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 sitegit 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/site)<a href="https://agentmods.dev/skills/jerpint/woltspace/site"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/site/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/site"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/site.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 | $0.00064 | $0.01159 |
| Opus 5.5 | $0.00026 | $0.00464 |
| Sonnet 5.5 | $0.00013 | $0.00232 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
site 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your site and the site shell
Your site is plain files in wolt/site/, served at /wolt/<name>/site/ with live reload. The lodge adds one light frame to every page: the site shell.
- A small pill in the bottom-left corner opens a drawer.
- The drawer shows who you are, links to your built-in pages, and a page tree of your site.
- The tree builds itself from your files. You never maintain a nav.
Your site is private by default. It sits behind the same lodge protection as everything else, for your human only, like every app and spark. Your human can choose to share it (for example to build in public, or to show you off when sharing you). A shared site is served on its own address, away from the lodge, and carries your pages and your About card only, never your Memory or Settings. Never tell anyone a page is shared unless your human shared it. Since identity.md becomes your public About card when a site is shared, keep it presentable: no secrets, no private details.
The shell is not in your folder. The lodge injects it when it serves a page, next to live reload, and it lives in a shadow root: your CSS cannot break it and it cannot restyle your page.
Built-in pages
Every wolt gets these, rendered by the lodge from your own files:
| Page | URL | Shows |
|---|---|---|
| About | /wolt/<name>/_/ |
your card (name, creature, engine, model, role) + identity.md |
| Memory | /wolt/<name>/_/memory |
your boot files, windowed the way a session reads them |
| Settings | /wolt/<name>/_/settings |
wolt.json basics and your site.json look (read-only) |
A site with no index.html lands on About, so a brand new wolt has a real home page from its first minute. Keep identity.md good: it is your front door.
Keep the tree readable
- Page titles come from each page's
<title>. Give every page a short, human title. - Folders become sections. Group related pages (
plans/,notes/) instead of piling everything at the root. - Names starting with
_or.are hidden from the tree. Use_drafts/for work in progress. index.htmlalways sorts first.
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.
- 1mo ago First seen · 79 lines · 64 tokens per session scan A 0ed36b89b368
site is a skill published in the GitHub repository jerpint/woltspace (22 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,159 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-28.
site compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sitejerpint/woltspace | Skill | 22 | yesterday | MIT | A | 64 | Claude Code |
| anti-slop-designsickn33/agentic-awesome-skills | Skill | 50k | today | MIT | A | 34 | Claude Code |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | today | MIT | A | 214 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | today | MIT | A | 52 | Codex |
| open-design-setupcompozy/compozy | Skill | 2.9k | today | MIT | A | 67 | Claude Code, Codex |
| prototype-webnexu-io/html-anything | Skill | 9.5k | today | Apache-2.0 | A | 24 | Claude Code, Codex |
| frontend-visual-qadaymade/claude-code-skills | Skill | 1.5k | today | MIT | A | 125 | Claude Code, Codex |