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 ArabAgentSkills/Skills --skill mena-growth-channelsgit clone --depth 1 https://github.com/ArabAgentSkills/SkillsWrote 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/arabagentskills/skills/mena-growth-channels)<a href="https://agentmods.dev/skills/arabagentskills/skills/mena-growth-channels"><img src="https://agentmods.dev/badge/skills/arabagentskills/skills/mena-growth-channels/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/arabagentskills/skills/mena-growth-channels"><img src="https://agentmods.dev/badge/skills/arabagentskills/skills/mena-growth-channels.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 | $0.00045 | $0.01158 |
| Opus 5 | $0.00023 | $0.00579 |
| Sonnet 5 | $0.00009 | $0.00232 |
| Haiku 4.5 | $0.00005 | $0.00116 |
Grade A, and why
mena-growth-channels 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 11d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MENA Growth Channels
When To Use
Use this skill for Arab/MENA channel selection, growth test planning, paid social/search/SEO planning, WhatsApp commerce, creator/influencer channels, marketplace channels, partnerships, and experiment design.
When Not To Use
- Do not launch ads, send outbound messages, publish creator content, upload audiences, or spend budget.
- Do not claim a channel "works" in a country without scoped evidence.
- Do not use this skill as legal, privacy, platform, religious, or local media-buying approval.
Required Context
- Country or countries, segment, product category, target audience, channel candidates, language, budget range, and test period.
- Existing assets: landing pages, analytics, CRM consent state, creative, content, marketplace listings, partnership leads, or creator lists.
- Risk flags: paid ads, direct marketing, creator/testimonial, regulated category, minors, privacy, finance, health, identity, politics, religion, or national symbolism.
- Sandbox/test state versus production/live campaign state.
Common Workflows
- Classify the request as channel selection, paid social, search/SEO, WhatsApp commerce, creators, marketplaces, partnerships, or experiments.
- Create scoped channel notes with country, segment, channel, confidence, evidence, source URL, and review status.
- Convert unsupported channel claims into hypotheses,
Unknown from public docs,Unknown from public sources,Needs vendor access, orneeds expert review. - Design small tests with success metrics, stop rules, review gates, and rollback.
- Require explicit human approval before spend, send, launch, publish, or audience upload.
Default Workflow
- Read
sources.ymlfor source groups, channel notes, confidence labels, and caveats. - Load only the relevant reference file from
references/. - Use
references/channel-selection.mdfor any cross-channel recommendation. - Use
references/experiments.mdfor test plans and measurement. - Answer with source-backed facts, hypotheses, unknowns, review gates, and validation steps.
What ships with it
17 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.
- evals/expected_behaviors.yml 1.8 KB
- evals/prompts.yml 1.1 KB
- examples/channel-test-plan.md 2.2 KB
- examples/source-backed-answer.md 1.3 KB
- README.md 1.2 KB
- references/channel-selection.md 1.7 KB
- references/creators-influencers.md 1.7 KB
- references/experiments.md 1.6 KB
- references/integration-checklist.md 1.9 KB
- references/marketplaces.md 1.8 KB
- references/paid-social.md 1.7 KB
- references/partnerships.md 1.5 KB
- references/search-seo.md 1.5 KB
- references/whatsapp-commerce.md 1.8 KB
- scripts/list-vendors.mjs 126 B runs code
- sources.yml 8.4 KB
- vendors/.gitkeep 1 B
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.
- 11d ago First seen · 106 lines · 45 tokens per session scan A 226a99d6f128
mena-growth-channels is a skill published in the GitHub repository ArabAgentSkills/Skills (11 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,158 once invoked, about $0.0002 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
logo-designer
A guided workflow for creating logos, brand marks, wordmarks, icons, and other visual identity elements. A wordmark is a logo made mainly from a company or product name.
arabic-hooks-library
A library and writing aid for opening lines in Arabic content. A hook is the first line or idea intended to make someone continue reading or watching.
arabic-seo-distributor
Arabic SEO and content distribution skill. Use whenever the user needs to optimize Arabic content for search, select hashtags, plan distribution across platforms, write Arabic meta descriptions/titles, research Arabic keywords, or build a distribution strategy for Arabic media. Triggers on: Arabic SEO, hashtags…
content-repurposing
Arabic content repurposing and atomization skill. Use whenever the user wants to turn one piece of content into multiple formats, extract clips from a podcast or video, repurpose an article into social content, or build a full content calendar from a single asset. Triggers on: repurpose content, content atomization…
podcast-production
A workflow guide for producing Arabic podcast episodes from planning through promotion. It covers research, writing, recording, editing, publishing information, and marketing materials.
arabic-brand-voice
Arabic brand voice and editorial identity skill. Use whenever the user needs to define or apply a brand's tone in Arabic, create a style guide, calibrate content to match brand personality, or ensure consistency across Arabic content outputs. Triggers on: brand voice, style guide, tone of voice, editorial guidelines…