translation-skill

translation-skill is a skill for Claude Code from zeenie-ai/OpenCompany. It costs 38 tokens per session (1,131 once invoked), scanned A, original, MIT.

A language tool that translates text, changes words into another writing system, or identifies the language being used. Transliteration changes the script without translating the meaning.

In plain words
What is it for?
Use it to translate between languages, transliterate names or text, and detect what language a passage uses.
Why use it?
It helps choose the right operation when you need readable translated text, native-script input, or language identification.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to translate between languages, transliterate names or text, and detect what language a passage uses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zeenie-ai/opencompany/translation-skill
Install

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.

Any agent
npx skills add zeenie-ai/OpenCompany --skill translation-skill
Clone the repo
git clone --depth 1 https://github.com/zeenie-ai/OpenCompany

Made for: Claude Code.

Wrote 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.

agentmods badge for translation-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/zeenie-ai/opencompany/translation-skill/github.svg)](https://agentmods.dev/skills/zeenie-ai/opencompany/translation-skill)
Your own site
<a href="https://agentmods.dev/skills/zeenie-ai/opencompany/translation-skill"><img src="https://agentmods.dev/badge/skills/zeenie-ai/opencompany/translation-skill/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.

agentmods 80×15 button for translation-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/zeenie-ai/opencompany/translation-skill"><img src="https://agentmods.dev/badge/skills/zeenie-ai/opencompany/translation-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,131 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01131
Opus 5 $0.00019 $0.00566
Sonnet 5 $0.00008 $0.00226
Haiku 4.5 $0.00004 $0.00113

Measured 12d ago against content hash ee964e46f650, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

translation-skill 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.

server/skills/language_agent/translation-skill/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Translation Skill

Three tools, several providers behind each. Pick the provider that fits the language pair rather than defaulting to one.

How It Works

Connect Translate, Transliterate and/or Detect Language to the agent's input-tools handle. Each has a provider parameter, and the credential for the chosen provider must be configured in the Credentials modal.

The distinction that matters most

Translation changes the words. Transliteration changes the script.

Input Tool Output
hello translate_text → hi नमस्ते
namaste transliterate_text → hi नमस्ते

Both produce Devanagari, but only one changed the meaning. Getting this backwards is the most common misuse: if the user wants to read foreign text, they want translation; if they want to type their own language in its native script, or make a foreign name pronounceable, they want transliteration.

translate_text

Field Type Required Description
text string Yes Text to translate
provider enum No deepl, sarvam, openai
target_language string No Blank uses the provider default
source_language string No Blank auto-detects
translate_model string No Blank uses the provider default
formality string No Register, where the provider supports it
context string No Disambiguating context — not itself translated
preserve_formatting boolean No Keep line breaks and punctuation as-is
provider_options object No Vendor-specific extras

Returns translated_text and detected_source_language.

Choosing a provider

  • deepl — best quality for European languages, and the only one that reports exactly how many characters it billed. Language codes are uppercase (DE, EN-US, PT-BR). Prefer prefer_more / prefer_less for formality over more / less: the strict forms 400 on target languages that do not support the distinction. Does not transliterate or detect.
  • sarvam — Indian languages: 22 on sarvam-translate:v1, 11 on mayura:v1. Codes are always -IN suffixed (hi-IN, ta-IN). formality maps to its register modes: formal, modern-colloquial, classic-colloquial, code-mixed.
  • openai — LLM-backed. Covers pairs the others do not, needs no extra credential if a chat key is already configured, and takes free-form context well. Slower, and billed as tokens rather than characters.

Read the full file on GitHub · 114 lines

Changes

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.

  1. 12d ago First seen · 114 lines · 38 tokens per session scan A ee964e46f650

Subscribe to this mod's changes

translation-skill is a skill published in the GitHub repository zeenie-ai/OpenCompany (883 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 1,131 once invoked, about $0.0002 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.