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 Netcracker/qubership-ai-packages --skill french-developer-stylegit clone --depth 1 https://github.com/Netcracker/qubership-ai-packagesWrote 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/netcracker/qubership-ai-packages/french-developer-style)<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/french-developer-style"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/french-developer-style/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/netcracker/qubership-ai-packages/french-developer-style"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/french-developer-style.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 | $0.00092 | $0.04291 |
| Opus 5 | $0.00046 | $0.02145 |
| Sonnet 5 | $0.00018 | $0.00858 |
| Haiku 4.5 | $0.00009 | $0.00429 |
Grade A, and why
french-developer-style 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 10d 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Style français pour le texte développeur
Cette compétence s’applique à la prose française destinée à des développeurs ou à des utilisateurs de produits
logiciels : documentation et README, commentaires de code et docstrings, messages de commit, descriptions de PR,
changelog, chaînes d’interface, messages d’erreur et journaux, fichiers de localisation (.po, .properties, JSON
i18n, .ftl, .arb). La longueur ne compte pas : un msgstr d’une ligne, un commentaire // FIXME : … et un
README complet passent par la même grille de lecture.
L’objectif n’est ni le marketing, ni le SEO, ni l’évasion d’un détecteur d’IA. Il s’agit d’écrire un français clair, naturel et techniquement précis, sans calques de l’anglais, sans tournures administratives et sans tics de modèle de langage.
1. Quand appliquer cette compétence
Activez la compétence dès que la tâche concerne du texte français orienté logiciel, quel que soit son volume.
Actions déclenchantes :
- Création : nouvelles pages, README, commentaires, messages de commit, descriptions de PR, changelog, chaînes d’interface, messages d’erreur ou de journal.
- Traduction et localisation : depuis ou vers le français ; édition des fichiers
.po,.pot,.properties,.resx, JSON i18n, Fluent, ARB. - Réécriture : reprise d’un brouillon LLM avant commit (usage principal), retouche d’une prose humaine.
- Relecture et vérification : « vérifie la formulation », « est-ce naturel ? », « rends ça moins traduit », « relis les messages d’erreur », « audite le changelog », « contrôle les docstrings par rapport au code ».
Pour les surfaces couvertes et les non-déclencheurs, voir le fichier d’instructions du paquet.
Quand charger les modules et références :
- chaînes UI, formulaires, plurals ICU, Fluent →
modules/ui-strings.mdetreferences/icu-fluent-placeholders.md; - texte ciblant un public canadien ou québécois →
modules/fr-ca-overrides.md; - politique d’écriture inclusive demandée par le projet →
modules/inclusive-writing.md; - terminologie : vérifier
references/glossary-fr.tsvavant d’inventer une traduction ; - doute sur la typographie →
references/typography-cheatsheet.md; - doute sur le ton ou un calque LLM →
references/ai-tics-checklist.md.
What ships with it
13 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.
- linter/.vale.ini 545 B
- linter/vale-fr-tech/AITics.yml 986 B
- linter/vale-fr-tech/Anglicisms.yml 641 B
- linter/vale-fr-tech/README.md 4.0 KB
- linter/vale-fr-tech/Terms.yml 722 B
- linter/vale-fr-tech/Typography.yml 889 B
- modules/fr-ca-overrides.md 5.3 KB
- modules/inclusive-writing.md 4.6 KB
- modules/ui-strings.md 7.3 KB
- references/ai-tics-checklist.md 10 KB
- references/glossary-fr.tsv 10 KB
- references/icu-fluent-placeholders.md 6.6 KB
- references/typography-cheatsheet.md 6.1 KB
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.
- 10d ago First seen · 285 lines · 92 tokens per session scan A 550b945ddd55
french-developer-style is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 92 tokens to every session and 4,291 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.
tiktok-shop-cross-border
Cross-border selling on TikTok Shop. Market selection, logistics setup, localization strategy, compliance requirements, and international expansion. Use when the user asks about TikTok Shop international selling, cross-border ecommerce, global expansion, or selling in multiple countries.