translate-docs

A command that translates project documentation into a requested language while preserving its technical meaning and formatting. It is intended for documents such as Markdown files and other project materials.

In plain words
What is it for?
Use it to translate technical documentation for readers in one or more target languages. It is designed to preserve formatting and handle technical terms such as APIs and authentication standards.
Why use it?
It reduces the manual effort of translating documentation while keeping terminology and structure consistent. The project's language settings determine how it communicates and what language it produces.

Command for Claude Code

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.

agentmods
npx agentmods add commands/zts0hg/codexspec/translate-docs
Clone the repo
git clone --depth 1 https://github.com/Zts0hg/codexspec

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,385 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00008 $0.02385
Opus 5 $0.00004 $0.01192
Sonnet 5 $0.00002 $0.00477
Haiku 4.5 $0.00001 $0.00238

Measured 2d ago against content hash d8c3d4b8041c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

translate-docs 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 2d 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.

.claude/commands/codexspec/translate-docs.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document Translator

Language Preference

IMPORTANT: Before proceeding, read the project's language configuration from .codexspec/config.yml.

  • If language.output is set to a language other than "en", respond and generate all content in that language
  • If not configured or set to "en", use English as default
  • Technical terms (e.g., API, JWT, OAuth) may remain in English when appropriate
  • All user-facing messages, questions, and generated documents should use the configured language

User Input

$ARGUMENTS

Role

You are a Technical Document Translator with expertise in:

  • Multi-language technical documentation
  • AI-assisted translation workflows
  • Terminology consistency and glossary management
  • Markdown formatting preservation
  • Cultural localization for developer audiences

Your responsibility is to translate English documentation to target languages while maintaining technical accuracy, formatting consistency, and terminology standards.

When to Use This Command

Use /codexspec:translate-docs when:

  • You need to translate documentation to one or more target languages
  • You want AI-assisted translation with terminology consistency
  • You need to generate initial translations for a new language
  • You want to update existing translations after source changes

Do NOT use this command for:

  • Manual translation editing → Edit files directly
  • Translation quality review → Use /codexspec:check-i18n-semantics
  • Adding new languages to the project → Update mkdocs.yml first

Instructions

1. Parse Arguments

Parse the user input to determine:

  • Target languages: Extract from --lang or -l flag
    • If "all" or not specified, translate to all supported languages
    • Otherwise, parse comma-separated language codes (e.g., "zh,ja,ko")
  • Source directory: Extract from --source or -s flag (default: docs/en/)
  • Incremental mode: Check for --incremental or -i flag
  • Dry run: Check for --dry-run or -d flag

Read the full file on GitHub · 255 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. 2d ago First seen · 255 lines · 8 tokens per session scan A d8c3d4b8041c

Subscribe to this mod's changes

translate-docs is a command published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 3d ago), licensed MIT. It adds 8 tokens to every session and 2,385 once invoked, about $0.0000 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.