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 Lingtai-AI/lingtai --skill html-reportgit clone --depth 1 https://github.com/Lingtai-AI/lingtaiWrote 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/lingtai-ai/lingtai/html-report)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/html-report"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/html-report/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/lingtai-ai/lingtai/html-report"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/html-report.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00119 | $0.01769 |
| Opus 5 | $0.00060 | $0.00885 |
| Sonnet 5 | $0.00024 | $0.00354 |
| Haiku 4.5 | $0.00012 | $0.00177 |
Grade A, and why
html-report 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 6d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML Report — Standalone Artifacts for Humans
You are writing an HTML file a human will open in a browser or receive as an attachment. This skill exists because agents repeatedly ship HTML with unrendered LaTeX inside <pre>/<code> blocks and other recoverable presentation gaps. Follow the checklist below before declaring the file ready.
When to use HTML
Reach for HTML — instead of plain text, Markdown, or a PDF — when the human will benefit from:
- Sectioned research memos or literature maps with anchor navigation.
- Dashboards or audit reports with tables/cards/callouts.
- Side-by-side comparisons (two columns, diff-style tables).
- Anything that contains rendered mathematics.
- Artifacts they will forward to others — HTML opens everywhere with no toolchain.
If the content is short and equation-free, plain text or Markdown is usually enough.
Standalone HTML skeleton
Start from the bundled template — it already wires up typography reset, cards,
callouts, tables, anchor nav, print styles, and MathJax. Copy it, fill in the
<!-- TODO --> markers, drop unused sections, and save under a project-local
path (paper/drafts/<topic>-$(date -u +%Y-%m-%d).html):
cp ~/.lingtai-tui/utilities/swiss-knife/reference/html-report/assets/template.html \
paper/drafts/<your-topic>-$(date -u +%Y-%m-%d).html
Key rules for any HTML you produce, whether from the template or freshly authored:
- One file, no external assets except CDN scripts. The human will move it around.
- Inline all CSS in a single
<style>block in<head>. - Set
<meta charset="utf-8">first. Math copy-paste from LaTeX sources frequently contains non-ASCII. - Set a sensible
<title>— the human will see it in browser tabs and saved-file names. - Use semantic tags (
<section>,<article>,<aside>,<nav>) — they reflow better on mobile and print. - Print stylesheet matters. A research memo often gets printed. Add
@media print { ... }to hide navigation and force readable margins.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 112 lines · 119 tokens per session scan A 3a16ebf4fb5b
html-report is a skill published in the GitHub repository Lingtai-AI/lingtai (670 stars, last pushed yesterday), licensed Apache-2.0. It adds 119 tokens to every session and 1,769 once invoked, about $0.0006 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
html-artifact-report
Create HTML report artifacts from notes or Markdown with paired JSON manifests for AI-agent audit and reuse.
restaurant-report-pdf
Generate a professional PDF restaurant report by scanning RESTAURANT-.md files in current directory and running the bundled Python ReportLab generator.
recruit-report-pdf
Professional PDF Report Generator — scans current directory for RECRUIT-.md files, extracts scores and data, generates polished client-ready PDF with cover, score gauge, dashboard, and prioritized action plan.
recruit-report-pdf
Professional PDF Report Generator — scans current directory for RECRUIT-.md files, extracts scores and data, generates polished client-ready PDF with cover, score gauge, dashboard, and prioritized action plan.
doc-kami-parchment
Warm parchment canvas (#f5f4ed), monochrome ink-blue accent (#1B365D), one serif family, and editorial-grade typography.
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.