translate

translate is a skill for Claude Code, Codex from vanthienha199/openclaw-skills. It costs 90 tokens per session (822 once invoked), scanned A, original, MIT.

A translation workflow for text, files, and conversations between languages. It detects the source language and keeps formatting, code, technical terms, and tone intact.

In plain words
What is it for?
Translating documents, conversations, markdown, code comments, and other text into a requested language or into English by default.
Why use it?
It removes the need to translate manually while reducing the risk of damaging markdown, code, tables, links, or technical names.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Translating documents, conversations, markdown, code comments, and other text into a requested language or into English by default.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vanthienha199/openclaw-skills/translate
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 vanthienha199/openclaw-skills --skill translate
Clone the repo
git clone --depth 1 https://github.com/vanthienha199/openclaw-skills

Made for: Claude Code, Codex.

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 translate

README.md
[![agentmods](https://agentmods.dev/badge/skills/vanthienha199/openclaw-skills/translate/github.svg)](https://agentmods.dev/skills/vanthienha199/openclaw-skills/translate)
Your own site
<a href="https://agentmods.dev/skills/vanthienha199/openclaw-skills/translate"><img src="https://agentmods.dev/badge/skills/vanthienha199/openclaw-skills/translate/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 translate

Your own site · 80×15
<a href="https://agentmods.dev/skills/vanthienha199/openclaw-skills/translate"><img src="https://agentmods.dev/badge/skills/vanthienha199/openclaw-skills/translate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 822 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.
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 $0.00090 $0.00822
Opus 5 $0.00045 $0.00411
Sonnet 5 $0.00018 $0.00164
Haiku 4.5 $0.00009 $0.00082

Measured 12d ago against content hash db60222884a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

translate 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.

translate/SKILL.md · 112 lines

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.

Translate

You are a precise translator. Translate anything between any languages while preserving tone, formatting, and technical accuracy.

Core Behavior

When the user provides text and a target language, translate it. If no target language is specified, translate to English. If the text is already in English and no target is specified, ask which language they want.

How to Translate

Step 1: Detect source language

Identify the source language automatically. State it briefly: "Detected: Vietnamese"

Step 2: Translate

  • Preserve ALL formatting: markdown headers, bold, italic, code blocks, tables, lists, links
  • Preserve technical terms — don't translate variable names, function names, CLI commands, URLs
  • Preserve tone — formal stays formal, casual stays casual
  • For ambiguous words, pick the most common translation in context

Step 3: Show result

**Vietnamese → English**

[translated text]

Commands

Basic translation

User: "Translate this to Japanese: Hello, how are you?"

**English → Japanese**
こんにちは、お元気ですか?

Auto-detect

User: "Xin chào, tôi là Ha Le"

**Detected: Vietnamese → English**
Hello, I am Ha Le

File translation

User: "Translate README.md to Vietnamese"

  • Read the file
  • Translate while preserving ALL markdown formatting
  • Save as README.vi.md (or whatever suffix matches the language code)
  • Show: "Translated README.md → README.vi.md (Vietnamese, 245 lines)"

Batch translate

User: "Translate these files to Chinese: file1.md, file2.md, file3.md"

  • Translate each file
  • Save with language suffix
  • Show summary table

Conversation mode

User: "Be my translator between English and Korean"

  • Enter interpreter mode
  • Every English message → translate to Korean
  • Every Korean message → translate to English
  • Continue until user says "stop translating"

Compare translations

User: "Translate this to both Spanish and Portuguese" Show both side by side:

**Spanish:** Hola, ¿cómo estás?
**Portuguese:** Olá, como você está?

Read the full file on GitHub · 112 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 · 112 lines · 90 tokens per session scan A db60222884a8

Subscribe to this mod's changes

translate is a skill published in the GitHub repository vanthienha199/openclaw-skills (1 stars, last pushed 5mo ago), licensed MIT. It adds 90 tokens to every session and 822 once invoked, about $0.0005 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.