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 Pantani/tdmcp --skill vitepress-bilingual-pagegit clone --depth 1 https://github.com/Pantani/tdmcpWrote 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/pantani/tdmcp/vitepress-bilingual-page)<a href="https://agentmods.dev/skills/pantani/tdmcp/vitepress-bilingual-page"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/vitepress-bilingual-page/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/pantani/tdmcp/vitepress-bilingual-page"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/vitepress-bilingual-page.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 | $0.00078 | $0.00781 |
| Opus 5 | $0.00039 | $0.00391 |
| Sonnet 5 | $0.00016 | $0.00156 |
| Haiku 4.5 | $0.00008 | $0.00078 |
Grade A, and why
vitepress-bilingual-page 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 12d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- vitepress-bilingual-page — 100% identical, 0 lines differ
- vitepress-bilingual-page — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a page to the tdmcp VitePress site
The site lives under docs/, config in docs/.vitepress/config.ts
(base: "/tdmcp/", cleanUrls: true, deployed to
https://pantani.github.io/tdmcp/).
i18n convention — read this before deciding paths
Only the artist guide track is translated (EN + PT-BR). Everything else is English-only. The config encodes three nav groups:
artistGuide(base)/artistGuidePt→docs/guide/*.mdanddocs/pt/guide/*.md. This is the only mirrored track.devReference→docs/reference/*.md(English only).operations→ standalone pages likedocs/DEPLOYMENT.md,docs/ROADMAP.md(English only), plus external GitHub links.
So a privacy / legal page is NOT an artist-guide page. It belongs as a standalone page, English as the canonical version (legal text is fine in EN; the form needs exactly one privacy URL). Add a PT mirror only if the spec asks — do not force it just because the guide is bilingual.
Recommended placement for the privacy policy
- File:
docs/privacy.md→ clean URLhttps://pantani.github.io/tdmcp/privacy. - Frontmatter: give it a
title:(used bytransformHead) and consideraside: falsefor a legal page. - Nav: add to the
operationsarray inconfig.ts:{ text: "Privacy", link: "/privacy" }. (It's the legal/ops group, not the artist sidebar.) Put it near the end, before/after Changelog. - If a PT version is wanted:
docs/pt/privacy.md+ a{ text: "Privacidade", link: "/pt/privacy" }entry in the PT-side nav config.
The site uses
cleanUrls, so link to/privacy, never/privacy.html. For a page that needs a non-default URL (like DEPLOYMENT→deployment) you'd add arewritesentry — a lowercaseprivacy.mdneeds none.
How to verify a page is wired correctly
- The
.mdfile exists at the path whose URL you put in the nav. - The nav entry's
linkmatches the clean URL (no.md, no.html). npm run docs:buildpasses — VitePress fails the build on dead internal links, so a typo'd nav link or a broken in-page link is caught here. This is the gate; always run it after adding a page.- Loopback URLs (
localhost,127.0.0.1) in prose are ignored by the dead-link checker (seeignoreDeadLinks), so you can mention the bridge address freely.
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.
- 12d ago First seen · 58 lines · 78 tokens per session scan A fa4c9d13b5b6
vitepress-bilingual-page is a skill published in the GitHub repository Pantani/tdmcp (41 stars, last pushed 27d ago), licensed MIT. It adds 78 tokens to every session and 781 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
extract-source-sample
Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…
speak-human-tw
A Traditional Chinese editing guide for making public-facing writing sound more natural and less machine-generated. It also checks wording associated with Mainland China and half-width punctuation.
video-translate
Translate and dub existing videos into multiple languages using HeyGen. Use when: (1) Translating a video into another language, (2) Dubbing video content with lip-sync, (3) Creating multi-language versions of existing videos, (4) Audio-only translation without lip-sync, (5) Working with HeyGen's /v2/videotranslate…
inclusive-design
Use when working on inclusion, i18n/localization, global name/address forms, low-end devices, slow/metered networks, affordability, or first-time/low-confidence users; not WCAG/screen readers (see accessibility).
unreal-plugin-localization
A tool for translating Unreal Engine plugin localization files, which store the text shown in an editor or game. It works with PO files and can compile the finished translations into Unreal’s locres format.