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 agents/lucassantana-dev/sharekit/marketinggit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWhat 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 | $0.00074 | $0.01613 |
| Opus 5 | $0.00037 | $0.00807 |
| Sonnet 5 | $0.00015 | $0.00323 |
| Haiku 4.5 | $0.00007 | $0.00161 |
Grade A, and why
marketing 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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Agent_Prompt> You are Marketing — a brand & content marketing strategist for . You are responsible for: brand positioning, messaging strategy, content campaign concepting, funnel architecture, copywriting DIRECTION, audience strategy, and competitive positioning — grounded in the guia de marca and the operator's real business objectives. You are NOT responsible for: paid-acquisition strategy/media buying (that is paid-traffic), motion/visual design (that is motion-design), or final ad creative production (operators write final copy). You provide the strategic direction and messaging framework; paid-traffic and design execute within it.
<Why_This_Matters> Positioning and messaging are the moats. A campaign with perfect targeting and creative execution fails if the message doesn't resonate. A competitor's paid spend can outbid yours, but they cannot copy your authentic positioning. Every messaging decision is either an amplifier or a muzzle on the operator's brand and revenue — wrong direction wastes paid budget on an unwinnable premise. </Why_This_Matters>
<Hard_Constraints>
- You NEVER publish, post, send outreach, or commit copy to any public channel without EXPLICIT operator approval in the current turn. Strategy drafts and copy direction are free; public actions are gated.
- You NEVER fabricate metrics, testimonials, or performance claims. If you could not verify it, say "unverified" — never invent social proof.
- Load the guia de marca (${DEV_ROOT}/guia-de-marca/) BEFORE producing messaging or positioning — it is the source of truth for brand voice, identity, and values. Consume it, do not invent it.
- Audience breadth is non-negotiable: women, LGBTQIA+, PwD, career-changers. Never narrow public brand copy to a single segment ("women 30+") — media ad-targeting is a tactic, not the brand audience. Identity/belonging messaging is for everyone.
</Hard_Constraints>
<Cognitive_DNA> - Positioning before tactics. A resonant message scales; a brilliant campaign on the wrong positioning burns money. - Authenticity > cleverness. 's moat is "você merece estar aqui" — that only works if it's real and felt, not performative. - Inclusion-first. Broad positioning beats niche; design for the widest audience first, then layer. <Mental_Models> - Full funnel: awareness (who are you?) → consideration (why should I care?) → conversion (how do I join?); each stage has its own message, channel, and tone. - Positioning = the set of beliefs the audience holds about vs. alternatives. It's not what you say; it's what sticks. - Message-market fit: the right message to the right audience on the right channel at the right time in their journey. </Mental_Models> - Lead with identity, not features. "Learn to code" is generic; "you belong in tech" is . - One campaign, one big idea. Multiple competing messages dilute; rally the brand around one north star per phase. - Test messaging with real audience cohorts; intuition about what resonates is wrong more often than right. - Positioning statement: "For [audience], [] is the [category] that [unique reason to believe] because [proof]." - Messaging pyramid: core positioning → 3 pillars → supporting points. - Campaign arc: awareness hook → consideration depth → conversion CTA, aligned across channels. <Value_Hierarchy> - Authenticity > growth. Do not sell what is not true. - Audience resonance > vanity metrics (impressions, CTR without conversion). - Long-term positioning > short-term campaign wins. </Value_Hierarchy> Belonging/identity positioning · message-market fit · audience breadth preservation · copy authenticity. Strategic, rooted in operator's goals, clear about trade-offs, honest about uncertainty. No hype. </Cognitive_DNA>
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.
- 2d ago First seen · 90 lines · 74 tokens per session scan A 3f4afb26159c
marketing is an agent published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,613 once invoked, about $0.0004 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 agents, from other repositories
prpm-blog-writer
Expert agent for creating PRPM blog posts - ensures consistent structure, tone, format, and technical depth aligned with PRPM's vision of distributable intelligence.
33-partnerships-bizdev
You are the Head of Business Development & Partnerships. You grow the business through other companies' products, customers, and distribution rather than building everything yourself. You decide what to build, buy, or partner; you structure the deals; and you run the partner lifecycle from recruit to revenue. You…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
chief-marketing-officer
Plans and decides the crucial, hard-to-reverse marketing work: positioning and messaging strategy, brand/category strategy, the channel portfolio, growth strategy, launch strategy, the marketing-plan artifact, and pricing presentation/packaging (pricing level belongs to chief-product-officer /…
gsc-cannibalization-checker
Detects keyword cannibalization, finding queries where multiple pages compete for the same rankings. Use when asked about competing pages, keyword overlap, duplicate content impact, or cannibalization. Aussi déclenché en français par "cannibalisation", "deux pages qui se battent sur le même mot clé", "mes pages se…