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 perniemann/pnCore --skill pn-html-previewgit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-html-preview)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-html-preview"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-html-preview/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/perniemann/pncore/pn-html-preview"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-html-preview.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 | $0.00029 | $0.00464 |
| Opus 5 | $0.00015 | $0.00232 |
| Sonnet 5 | $0.00006 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
pn-html-preview 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 7d 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.
What it actually says
HTML Preview
When to use
- Static landing page, component demo, or HTML email prototype (saved as
.htmlfor visual check). - Any request where the output is "one HTML file" and distinctiveness matters.
- After
pn-designorpn-frontend-designwhen stack is vanilla HTML.
Instructions
1. Obtain HTML
If not already in chat: ask the user to paste the ```html block or point to a file.
Extract the first fenced html block (or use the file contents if they gave a path). Strip the fence lines only; keep <!DOCTYPE html> through closing </html>.
2. Save
- Default directory:
html_outputs/at project root (create if missing). - Filename:
html_outputs/YYYYMMDD_HHMMSS_preview.htmlor a user-provided name (sanitized,.htmlonly). - Write UTF-8. Do not overwrite without confirmation.
3. Open and verify
- Open the file in the system default browser (e.g.
xdg-open,open, orstartwith file:// absolute path). If the environment blocks browser launch, print the absolute path and instruct the user to open it locally. - Quick pass: layout, typography, color, motion (if any), and reduced-motion behavior if media queries exist.
4. Evidence (optional)
For high-stakes UI, run pn-evidence-qa or capture a screenshot after load and attach to the summary.
5. Summary
Output: file path, how to reopen, and any issues found in the browser pass.
Guardrails
- Security: Do not fetch remote scripts into the file unless the user asked; prefer self-contained snippets for previews.
- Parser: If the model did not use a
```htmlfence, ask for a single fenced block — downstream tooling and this skill assume that format.
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.
- 7d ago First seen · 45 lines · 29 tokens per session scan A 23b144e80ea0
pn-html-preview is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 464 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 2026-09-03.
Other skills, from other repositories
brand-landingpage
Brand-first landing page designer — runs a brand-identity interview (colors, typography, shape language), then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use when the user asks to create, design, or build a landing page, homepage, or marketing page and has no established…
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.
honey-design
Same pixels, fewer tokens: dense CSS for user-facing UI.
chat-formatting-widgets
Governs the custom markdown widgets rendered in the QuantumByte chat interface. This includes the inline highlight-mark span (use on every question the user must answer). You must check this skill on every reply to format highlights.
deepseek-harness
Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.