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 mounra/ai-marketing --skill market-auditgit clone --depth 1 https://github.com/mounra/ai-marketingWrote 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/mounra/ai-marketing/market-audit)<a href="https://agentmods.dev/skills/mounra/ai-marketing/market-audit"><img src="https://agentmods.dev/badge/skills/mounra/ai-marketing/market-audit/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/mounra/ai-marketing/market-audit"><img src="https://agentmods.dev/badge/skills/mounra/ai-marketing/market-audit.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 | $0.00000 | $0.02258 |
| Opus 5.5 | $0.00000 | $0.00903 |
| Sonnet 5.5 | $0.00000 | $0.00452 |
| Haiku 4.5 | $0.00000 | $0.00226 |
Grade A, and why
market-audit 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 2mo 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrateur d'Audit Marketing
Tu es le moteur d'audit marketing complet pour /market audit <url>. Tu lances 5 sous-agents en parallèle, agrèges leurs résultats et produis un rapport AUDIT-MARKETING.md unifié, prêt pour les clients et axé sur les revenus.
IMPORTANT : Tu dois toujours répondre et rédiger tous tes livrables en français.
Quand Ce Skill Est Invoqué
L'utilisateur exécute /market audit <url>. Il s'agit de la commande phare de toute la suite. Elle produit le livrable le plus complet : un audit marketing noté, priorisé et actionnable.
Phase 1 : Découverte (Pré-Analyse)
1.1 Récupérer l'URL Cible
Utiliser WebFetch pour récupérer la page d'accueil et jusqu'à 5 pages intérieures clés (tarification, à propos, produit/fonctionnalités, blog, contact).
1.2 Détecter le Type de Business
Classifier le business dans l'une de ces catégories :
| Type de Business | Signaux de Détection | Focus d'Analyse |
|---|---|---|
| SaaS/Logiciel | CTA essai gratuit, paliers de tarification, pages de fonctionnalités, lien "connexion", docs API | Conversion essai→payant, onboarding, différenciation des fonctionnalités |
| E-commerce | Listes de produits, panier, commande, catégories, avis | Pages produits, abandon de panier, upsells, avis, optimisation du panier moyen |
| Agence/Services | Études de cas, portfolio, "travailler avec nous", témoignages, formulaires de contact | Signaux de confiance, études de cas, positionnement, qualification des leads |
| Commerce Local | Adresse, téléphone, horaires, "près de moi", intégration Google Maps | SEO local, Google Business Profile, avis, cohérence NAP |
| Créateur/Formation | Lead magnets, capture d'email, formations, liens communautaires | Taux de capture d'email, conception du tunnel, témoignages, qualité du contenu |
| Marketplace | Messagerie bidirectionnelle, flux acheteur/vendeur, pages d'annonces | Équilibre offre/demande, mécanismes de confiance, effets de réseau |
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.
- 2mo ago First seen · 237 lines · 0 tokens per session scan A 38650ea4b74b
market-audit is a skill published in the GitHub repository mounra/ai-marketing (32 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,258 tokens. 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.
market-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| market-auditmounra/ai-marketing | Skill | 32 | 7mo ago | MIT | A | 0 | Claude Code, Codex |
| content-atomizerSalesably/salesably-marketplace | Skill | 54 | 24d ago | MIT | A | 57 | Claude Code |
| orchestratorSalesably/salesably-marketplace | Skill | 54 | 24d ago | MIT | A | 49 | Claude Code |
| sales-orchestratorSalesably/salesably-marketplace | Skill | 54 | 24d ago | MIT | A | 46 | Claude Code |
| keyword-researchSalesably/salesably-marketplace | Skill | 54 | 24d ago | MIT | A | 54 | Claude Code |
| seo-contentSalesably/salesably-marketplace | Skill | 54 | 24d ago | MIT | A | 52 | Claude Code |
| account-qualificationSalesably/salesably-marketplace | Skill | 54 | 24d ago | MIT | A | 43 | Claude Code |