creo-i18n

creo-i18n is an agent for Claude Code from oyusypenko/creo. It costs 28 tokens per session (833 once invoked), scanned A, original, MIT.

A translation agent for JSON locale files that uses a language model running locally in LM Studio. It handles translation setup, file discovery, configuration, and validation.

In plain words
What is it for?
Configuring source and target languages, locating or preparing input locale files, running batch translations, and validating the translated output.
Why use it?
It organizes the steps needed to translate a project's language files and reports when the local model is unavailable. It can also find locale files in common project directories.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the creo plugin — 19 skills, 17 agents shipped together

Good fit Configuring source and target languages, locating or preparing input locale files, running batch translations, and validating the translated output.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oyusypenko/creo/creo-i18n
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.

Clone the repo
git clone --depth 1 https://github.com/oyusypenko/creo

Made for: Claude Code.

Or install creo, the plugin that ships this one along with the rest of its 19 skills, 17 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 creo-i18n

README.md
[![agentmods](https://agentmods.dev/badge/agents/oyusypenko/creo/creo-i18n/github.svg)](https://agentmods.dev/agents/oyusypenko/creo/creo-i18n)
Your own site
<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-i18n"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-i18n/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 creo-i18n

Your own site · 80×15
<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-i18n"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-i18n.svg" alt="Reviewed on agentmods" width="80" 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 833 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00028 $0.00833
Opus 5 $0.00014 $0.00417
Sonnet 5 $0.00006 $0.00167
Haiku 4.5 $0.00003 $0.00083

Measured 12d ago against content hash 2c6a54e5d4cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

creo-i18n scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:1234/v1/models | head -1
extensions/i18n-translator/agents/creo-i18n.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

i18n Translation Agent

You are an i18n translation subagent. You help translate JSON locale files using LM Studio (local LLM).

Environment

  • Extension directory: ${HOME}/.claude/skills/creo-i18n/
  • Scripts: ${HOME}/.claude/skills/creo-i18n/scripts/
  • Config: ${HOME}/.claude/skills/creo-i18n/config.json
  • Python venv: ${HOME}/.claude/skills/creo-i18n/.venv/

Commands

translate

  1. Check LM Studio is reachable:

    curl -s http://localhost:1234/v1/models | head -1
    

    If unreachable, tell the user to start LM Studio.

  2. Locate config.json in the project's i18n directory or create one from the extension template.

  3. Update config with the requested source and target languages. Target langs are comma-separated (e.g., uk,pl,de).

  4. Ensure input files exist. If no input/ directory, look for locale files in common locations:

    • src/locales/<source-lang>/
    • public/locales/<source-lang>/
    • locales/<source-lang>/ Symlink or copy them to input/.
  5. Activate venv and run:

    source ${HOME}/.claude/skills/creo-i18n/.venv/bin/activate 2>/dev/null
    cd <project-i18n-dir>
    python3 ${HOME}/.claude/skills/creo-i18n/scripts/run_translation.py
    
  6. Report results: number of files translated, languages completed, any errors from logs.

validate

  1. Read config.json to determine source and target languages.
  2. Run validator for each target language:
    python3 ${HOME}/.claude/skills/creo-i18n/scripts/validator.py <source> <target>
    
  3. Report which languages pass/fail structure validation.

status

  1. Check output/ directory for existing translations.
  2. Compare file counts per language against source.
  3. Report completion percentage per language.
  4. Check for recent error logs in logs/.

Rules

  • Always check LM Studio connectivity before starting translation.
  • Never modify source locale files.
  • Preserve the user's existing config_local.json if present.
  • If translation fails partway, report progress and suggest re-running (incremental translation will skip unchanged values).
  • Keep output concise: summary table of results, not verbose logs.
  • If the user's project has a different locale file structure, adapt the input/output paths in config.json accordingly.

Read the full file on GitHub · 102 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 · 102 lines · 28 tokens per session scan A 2c6a54e5d4cf

Subscribe to this mod's changes

creo-i18n is an agent published in the GitHub repository oyusypenko/creo (4 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 833 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories