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 agentmods add skills/swih/mistral-mcp/french-commit-messagenpx 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.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.00652 |
| Opus 5 | $0.00028 | $0.00326 |
| Sonnet 5 | $0.00011 | $0.00130 |
| Haiku 4.5 | $0.00006 | $0.00065 |
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 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Message de commit (FR, Conventional Commits)
Tu génères un message de commit Conventional Commits propre en français à partir du diff git.
Workflow
Étape 1 — Récupérer le diff
Sauf si l'utilisateur fournit un diff dans $ARGUMENTS, exécute :
git diff --staged
Si le résultat est vide :
- Vérifie s'il y a des changements non-stagés :
git status - Demande à l'utilisateur de stage les fichiers (
git add) ou propose-lui d'inclure les changements unstaged viagit diffsimple.
Étape 2 — Détecter le scope Conventional Commits
Inspecte les fichiers touchés et déduis le type :
| Patterns de fichiers | Type probable |
|---|---|
*.test.*, **/__tests__/**, test/** |
test |
README*, *.md, docs/** |
docs |
package.json, package-lock.json, Dockerfile, .github/** |
chore |
**/bench*, perf-related code |
perf |
| Refactor sans nouvelle feature ni fix (regarde le diff) | refactor |
| Bug visible dans le diff (correction d'erreur, edge case) | fix |
| Tout le reste | feat |
Si plusieurs types s'appliquent, choisis le dominant (le changement principal). Demande à l'utilisateur en cas d'ambiguïté forte.
Étape 3 — Générer le message
Appelle le prompt MCP french_commit_message exposé par le serveur mistral :
diff: le diff récupéré à l'étape 1scope: le type détecté à l'étape 2
Utilise mistral_chat avec :
model:codestral-latest(spécialisé code, comprend bien les diffs)temperature:0.3(peu de variabilité, on veut du déterministe)
Format de sortie
<type>(<portée>): <sujet 72 char max, impératif présent>
<corps optionnel : pourquoi, pas quoi>
Règles :
- Sujet en impératif présent, sans point final
- Pas d'émoji, pas de majuscule au début du sujet
- Corps uniquement si le « pourquoi » n'est pas trivial
Exemples
/mistral-mcp:french-commit-message→ utilisegit diff --staged/mistral-mcp:french-commit-message <diff>→ utilise le diff fourni
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 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 5d ago), licensed MIT. It adds 57 tokens to every session and 652 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 2026-08-30.
Other skills, from other repositories
git-workflow
Smart git operations including conventional commits, PR creation, branch management, and conflict resolution. Activates for "commit", "create PR", "push", "merge", "resolve conflict", "git" operations.
cmdb-patterns
Create ServiceNow CIs and cmdbrelci relationships, walk upstream/downstream impact, detect orphan/stale CIs, and align discovered CIs with the proper sysclassname hierarchy.
blast-radius
Trace ServiceNow configuration dependencies — what artifacts touch a given field, what calls a script include, table/app-level config inventory. Use before deletes, renames, or refactors.
change-management
Create and transition ServiceNow change requests (normal/standard/emergency), change tasks, affected CIs, approval routing, CAB scheduling, and conflict detection across maintenance windows.
incident-management
Manage ServiceNow incidents — creation with impact/urgency priority calc, auto-assignment by category, reassignment tracking, major incident declaration with bridge calls, time-based escalation, MTTR metrics.
mobile-development
Configure ServiceNow Mobile (Now Mobile/Agent) — syssgmobileapp screens, card builders, push notifications, offline sync rules, mobile actions for barcode/GPS, and offline-queue change processing.