Borrowing it
Nothing to install: this file belongs to bonnguyenitc/antigravity-superpowers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bonnguyenitc/antigravity-superpowers/main/.agent/skills/i18n-localization/SKILL.mdgit clone --depth 1 https://github.com/bonnguyenitc/antigravity-superpowersWrote 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/bonnguyenitc/antigravity-superpowers/i18n-localization)<a href="https://agentmods.dev/skills/bonnguyenitc/antigravity-superpowers/i18n-localization"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/antigravity-superpowers/i18n-localization/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/bonnguyenitc/antigravity-superpowers/i18n-localization"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/antigravity-superpowers/i18n-localization.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 | $0.00037 | $0.01287 |
| Opus 5 | $0.00018 | $0.00643 |
| Sonnet 5 | $0.00007 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
i18n-localization 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
i18n / Localization Lens
Philosophy: Localization is not translation. It's redesigning the experience for a different culture. A poorly localized app signals "we don't really care about your market."
Core Instincts
- i18n first, l10n second — build the architecture for internationalization before translating
- Never hardcode strings — every user-visible string lives in an external translation file
- RTL is a layout problem, not a text problem — Hebrew, Arabic require mirrored layouts
- Local market ≠ translated market — date formats, numbers, currencies, cultural norms all differ
- App Store localization = free ASO — localized store listings rank in local search without app changes
i18n vs l10n
| Term | Definition |
|---|---|
| i18n (internationalization) | Engineering — building support for multiple locales |
| l10n (localization) | Content — adapting content for a specific locale |
| t9n (translation) | Linguistic — converting text between languages |
Technical Requirements
Strings
- Never concatenate user-visible strings:
"Hello " + name→ use named placeholders:"Hello {name}" - Pluralization rules differ by language (Russian has 4 plural forms; English has 2)
- Use ICU message format for complex strings:
{count, plural, one {# item} other {# items}}
Date / Time / Numbers
| Category | Example variance |
|---|---|
| Date format | US: 12/31/2024, EU: 31/12/2024, ISO: 2024-12-31 |
| Time format | 12h (US) vs 24h (EU/Asia) |
| Number format | 1,234.56 (US) vs 1.234,56 (EU) vs 1 234,56 (FR) |
| Currency | Symbol position varies; decimal precision varies by currency |
| Calendar | Gregorian default; some markets use Islamic, Hebrew, Chinese calendars |
Always use: Intl.DateTimeFormat, Intl.NumberFormat (JS) or locale-aware libraries — never manually format.
Right-to-Left (RTL) Languages
Arabic, Hebrew, Persian, Urdu — require:
- Mirrored layout (left → right becomes right → left)
- Text alignment:
start/endinstead ofleft/right - Icons that indicate direction must be flipped
- Test with: RTL pseudo-localization before translating
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 · 127 lines · 37 tokens per session scan A 412fa16d418c
i18n-localization is a skill published in the GitHub repository bonnguyenitc/antigravity-superpowers (19 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 1,287 once invoked, about $0.0002 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
accessibility-i18n
A guide for building accessible and multilingual software. Accessibility means making interfaces usable with tools such as keyboards and screen readers; internationalisation prepares them for different languages, regions, and writing directions.
codeck
Route explicit requests from a host coding agent to one or more locally configured AI executors through Codeck, attach Markdown or other project files, moderate cross-model consultation, expose disagreements, and synthesize traceable results. Use when the user explicitly names Codeck or asks to consult, compare, or…
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…
copperhead
Change or verify a KiCad project through copperhead's gated pipeline. Use whenever a task touches .kicadsch or .kicadpcb files, a schematic, a PCB layout, a netlist, ERC/DRC, a BOM, or hardware design docs — instead of editing those files directly.
control-chrome
Control the user's Chrome browser for tasks that depend on existing Chrome state: tabs, logged-in sessions, or extensions. Prefer purpose-built connectors, APIs, or CLIs when available.
Presentations
Read, create or edit PowerPoint or Google Slides decks. Use for presentation, slide deck, PowerPoint, PPT, PPTX, or Google Slides requests.