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 ZyxWorks/agent-office --skill marketinggit clone --depth 1 https://github.com/ZyxWorks/agent-officeWrote 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/zyxworks/agent-office/marketing)<a href="https://agentmods.dev/skills/zyxworks/agent-office/marketing"><img src="https://agentmods.dev/badge/skills/zyxworks/agent-office/marketing/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/zyxworks/agent-office/marketing"><img src="https://agentmods.dev/badge/skills/zyxworks/agent-office/marketing.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 | $0.00065 | $0.00463 |
| Opus 5.5 | $0.00026 | $0.00185 |
| Sonnet 5.5 | $0.00013 | $0.00093 |
| Haiku 4.5 | $0.00006 | $0.00046 |
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 9d 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.
What it actually says
50 upstream skills sit in {{office.vendors}}/marketingskills/skills/<name>/SKILL.md. Pick the one or two that fit, read them, and follow them. Their references/ sit beside them.
- SEO and content: seo-audit, ai-seo, site-architecture, programmatic-seo, schema, content-strategy, aso
- CRO: cro, signup, onboarding, popups, paywalls
- Copy: copywriting, copy-editing, cold-email, emails, social, video, image, sms
- Paid and measurement: ads, ad-creative, ab-testing, analytics, attribution
- Growth and retention: referrals, free-tools, churn-prevention, community-marketing, lead-magnets, co-marketing, marketing-loops
- Sales and GTM: revops, sales-enablement, launch, pricing, offers, competitors, competitor-profiling, directory-submissions, prospecting, public-relations, events, influencer-marketing
- Strategy: product-marketing, marketing-ideas, marketing-psychology, marketing-plan, marketing-council, customer-research
Every upstream skill first reads the project's .agents/product-marketing-context.md. If it is missing, run product-marketing first or ask for the product, audience and offer.
~/AGENTS.md wins where they disagree. The upstream tools/ CLIs and its partner picks are not checked out: they are a sponsor list, and none is read or installed.
Upstream: coreyhaines31/marketingskills (MIT), only its skills/ folder, checked out by Agent Office at the commit its config/components.toml pins. office update moves it to a new pin, and a pin moves only after the upstream change was read. Do not pull it by hand unread: the files are instructions an agent follows.
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.
- 9d ago First seen · 21 lines · 65 tokens per session scan A c48fdc99a28e
marketing is a skill published in the GitHub repository ZyxWorks/agent-office (2 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 463 once invoked, about $0.0003 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 2026-10-29.
marketing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marketingZyxWorks/agent-office | Skill | 2 | today | MIT | A | 65 | Claude Code, Codex |
| verify-behaviornicknisi/dotfiles | Skill | 3.0k | 4d ago | MIT | A | 68 | Claude Code, Codex |
| create-skillwarpdotdev/warp | Skill | 66k | today | AGPL-3.0 | A | 64 | Claude Code, Codex |
| figma-generate-designwarpdotdev/warp | Skill | 66k | today | AGPL-3.0 | A | 160 | Claude Code, Codex |
| figma-create-design-system-ruleswarpdotdev/warp | Skill | 66k | today | AGPL-3.0 | A | 71 | Claude Code |
| figma-generate-librarywarpdotdev/warp | Skill | 66k | today | AGPL-3.0 | A | 95 | Claude Code |
| figma-implement-designwarpdotdev/warp | Skill | 66k | today | AGPL-3.0 | A | 81 | Claude Code |