Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/oyusypenko/creonpx agentmods add skills/oyusypenko/creo/creo-i18nWrote 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.
[](https://agentmods.dev/skills/oyusypenko/creo/creo-i18n)<a href="https://agentmods.dev/skills/oyusypenko/creo/creo-i18n"><img src="https://agentmods.dev/badge/skills/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.
<a href="https://agentmods.dev/skills/oyusypenko/creo/creo-i18n"><img src="https://agentmods.dev/badge/skills/oyusypenko/creo/creo-i18n.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.01150 |
| Opus 5 | $0.00031 | $0.00575 |
| Sonnet 5 | $0.00012 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
creo-i18n 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
i18n Translator Skill
Batch translate JSON locale files using a local LLM via LM Studio. Preserves JSON structure, placeholders, and validates output.
Commands
| Command | Description |
|---|---|
/creo i18n translate <source-lang> <target-langs> |
Translate JSON files from source language to one or more target languages (comma-separated) |
/creo i18n validate |
Validate that translated files match source structure |
/creo i18n status |
Show translation status: which languages are done, which have issues |
Examples
/creo i18n translate en uk,pl,de
/creo i18n translate en fr
/creo i18n validate
/creo i18n status
Prerequisites
- Python 3.8+ with
requestspackage - LM Studio running locally on port 1234 (default) with a loaded model
- Source JSON locale files in the
input/directory
Supported Languages (39+)
| Code | Language | Code | Language | Code | Language |
|---|---|---|---|---|---|
| ar | Arabic | bg | Bulgarian | cs | Czech |
| da | Danish | de | German | el | Greek |
| en | English | es | Spanish | et | Estonian |
| fi | Finnish | fr | French | he | Hebrew |
| hi | Hindi | hr | Croatian | hu | Hungarian |
| id | Indonesian | it | Italian | ja | Japanese |
| ko | Korean | lt | Lithuanian | lv | Latvian |
| ms | Malay | nl | Dutch | no | Norwegian |
| pl | Polish | pt | Portuguese | ro | Romanian |
| ru | Russian | sk | Slovak | sl | Slovenian |
| sr | Serbian | sv | Swedish | th | Thai |
| tr | Turkish | ua | Ukrainian | vi | Vietnamese |
| zh | Chinese (Simplified) | zh-TW | Chinese (Traditional) | fil | Filipino |
You can specify any language code supported by your LLM model.
How It Works
- Source files: Place JSON locale files in the
input/directory - Configure: Edit
config.jsonto set source language, target languages, and LM Studio URL - Translate: The translator walks each JSON file recursively, sending each string value to the LLM with context (the JSON key path)
- Validate: After translation, the validator checks that every translated file has the exact same structure as the source
- Output: Translated files are saved to
output/<lang>/preserving the original directory structure
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.
- 11d ago First seen · 139 lines · 62 tokens per session scan A adb391b83b46
creo-i18n is a skill published in the GitHub repository oyusypenko/creo (4 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 1,150 once invoked, about $0.0003 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.
Other skills, from other repositories
agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
guide-recap
Transform CHANGELOG entries into social content (LinkedIn, Twitter/X, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate ready-to-post content from guide updates.
ci-all
Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.
ci-pipeline
Push current branch and return the pipeline tracking URL (GitLab or GitHub Actions).
ci-status
Show current pipeline status for the active branch (GitLab CI or GitHub Actions).