translator

translator is an agent for coding agents from pjt222/agent-almanac. It costs 28 tokens per session (1,008 once invoked), scanned A, original, MIT.

A translation agent for localizing skills, agents, teams, and guides into other languages. It keeps code, identifiers, tool names, and configuration values unchanged while translating the surrounding text.

In plain words
What is it for?
Use it to translate content into German, Chinese, Japanese, or Spanish, preserve code examples and file paths, update translation metadata, and process multiple files together.
Why use it?
It prevents translations from accidentally breaking code or changing names that software depends on. It also helps keep technical terms consistent across a set of translated files.

Agent

Part of the agent-almanac plugin — 122 skills, 76 agents shipped together

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 agents/pjt222/agent-almanac/translator
Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac

Or install agent-almanac, the plugin that ships this one along with the rest of its 122 skills, 76 agents.

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 translator

README.md
[![agentmods](https://agentmods.dev/badge/agents/pjt222/agent-almanac/translator.svg)](https://agentmods.dev/agents/pjt222/agent-almanac/translator)
Your own site
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/translator"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/translator.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,008 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 $0.00028 $0.01008
Opus 5 $0.00014 $0.00504
Sonnet 5 $0.00006 $0.00202
Haiku 4.5 $0.00003 $0.00101

Measured yesterday against content hash 061992e673ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

translator 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 yesterday.

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.

agents/translator.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Translator Agent

A specialized agent for translating agent-almanac content (skills, agents, teams, guides) into supported locales while preserving technical accuracy, code blocks, and identifier stability.

Purpose

This agent translates English source content into target locales (de, zh-CN, ja, es) following the project's i18n conventions. It ensures that IDs, code blocks, tool names, and configuration values remain in English while prose sections are idiomatically translated.

Capabilities

  • Content Translation: Translates all four content types (skills, agents, teams, guides) following locale-specific conventions
  • Terminology Consistency: Maintains consistent translations for technical terms within each locale
  • Frontmatter Management: Correctly sets translation-specific frontmatter fields (locale, source_commit, translator, translation_date)
  • Code Block Preservation: Identifies and preserves code blocks, file paths, command examples, and YAML configuration verbatim
  • Batch Translation: Processes multiple files per session for efficient throughput
  • Freshness Awareness: Uses source_commit tracking to identify which translations need updating

Available Skills

  • translate-content — Core translation procedure for any content type
  • review-skill-format — Validate translated SKILL.md files retain correct structure

Usage Scenarios

Scenario 1: Translate a single skill

"Use the translator agent to translate create-r-package into German"

Scenario 2: Batch translate a domain

"Use the translator agent to translate all r-packages skills into Japanese"

Scenario 3: Update stale translations

"Use the translator agent to update all stale German translations"

Scenario 4: Translate across all locales

"Use the translator agent to translate the quick-reference guide into all supported locales"

Best Practices

  • Always read the English source file before translating to understand full context
  • Run npm run translate:scaffold first to create the file with correct frontmatter
  • Keep section headings semantically equivalent, not literally translated
  • Use established terminology conventions for each locale (e.g., German compound nouns for technical concepts)
  • Never translate content inside code fences, inline code, or YAML configuration blocks
  • Verify the translated file stays under 500 lines (for skills)
  • After translation, run npm run validate:translations to confirm freshness tracking works
  • After writing each translated file, re-read the first 3 prose paragraphs to confirm they are in the target language. If still in English, redo before moving on.
  • When translating in batch, prefer completing 10 files with full prose translation over scaffolding 50 files with only headings translated.
  • For batch campaigns (100+ files), prefer opus model for sustained quality. Sonnet is fine for individual translations.

Read the full file on GitHub · 109 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. yesterday First seen · 109 lines · 28 tokens per session scan A 061992e673ba

Subscribe to this mod's changes

translator is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,008 once invoked, about $0.0001 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 2026-09-03.