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 Swih/mistral-mcp --skill french-commit-messagegit clone --depth 1 https://github.com/Swih/mistral-mcpWrote 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/swih/mistral-mcp/french-commit-message)<a href="https://agentmods.dev/skills/swih/mistral-mcp/french-commit-message"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/french-commit-message/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/swih/mistral-mcp/french-commit-message"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/french-commit-message.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.00456 |
| Opus 5.5 | $0.00018 | $0.00182 |
| Sonnet 5.5 | $0.00009 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
french-commit-message 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 26d 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.
What it actually says
Message de commit en français
Utilise le prompt MCP french_commit_message, puis mistral_chat. Le chat est disponible dans core, metier-docs, admin et sur un endpoint compatible avec self-hosted. Vérifie mistral://capabilities si nécessaire.
- Utilise le diff fourni ou exécute
git diff --staged. Si l'index est vide, consultegit diffet précise que le message proposé décrit des changements non indexés. S'il n'y a aucun diff, demande la plage à résumer. - Choisis le type selon le changement principal :
feat,fix,refactor,docs,test,choreouperf. Ne déduis pas une fonctionnalité du seul nom d'un fichier. - Récupère le prompt
french_commit_messageavecdiffetscope. Malgré son nom,scopeattend le type ci-dessus, pas le nom d'un module. - Convertis chaque message texte du prompt en
{role, content: message.content.text}, puis appellemistral_chatavecmessages. Ometmodelpour respecter le modèle configuré.temperature: 0.3est facultatif et ne garantit pas une sortie déterministe. - Vérifie
isError, puis lisstructuredContent.textet confronte le message au diff.
Rends un message prêt à copier :
<type>(<portée>): <sujet français à l'impératif, 72 caractères maximum>
<corps facultatif expliquant la raison du changement>
Le sujet commence par une minuscule, sans émoji ni point final. N'invente pas de motivation ni de tests exécutés. Cette demande produit un message ; elle n'autorise pas à indexer des fichiers, créer un commit ou pousser une branche.
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.
- 26d ago Changed · -41 lines · -11 tokens per session a9e74a722fe8
- 1mo ago First seen · 66 lines · 57 tokens per session scan A 18277fcbe3e6
french-commit-message is a skill published in the GitHub repository Swih/mistral-mcp (15 stars, last pushed 25d ago), licensed MIT. It adds 46 tokens to every session and 456 once invoked, about $0.0002 per session on Opus 5.5. 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
papi-build
Invoke when executing a build via buildexecute. Covers branching, gestalt pre-build check, and post-build audit.
papi-auto
Continue an approved PAPI cycle through implementation, verification and review using bounded autonomy. Resume durable work without rebuilding it; propose new scope before persisting it.
pn-github-vertical-slices
Break a plan or PRD into tracer-bullet vertical slices and create GitHub Issues via GitHub MCP (official github/github-mcp-server). Dependencies first (AFK/HITL). Use after pn-writing-plans or pn-create-prd when work must ship as Issues.
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
commit
Commit staged or unstaged changes with an AI-generated commit message that matches the repository's existing commit style. Use when the user asks to 'commit', 'commit changes', 'create a commit', 'save my work', or 'check in code'.