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.
npx skills add ucoz-skills/agent-skills --skill ucoz-site-translator-skillgit clone --depth 1 https://github.com/ucoz-skills/agent-skillsWrote 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/ucoz-skills/agent-skills/ucoz-site-translator-skill)<a href="https://agentmods.dev/skills/ucoz-skills/agent-skills/ucoz-site-translator-skill"><img src="https://agentmods.dev/badge/skills/ucoz-skills/agent-skills/ucoz-site-translator-skill/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/ucoz-skills/agent-skills/ucoz-site-translator-skill"><img src="https://agentmods.dev/badge/skills/ucoz-skills/agent-skills/ucoz-site-translator-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 32 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 50 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00067 | $0.05163 |
| Opus 5.5 | $0.00027 | $0.02065 |
| Sonnet 5.5 | $0.00013 | $0.01033 |
| Haiku 4.5 | $0.00007 | $0.00516 |
Grade A, and why
ucoz-site-translator-skill 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 9d 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
uCoz Site Translator Skill
Version: 1.2
Usage accounting
After successfully completing the skill's main work, record the usage:
skills_tool(action="register_usage", skill_id="ucoz-site-translator-skill")
If the usage API is unavailable or returns an error, show a brief warning and continue the skill's main workflow. Do not ask the user for a UUID or site URL — the site is taken from the active ucoz-mcp connection (selected with select_site).
Purpose
You are an AI agent that translates and localizes uCoz site content through the current official ucoz-mcp, or copies content with translation to a separate target uCoz site.
The skill focuses on real translation work: module materials and categories, design templates and global blocks, site menus, Page Editor pages, and associated images. It is not a generic machine-translation wrapper. It must preserve uCoz variables, template syntax, protected fields, and content formats (plain/BBCode/HTML), and it must never write without a preview and explicit approval.
Mandatory connection model
This skill is designed to be used together with ucoz-mcp.
- Connect to
ucoz-mcp(https://www.ucoz.com/mcp, sign in to the uCoz account) and select the site:list_sites→select_site(site_id). All tools work on the selected site. - Work through MCP tools only:
content_read/content_write/content_deletefor module materials and categories;forum_read/forum_write/forum_deletefor the forum (notcontent_*);templates_read/templates_write/templates_deletefor templates, global blocks, menus, and Page Editor pages;shop_read/shop_write/shop_deletefor the shop;files_read/files_write/files_deletefor site files;modules_read/modules_write/modules_uninstallfor modules (there is nomodules_delete). - Do not ask the user for keys, tokens, or site URLs; do not reveal credentials in the chat, logs, reports, examples, or error messages.
- If a tool returns a permission error, report that the signed-in account does not have enough rights on the selected site (owner or administrator is required).
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago Changed · +1 tokens per session 772c2b2fc666
- 17d ago Changed · +8 lines · +4 tokens per session cf8adae966d4
- 1mo ago Changed · -19 lines 1e4ce48bc771
- 1mo ago Changed 1eb3ef0cfc75
- 2mo ago First seen · 367 lines · 62 tokens per session scan A 671d83bc4872
ucoz-site-translator-skill is a skill published in the GitHub repository ucoz-skills/agent-skills (24 stars, last pushed 8d ago), licensed MIT. It adds 67 tokens to every session and 5,163 once invoked, about $0.0003 per session on Opus 5.5. 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.
ucoz-site-translator-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ucoz-site-translator-skillucoz-skills/agent-skills | Skill | 24 | 8d ago | MIT | A | 67 | Claude Code |
| blog-localizeAgriciDaniel/claude-blog | Skill | 2.7k | 4d ago | MIT | A | 135 | Claude Code |
| blog-translateAgriciDaniel/claude-blog | Skill | 2.7k | 4d ago | MIT | A | 137 | Claude Code |
| blog-locale-auditAgriciDaniel/claude-blog | Skill | 2.7k | 4d ago | MIT | A | 123 | Claude Code |
| internationalizationrampstackco/claude-skills | Skill | 1.0k | 11d ago | MIT | A | 123 | Claude Code |
| page-metadatakostja94/marketing-skills | Skill | 1.1k | 2d ago | MIT | A | 116 | Claude Code, Codex |
| localization-strategykostja94/marketing-skills | Skill | 1.1k | 2d ago | MIT | A | 60 | Claude Code, Codex |