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 pedroiff0/awesome-skills --skill mt-markup-preserving-translationgit clone --depth 1 https://github.com/pedroiff0/awesome-skillsWrote 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/pedroiff0/awesome-skills/mt-markup-preserving-translation)<a href="https://agentmods.dev/skills/pedroiff0/awesome-skills/mt-markup-preserving-translation"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/mt-markup-preserving-translation/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/pedroiff0/awesome-skills/mt-markup-preserving-translation"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/mt-markup-preserving-translation.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 | $0.00054 | $0.01354 |
| Opus 5 | $0.00027 | $0.00677 |
| Sonnet 5 | $0.00011 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
mt-markup-preserving-translation 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markup-preserving MT translation
The engine (LibreTranslate) WILL corrupt your source if you hand it raw Markdown. The fix is a single principle: never let the engine see anything structural — split the line, keep markup/URLs/wikilinks/proper-nouns/HTML literal, translate only the plain-text spans between them, rejoin.
Core strategy (apply in this order, per line)
- Split positional, not placeholder. Find protected spans (wikilinks, embeds, proper nouns, inline HTML) with
re.finditer, keep them literal, translate the text BETWEEN them. Placeholders (§N§,ZZNZZ,\x00N\x00) are silently mangled by the engine (see references/libretranslate-notes.md) — do NOT use them for anything except bold/italic (which uses real HTML tags:<strong>/<em>withformat=html). - Wikilinks/embeds — capture with
!?\[\s*\[\s*[^\[\]]*\]\s*\]\s*(the FIRST[is mandatory so the!of embeds is kept; a leading\s*before[drops the!and yields broken[[[). Keep literal — engine turns![[assets/b/b.pdf|B]]into[ [ [assets/b/b.pdf|Banner]]. - Internal links —
\[([^\]]*)\]\(([^)]+)\); translate only the anchor text, re-emit with the ORIGINAL url. Engine mangles URLs (integrra.iff.edu.br/p/x->https: / / integrra ... / x). - Proper nouns — positional, NOT to the engine. "Soja" -> "Soya", "Ana Cecília Soja" -> "Chapitre 1" if seen. Stash as literal spans (longest-first ordering matters).
- Tables — split each row on
|, translate per cell, rejoin. Engine drops inner|and merges columns if given the whole row. - Bold/italic — convert
**x**-><strong>x</strong>,*x*-><em>x</em>, call engine withformat=html, revert tags after. Engine preserves real HTML tags. - Headings — strip
##(+ emoji) as a prefix, re-prepend after translate; clean a leading^[-\*#]\s+the engine may inject.
Inline HTML blocks (carousels etc.) — the hard one
Non-greedy regex (<\w+...>.*?</\w+>) is NOT enough for nested tags: it matches the smallest tag and leaves the outer wrapper (<div class="media-carousel">, <a href=...>) to be fed to the engine, which then corrupts attributes and spaces URLs (< div classe = "media-carrousel" >, href = classe "/ pt-br / ... " = "carrousel-glide").
What ships with it
5 files 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.
- 12d ago First seen · 53 lines · 54 tokens per session scan A 235cbfeb46fd
mt-markup-preserving-translation is a skill published in the GitHub repository pedroiff0/awesome-skills (1 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 1,354 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
dx-roaster
Brutally honest developer-experience audit for a GitHub repo. Scores 10 DX dimensions (time-to-first-success, README clarity, visual proof, install, quick-start, docs, examples, community, trust, marketing), writes a shareable roast in the requested tone (brutal/honest/kind), produces a prioritized action plan ranked…
review-workflow
A review workflow for GitHub pull requests and issues, including judging whether changes can be merged or an issue can be closed. It requires read-only review, REST API access, and testing changes in practice.
mnemosyne-maintenance
Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.
code-review
When the user wants a thorough code review of changes, a PR, a file, or a feature branch. Use when the user says "review this," "code review," "check my code," "what's wrong with this," "review my PR," "look over this," "critique this," "review before merge," or when submitting code for quality assessment. Performs…
specification-compliance-review
Use this skill when an implementation is described as partial, passing, or complete and the task is to determine whether it actually satisfies an explicit specification. This is not a generic code review and not a re-run of the test suite. The central question is: does every normative requirement have both a correct…
github-code-review
Perform code reviews on local changes before pushing, or review open PRs on GitHub. Most of this skill uses plain git — the gh/curl split only matters for PR-level interactions.