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 growthack88/growth-marketing-os --skill mena-adsgit clone --depth 1 https://github.com/growthack88/growth-marketing-osWrote 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/growthack88/growth-marketing-os/mena-ads)<a href="https://agentmods.dev/skills/growthack88/growth-marketing-os/mena-ads"><img src="https://agentmods.dev/badge/skills/growthack88/growth-marketing-os/mena-ads/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/growthack88/growth-marketing-os/mena-ads"><img src="https://agentmods.dev/badge/skills/growthack88/growth-marketing-os/mena-ads.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 | $0.00258 | $0.02593 |
| Opus 5.5 | $0.00103 | $0.01037 |
| Sonnet 5.5 | $0.00052 | $0.00519 |
| Haiku 4.5 | $0.00026 | $0.00259 |
Grade A, and why
mena-ads 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 13d 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.
MENA Ads Command Center · مركز قيادة الإعلانات
By Mahmoud Omar · One skill that runs paid ads like a senior media buyer who knows the Arab market: it asks for the right inputs, does the maths, scores the account, and returns decisions with the next actions, not commentary.
How to call it
Users can type a command or just describe the problem in Arabic or English. Map the request to one or more commands (a "should I scale?" question on a COD store is calc + optimize):
| Command | Arabic triggers | What it returns | Load these references |
|---|---|---|---|
audit |
راجع حسابي · افحص الحملات | Scored health check (0-100, A-F) + top fixes | audit-checklist, the platform file(s), tracking |
plan |
خطة إعلانية · ميديا بلان · وزع الميزانية | Platform mix, budget split, funnel, KPI targets, 90-day roadmap | budget-scaling, mena-market, platform files |
build |
ابني حملة · اطلق حملة · هيكل الحملات | Campaign architecture, settings checklist, naming, launch QA | platform file, tracking |
optimize |
زود المبيعات · قلل التكلفة · أكبّر ولا أوقف؟ | Scale / hold / kill per campaign, budget moves | budget-scaling, platform file |
diagnose |
الروآس وقع · المبيعات نزلت · ليه مش شغال | Root cause by funnel layer + ranked fixes | budget-scaling §4, platform file, tracking |
creative |
أفكار إعلانات · هوكات · سكريبت · بريف UGC | Angle matrix, hooks, scripts, briefs, test plan | creative-system |
copy |
اكتب إعلان · كوبي | Ad copy per platform in the right dialect + EN | creative-system §5 |
tracking |
البيكسل · الكونفرجن API · التتبع | Pass/Partial/Fail per platform + fixes | tracking |
calc |
احسب · نقطة التعادل · الروآس الحقيقي | Break-even ROAS/CPA, real COD ROAS, learning budget, VAT | run scripts/ads_calc.py |
season |
رمضان · الجمعة البيضاء · العيد · اليوم الوطني | Seasonal flight plan + creative calendar | mena-market §3 |
competitors |
المنافسين · مكتبة الإعلانات | Competitor ad teardown from Meta Ad Library / TikTok Creative Center | creative-system §6 |
report |
تقرير · ريبورت للعميل | Weekly/monthly client report (AR or EN) | reporting |
compliance |
سياسات · الإعلان اترفض · ترخيص موثوق | Policy and regulation check per market | mena-market §6, platform file |
connect |
اربط حسابي · MCP | How to connect live ad accounts (read-only by default) | data-connections |
What ships with it
20 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.
- CREDITS.md 3.1 KB
- install.sh 2.7 KB runs code
- licenses/LICENSE-claude-ads.txt 1.0 KB
- licenses/LICENSE-claude-marketing-rebecca-rae-barton.txt 1.0 KB
- licenses/LICENSE-gomarble-marketing-agent.txt 1.0 KB
- licenses/LICENSE-meta-ads-skills.txt 1.1 KB
- README.md 9.6 KB
- references/audit-checklist.md 5.9 KB
- references/budget-scaling.md 6.5 KB
- references/creative-system.md 10 KB
- references/data-connections.md 4.7 KB
- references/google.md 9.7 KB
- references/mena-market-playbook.md 13 KB
- references/meta.md 13 KB
- references/other-platforms.md 4.2 KB
- references/reporting.md 3.4 KB
- references/snapchat.md 4.9 KB
- references/tiktok.md 5.2 KB
- references/tracking-measurement.md 6.2 KB
- scripts/ads_calc.py 20 KB runs code
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.
- 13d ago First seen · 108 lines · 258 tokens per session scan A 7e8228d4f885
mena-ads is a skill published in the GitHub repository growthack88/growth-marketing-os (120 stars, last pushed 6d ago), licensed MIT. It adds 258 tokens to every session and 2,593 once invoked, about $0.0010 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 2026-10-03.
Other skills, from other repositories
marketing-seo-contenido
Auditar SEO de una pagina o web a fondo, cubriendo SEO on-page, calidad de contenido (E-E-A-T), analisis de keywords, SEO tecnico y estrategia de contenido. Combina analisis automatico via scripts/analizarpagina.py con revision experta manual para producir una auditoria SEO accionable.
marketing-ads
Eres el motor de publicidad para /marketing ads . Generas campanas completas en varias plataformas con copy, variaciones, estrategia de audiencias, recomendaciones de presupuesto y specs creativas. Cada anuncio queda listo para produccion o para pasar al media buyer.
marketing-competidores
Eres el motor de inteligencia competitiva para /marketing competidores . Identificas competidores, analizas su estrategia de marketing y produces un informe comparativo que revela huecos de posicionamiento, tacticas robables y oportunidades de diferenciacion. La salida sirve tanto para decisiones estrategicas como…
marketing-emails
Eres el motor de email marketing para /marketing emails . Generas secuencias completas listas para enviar con asuntos, cuerpo, timing y estrategia de segmentacion. Cada secuencia se apoya en frameworks probados y benchmarks del sector.
marketing-funnel
Eres el motor de analisis de funnel para /marketing funnel . Mapeas el camino completo de conversion desde la primera visita hasta la compra, identificas drop-off points, cuantificas la friccion y recomiendas optimizaciones concretas con impacto estimado en revenue. Cada recomendacion se prioriza por lift estimado y…
marketing-informe-pdf
Generar un informe de marketing profesional y visualmente cuidado en PDF usando el script Python scripts/generarinformepdf.py. La skill recoge toda la data disponible de auditorias, la estructura en el JSON esperado, invoca el script y produce un PDF con marca, medidores de score, barras, tablas comparativas…