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 khasky/awesome-agent-skills --skill awesome-translate-ru-engit clone --depth 1 https://github.com/khasky/awesome-agent-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/khasky/awesome-agent-skills/awesome-translate-ru-en)<a href="https://agentmods.dev/skills/khasky/awesome-agent-skills/awesome-translate-ru-en"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-translate-ru-en/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/khasky/awesome-agent-skills/awesome-translate-ru-en"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-translate-ru-en.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 | $0.00045 | $0.03113 |
| Opus 5.5 | $0.00018 | $0.01245 |
| Sonnet 5.5 | $0.00009 | $0.00623 |
| Haiku 4.5 | $0.00005 | $0.00311 |
Grade A, and why
awesome-translate-ru-en 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.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Translate Russian → English
Translate Russian text into natural English that reads as if a native English speaker wrote it. Preserve every structural and non-prose element of the source byte-for-byte, and never re-introduce AI-bureaucratic phrasing on the English side.
This skill is content-neutral: the source can be a Markdown document, a plain article, fiction, a technical spec, a chat transcript, marketing copy, source code with comments — anything written in Russian that needs to become English.
Strict Rules
1. Preserve structure and non-prose elements byte-for-byte
Whatever non-prose elements appear in the source must survive translation byte-for-byte. Common categories — apply only those that are present in the source:
- Section markers / headings (Markdown
#, RST===, HTML<h1>, plain1./2.numbering, etc.) — translate the heading text, but keep the marker, level, and order. - Code blocks in any format (fenced
```, indented,<pre>, etc.) — keep contents EXACTLY as-is. Do not translate code, identifiers, or comments inside code unless the user explicitly asks. - Inline code / identifiers in backticks or tags (
like_this,<code>like_this</code>) — never rephrase identifier names. - Links and URLs (
[text](url),<a href>, plain URLs) — keep targets intact. Translate only the visible link text. - Markup tags: HTML, XML, frontmatter (YAML/TOML), JSX — leave the structure untouched, translate only the human-readable text inside.
- Tables: same row count, column count, and cell alignment.
- List structure: same number of items, same nesting depth, same order.
- Emphasis markers on key terms (
**bold**,*italic*,<strong>,<em>) — keep both the markers and the term they emphasize. - Numbers, version strings, dates, timestamps, units, identifiers — exactly as they appear.
- Emojis and special characters (❌, ✅, →, em-dashes) — keep in the same positions.
- Placeholder tokens (
{username},%s,%d,{{var}}) — keep exactly as-is, and position them so the English sentence reads grammatically around them.
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.
- 7d ago Changed b5d34688fdb0
- 9d ago Changed · +2 lines 276ab6259bef
- 17d ago Changed · +13 lines 3c455155f53a
- 1mo ago Changed · -46 tokens per session 2bdf6f544b99
- 1mo ago Changed · +2 lines 47c21370568b
- 1mo ago Changed · +6 lines 182869a75b79
- 1mo ago Changed · -8 lines 15d037b77dda
- 1mo ago Changed dcee3a77e4ea
- 1mo ago Changed · +1 lines 7c69081a1be6
- 1mo ago First seen · 162 lines · 91 tokens per session scan A 66de1b71aa25
awesome-translate-ru-en is a skill published in the GitHub repository khasky/awesome-agent-skills (21 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 3,113 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 2026-08-31.
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.
bopomofo-rescue
A text-recovery tool for Taiwanese Bopomofo, also called Zhuyin, keyboard mistakes. It converts letter-and-number sequences typed with the wrong input mode back into likely Chinese text.
translate-skill
A project skill for translating mattpocock/skills content into Simplified Chinese. It preserves commands, names, file paths, code, links, and other behavior-critical details.
i18n
Audit internationalization coverage and find hardcoded strings. Use when asked to "check i18n", "find hardcoded strings", or verify translation coverage. Don't use for backend code, projects without an i18n library, accessibility (/a11y-audit), or bundle size (/perf-audit).
i18n-setup
Takes a project from hardcoded strings to internationalized, connected to Crowdin, and translating continuously. Use when someone wants to add i18n or multi-language support, internationalize an app, extract hardcoded strings, set up Lingui (or another i18n library), or connect Crowdin to a repository - including…
crowdin-cli
Guides correct usage of Crowdin CLI - the crowdin command that syncs localization files between a local project and Crowdin. Use whenever the user runs, scripts, or debugs crowdin commands, authorizes the CLI, creates or edits a crowdin.yml configuration, uploads sources, downloads translations, checks translation…