false
}
Fields
| Field | Required | Description |
|---|---|---|
name |
yes | App name (matches directory name, globally unique) |
keeper |
yes | Your wolt name — who owns this app |
description |
no | What the app does |
stack |
no | Tech stack: python, vite, node, html |
install |
no | Install command (e.g. npm install, uv sync) |
port |
yes | Fixed port for this app (use 4000-5999 range). Pick one, it's yours permanently. Avoid 7777 (platform) and 3001 (TUI). Sites use 6000+ so no collisions. |
start |
no | Start command. Use $PORT — the platform expands it. Add --host 0.0.0.0 for network access. Null = app can't be started from the lodge. |
source |
no | Origin URL if cloned/forked |
emoji |
no | Display emoji (auto-assigned if omitted) |
public |
no | If true, the app is shared publicly when started. With a named tunnel: served at {name}.{domain} (e.g. corework.woltspace.com). Without: a random quick tunnel URL. Default: false. |
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.
- 8d ago First seen · 138 lines · 37 tokens per session scan A 1d4b89739714
woltspace-new-app is a skill published in the GitHub repository jerpint/woltspace (11 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,343 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…