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 romshark/datapages --skill datapages-offlinegit clone --depth 1 https://github.com/romshark/datapagesWrote 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/romshark/datapages/datapages-offline)<a href="https://agentmods.dev/skills/romshark/datapages/datapages-offline"><img src="https://agentmods.dev/badge/skills/romshark/datapages/datapages-offline/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/romshark/datapages/datapages-offline"><img src="https://agentmods.dev/badge/skills/romshark/datapages/datapages-offline.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 | $0.00042 | $0.02414 |
| Opus 5.5 | $0.00017 | $0.00966 |
| Sonnet 5.5 | $0.00008 | $0.00483 |
| Haiku 4.5 | $0.00004 | $0.00241 |
Grade A, and why
datapages-offline 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 yesterday.
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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offline and instant loads
Read datapages first for the build loop, hard rules and naming conventions.
modules/offline serves a service worker and adds registration to HTML responses. Handlers write its cache through the pageCache datapages.PageCacheWriter parameter:
- Snapshots (
Set): served only while the browser is offline. - Shims (
SetShim): served online too, at once, then replaced by the live page.
The worker runs only in a secure context (HTTPS or localhost). Everywhere else the API does nothing.
Configure the module
Declaring PageOffline generates a WithOffline option with that page's route:
// PageOffline is /offline
type PageOffline struct{ App *App }
func (PageOffline) GET(r *http.Request) (body datapages.Component, err error) {
return pageOffline(), nil
}
opts := []datapages.ServerOption{
// Self-host Datastar: the CDN is unreachable offline.
datapages.WithDatastarJS(assets.Path("datastar.js")),
datapagesgen.WithOffline(app.OfflineConfig()),
}
// OfflineWorkerVersion identifies the installed worker and its cache. Increment
// it after a Datapages upgrade or a change to Assets, ExcludePaths,
// CrossOriginDestinations, OfflineClass, or PageOffline. Changes to Assets or
// PageOffline require a new installation because the worker fetches them only
// during installation.
const OfflineWorkerVersion = 1
func OfflineConfig() offline.Config {
return offline.Config{
WorkerVersion: OfflineWorkerVersion,
// Precache the files required to render cached pages offline.
Assets: []string{
assets.Path("style.css"), assets.Path("datastar.js"),
},
}
}
For shims without PageOffline, install the module directly:
offline.WithServiceWorker("", offline.Config{WorkerVersion: 1})
offline.Config field |
default |
|---|---|
WorkerVersion |
1; increment after a Datapages upgrade or a change to Assets, ExcludePaths, CrossOriginDestinations, OfflineClass, or PageOffline |
ScriptURL |
/service-worker.js; the scope is the whole origin either way |
Assets |
none; files cached during installation |
OfflineClass |
is-offline, toggled on <html> while offline |
CrossOriginDestinations |
image, style, script, font; empty non-nil disables |
ExcludePaths |
none; same-origin prefixes never cached |
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.
- yesterday Changed fd95cf950685
- 4d ago Changed 55f778f44f07
- 13d ago Changed · +2 lines e66c3af9ad9e
- 20d ago Changed · +2 lines 3e50ed6fd515
- 24d ago First seen · 199 lines · 42 tokens per session scan A 09292e5e7f30
datapages-offline is a skill published in the GitHub repository romshark/datapages (114 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 2,414 once invoked, about $0.0002 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 2026-09-22.
Other skills, from other repositories
playwright
Use when the task requires capturing or automating a real browser from the terminal.
pinchtab
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
ketch
Research skill for ketch — a fast stateless CLI for web search, OSS code search, curated library docs, page scraping, and site crawling; an optional MCP server exists for operators who want it, but the CLI is the primary interface. Use when a question needs live sources: 'research X', 'what are people saying about Y'…
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.
crawlberg
Crawl, scrape, and convert websites to Markdown using the local crawlberg CLI and its MCP server. Use when the user wants to fetch a page, follow links across a domain, enumerate URLs, or drive a real browser. Covers installation, the subcommands (scrape, crawl, map, interact, batch-scrape, batch-crawl, download…