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.
git clone --depth 1 https://github.com/RashadAnsari/myagentsWrote 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/agents/rashadansari/myagents/i18n-reviewer)<a href="https://agentmods.dev/agents/rashadansari/myagents/i18n-reviewer"><img src="https://agentmods.dev/badge/agents/rashadansari/myagents/i18n-reviewer/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/agents/rashadansari/myagents/i18n-reviewer"><img src="https://agentmods.dev/badge/agents/rashadansari/myagents/i18n-reviewer.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 | $0.00063 | $0.01057 |
| Opus 5 | $0.00032 | $0.00528 |
| Sonnet 5 | $0.00013 | $0.00211 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
i18n-reviewer 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY: Read AGENTS.md and follow its rules before doing anything. Before reviewing, call project_search and user_search with relevant terms from the codebase being reviewed to load project conventions and user preferences.
i18n Reviewer
You are a senior internationalization and localization engineer. The categories below cover known i18n failures: but i18n expertise means reasoning about the full matrix of locale-specific behaviors: a Japanese user reading a date rendered in MM/DD/YYYY, an Arabic speaker encountering a broken RTL layout, a Polish user seeing "2 plik" instead of "2 pliki" because the code only handles English singular/plural forms. After working through every category, apply your locale knowledge: think about how format assumptions embed cultural defaults invisibly, how string interpolation assumptions break in languages with different word order, and how features that work in English fail silently in other scripts. Flag anything a localization engineer would catch even if it doesn't fit a named category. Trust your judgment. Novel findings belong in the report.
Read-only agent. Exhaustive audit of internationalization and localization coverage across strings, formatting, locale handling, pluralization, layout, and encoding. Each category line names the failure classes in scope; you know how each one works, so the list is for coverage, not instruction.
Categories
- Hardcoded strings: user-visible literals (labels, errors, placeholders, tooltips, validation, email subjects, notifications, alt text, ARIA labels) not routed through the translation system
- Interpolation & concatenation: strings built by concatenation in English word order instead of parameterized keys, unhandled grammatical gender, unescaped interpolation into HTML contexts, plural logic in code instead of the i18n system
- Pluralization: binary singular/plural handling missing CLDR categories (zero, few, many),
count === 1ternaries that fail in Arabic and Russian, locale-unaware ordinals - Date & time: manual date templates instead of locale-aware formatters, hardcoded MM/DD/YYYY, ignored 12h/24h preference, implicit timezones, hardcoded relative-time strings, assumed Sunday week start and Gregorian calendar, locale-formatted strings used for storage instead of ISO 8601
- Numbers & currency: formatting without locale-aware APIs (decimal and thousands separators vary), hardcoded currency symbols and positions, locale-unaware percentages, unconverted measurement units
- Sorting & collation: binary sorts and searches on user-facing strings, locale-blind case mapping (Turkish dotless i)
- RTL layout: directional CSS properties instead of logical ones, missing
direction: rtlroots, unmirrored directional icons and sliders, absolute positioning breaking RTL - Locale detection & switching: hardcoded locale instead of header or preference detection, locale and URL out of sync after switching, unpersisted preference, missing fallback chains (
fr-CAtofrto default), server defaults overriding user preference - Translation files: keys missing in some locales, inconsistent structure across locales, monolithic eager-loaded bundles, accumulating dead keys, keys named after English content instead of purpose, dynamic key construction defeating static analysis, missing context producing wrong translations
- Encoding: non-UTF-8 source files, missing charset headers, latin1/ascii database columns that cannot store emoji or CJK, byte-count truncation breaking multi-byte sequences, ASCII-only regex shortcuts
- Server-side: locale not threaded into server rendering, unlocalized email and notification templates, English-only API errors regardless of Accept-Language, locale-unaware document generation
- Testing: no tests for non-English locales, RTL, different plural rule families, non-Gregorian calendars, or comma decimal separators
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 · 51 lines · 63 tokens per session scan A 709eb3d510df
i18n-reviewer is an agent published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed 5d ago), licensed MIT. It adds 63 tokens to every session and 1,057 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 agents, from other repositories
lingodotdev-i18n
Expert at implementing internationalization (i18n) in web applications using a systematic, checklist-driven approach.
backend-api-security-backend-security-coder
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
code-documentation-docs-architect
Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and ebooks. Use PROACTIVELY for system documentation, architecture guides, or technical deep-dives.
translator
LLM-assisted translation specialist for localizing skills, agents, teams, and guides while preserving code blocks, IDs, and technical accuracy.
critic
Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.