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 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/new-app)<a href="https://agentmods.dev/skills/jerpint/woltspace/new-app"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/new-app/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/jerpint/woltspace/new-app"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/new-app.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 | $0.00034 | $0.01425 |
| Opus 5.5 | $0.00014 | $0.00570 |
| Sonnet 5.5 | $0.00007 | $0.00285 |
| Haiku 4.5 | $0.00003 | $0.00143 |
Grade A, and why
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 28d 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 — 140 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.
- 28d ago Changed · +2 lines 884b7d9cbcaa
- 2mo ago First seen · 138 lines · 34 tokens per session scan A 97b6597e6d89
new-app is a skill published in the GitHub repository jerpint/woltspace (22 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,425 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-09.
new-app compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| new-appjerpint/woltspace | Skill | 22 | today | MIT | A | 34 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | 3d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | today | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | today | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 573 | today | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 254 | today | MIT | A | 106 | Claude Code |