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 specsnl/agent-specs --skill fix-translationsgit clone --depth 1 https://github.com/specsnl/agent-specsWrote 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/specsnl/agent-specs/fix-translations)<a href="https://agentmods.dev/skills/specsnl/agent-specs/fix-translations"><img src="https://agentmods.dev/badge/skills/specsnl/agent-specs/fix-translations/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/specsnl/agent-specs/fix-translations"><img src="https://agentmods.dev/badge/skills/specsnl/agent-specs/fix-translations.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 | $0.00107 | $0.01113 |
| Opus 5 | $0.00053 | $0.00557 |
| Sonnet 5 | $0.00021 | $0.00223 |
| Haiku 4.5 | $0.00011 | $0.00111 |
Grade A, and why
fix-translations 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 4d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix {{TARGET_LANGUAGE}} Laravel Translations — {{REPOSITORY}}
Scan all {{TARGET_LANGUAGE}} Laravel translation files for values still in the source language, translate them, fix errors and typos, commit the changes, and open a PR.
Fixed context
- Repository:
{{REPOSITORY}} - Translation files: {{TRANSLATION_FILES_INLINE}}
— when not specified, default to Laravel's conventional locations:
lang/{{TARGET_LOCALE}}/**/*.phpandlang/{{TARGET_LOCALE}}.json(older projects:resources/lang/...) - PR title format:
{{PR_TITLE_PREFIX}}: <short description>
Workflow
Execute these phases in order.
Phase 1 — Scan for untranslated values
Read every file matching {{TRANSLATION_FILES_SCAN}} — when that is not supplied, scan
lang/{{TARGET_LOCALE}}/**/*.php and lang/{{TARGET_LOCALE}}.json (fall back to
resources/lang/... on older Laravel versions). For each file, identify values that are still in
the source language. A value needs translation if it:
- Uses source-language words as the primary language (e.g. "Save", "Cancel", "Overview")
- Contains a full source-language sentence or phrase
- Is a mix of {{TARGET_LANGUAGE}} and the source language
- Contains a typo that is clearly not {{TARGET_LANGUAGE}}
Do not flag:
- Keys (array keys are in the source language by convention). In JSON catalogues the key is the source string — translate the value, leave the key byte-for-byte untouched.
- Technical/universal strings like email addresses, URLs, currency symbols
- Values that are intentionally the same in both languages (e.g.
'Logo','URL') - Placeholder variables like
:count,:name
Phase 2 — Translate and fix
For each identified value, produce the correct {{TARGET_LANGUAGE}} translation. Apply these rules:
- Translate naturally — not word-for-word. Use the tone of the surrounding context.
- {{FORMALITY_NOTE}}
- Plural forms using Laravel's
|syntax must be preserved:'{\1'}in :count day|[2,*]in :count days'→ translate each segment, keep the|syntax intact. - Never rename or translate
:placeholdertokens (:count,:name,:Name,:NAME) — the casing carries Laravel's capitalisation behaviour, so copy them through verbatim. - Leave Blade and HTML fragments inside a value alone (
{{ $var }},@lang(...),<a href="...">) — translate only the surrounding prose. - Fix typos
- Fix wrong translations
- Fix mixed-language values
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.
- 4d ago Changed · +3 lines 1ad47cca9a75
- 9d ago First seen · 105 lines · 107 tokens per session scan A 9b725ef9d810
fix-translations is a skill published in the GitHub repository specsnl/agent-specs (2 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 1,113 once invoked, about $0.0005 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
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.