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 indranilbanerjee/contentforge --skill cf-translategit clone --depth 1 https://github.com/indranilbanerjee/contentforgeWrote 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/indranilbanerjee/contentforge/cf-translate)<a href="https://agentmods.dev/skills/indranilbanerjee/contentforge/cf-translate"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/contentforge/cf-translate.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00163 | $0.03559 |
| Opus 5 | $0.00081 | $0.01780 |
| Sonnet 5 | $0.00033 | $0.00712 |
| Haiku 4.5 | $0.00016 | $0.00356 |
Grade A, and why
cf-translate 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cf-translate — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Translation — Multilingual Publishing
Translate publication-ready ContentForge content into 15 languages while preserving brand voice integrity, citation accuracy, and SEO optimization. Three localization levels let you control the depth of cultural adaptation.
When to Use
Use /contentforge:cf-translate when you need:
- Translated content for international markets (15 languages)
- Brand-consistent multilingual content that matches your source voice in the target language
- SEO-localized content with keywords adapted for target market search behavior
- Citation-safe translations where URLs, source references, and inline citations remain intact
- Cultural adaptation beyond word-for-word translation (adapted or transcreated levels)
Prerequisite: Content must be produced (or imported) through the ContentForge pipeline first. Raw untreated content should go through /contentforge:create-content before translation.
Supported Languages
| Code | Language | Direction | Notes |
|---|---|---|---|
es |
Spanish | LTR | Spain + Latin America variants |
fr |
French | LTR | France + Canadian French |
de |
German | LTR | Compound word handling |
pt |
Portuguese | LTR | Brazil + Portugal variants |
it |
Italian | LTR | |
nl |
Dutch | LTR | |
ja |
Japanese | LTR | Honorifics and formality levels |
zh |
Chinese (Simplified) | LTR | Simplified by default, Traditional on request |
ko |
Korean | LTR | Honorific levels mapped to brand formality |
ar |
Arabic | RTL | Right-to-left layout considerations |
hi |
Hindi | LTR | Devanagari script handling |
ru |
Russian | LTR | |
pl |
Polish | LTR | |
tr |
Turkish | LTR | |
vi |
Vietnamese | LTR | Diacritics preservation |
Localization Levels
Literal (Level 1)
Word-for-word structural translation. Preserves the exact document structure, sentence order, and paragraph boundaries. Translates meaning accurately but does not adapt cultural references, humor, or idiomatic expressions.
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.
- 8d ago First seen · 282 lines · 163 tokens per session scan A 8497ade49bd7
cf-translate is a skill published in the GitHub repository indranilbanerjee/contentforge (26 stars, last pushed 21d ago), licensed MIT. It adds 163 tokens to every session and 3,559 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
hreflang-check
Audit hreflang implementation from supplied HTML, sitemap XML, or SEO-tool exports (it does not crawl sites) — running seven checks: self-referential tags, bidirectional pairs, valid ISO 639-1/3166-1 codes, x-default, duplicates, absolute URLs, and URL consistency — producing a 0-100 score, a language coverage matrix…
multilingual-score
Score translated or localized content into one composite quality verdict — technical translation scoring (length ratio, formatting, do-not-translate terms, placeholders), content quality in the target language, brand voice consistency, and target-market compliance — classified as Publish Ready (85+), Native Speaker…
region-config
Configure a brand's regional settings — timezone, languages, currency, compliance regulations (GDPR, CCPA, APPI, LGPD, EU AI Act Article 50, and more), local platforms, business hours, holiday calendars, and data-residency rules — written to a persistent per-region config file plus a practical compliance checklist.…
language-audit
Audit multilingual integrity across every language version of a site or content set — hreflang implementation, content parity (missing, outdated, or structurally divergent translations), translation-quality spot checks via language-router.py, regional compliance per market (GDPR, DPDPA, LGPD, PIPA, APPI, CCPA), and…
language-config
Configure the brand's multilingual settings in profile.json — primary and secondary languages, do-not-translate terms, preferred translation service per language (routed by language family across the translation MCPs you have connected), and locale formatting for dates, numbers, and currency — with…
continuous-improvement-loop
Run Part 12 of the engagement methodology — the continuous improvement loop that aggregates quarterly-review, customer-feedback, competitive, and operating signals into a Quarterly Product & Offering Improvement Brief for business leadership, plus fast 1-3 page ad-hoc briefs when a significant signal lands…