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.
git clone --depth 1 https://github.com/JasonColapietro/suede-creator-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/plugins/jasoncolapietro/suede-creator-skills/suede-marketing)<a href="https://agentmods.dev/plugins/jasoncolapietro/suede-creator-skills/suede-marketing"><img src="https://agentmods.dev/badge/plugins/jasoncolapietro/suede-creator-skills/suede-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/plugins/jasoncolapietro/suede-creator-skills/suede-marketing"><img src="https://agentmods.dev/badge/plugins/jasoncolapietro/suede-creator-skills/suede-marketing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
suede-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 yesterday.
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
{
"name": "suede-marketing",
"source": "./skills",
"strict": false,
"skills": [
"./suede-ab-testing",
"./suede-ad-creative",
"./suede-ads",
"./suede-ai-seo",
"./suede-analytics",
"./suede-aso",
"./suede-attribution",
"./suede-churn-prevention",
"./suede-co-marketing",
"./suede-cold-email",
"./suede-community-marketing",
"./suede-competitor-profiling",
"./suede-competitors",
"./suede-clip-to-guide",
"./suede-content-strategy",
"./suede-customer-research",
"./suede-directory-submissions",
"./suede-emails",
"./suede-free-tools",
"./suede-image",
"./suede-influencer-outreach",
"./suede-lead-magnets",
"./suede-marketing-council",
"./suede-marketing-loops",
"./suede-marketing-plan",
"./suede-newsroom",
"./suede-offers",
"./suede-onboarding",
"./suede-paywalls",
"./suede-pricing",
"./suede-product-marketing",
"./suede-programmatic-seo",
"./suede-prospecting",
"./suede-public-relations",
"./suede-referrals",
"./suede-revops",
"./suede-sales-enablement",
"./suede-sms",
"./suede-social",
"./suede-video"
],
"description": "Suede AI marketing and growth subset: SEO and AI search, paid acquisition and outbound, monetization (pricing, offers, paywalls), lifecycle and retention, and the measurement and operations layer. License notices for adapted material are in NOTICE.md."
}What it installs
The manifest is a name and a version. 40 skills travel with it, and installing the plugin installs all of them — 6,013 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill suede-ads A 91 tokens
- Skill suede-ad-creative A 98 tokens
- Skill suede-attribution A 80 tokens
- Skill suede-clip-to-guide A 95 tokens
- Skill suede-content-strategy A 94 tokens
- Skill suede-directory-submissions A 87 tokens
- Skill suede-image A 94 tokens
- Skill suede-video A 109 tokens
- Skill suede-ab-testing A 88 tokens
- Skill suede-ai-seo A 91 tokens
- Skill suede-aso A 87 tokens
- Skill suede-churn-prevention A 80 tokens
- Skill suede-competitor-profiling A 88 tokens
- Skill suede-customer-research A 95 tokens
- Skill suede-marketing-plan A 101 tokens
- Skill suede-newsroom A 102 tokens
- Skill suede-prospecting A 104 tokens
- Skill suede-sales-enablement A 105 tokens
- Skill suede-social A 116 tokens
- Skill suede-co-marketing A 85 tokens
- Skill suede-community-marketing A 83 tokens
- Skill suede-emails A 96 tokens
- Skill suede-influencer-outreach A 108 tokens
- Skill suede-marketing-council A 85 tokens
- Skill suede-offers A 94 tokens
- Skill suede-pricing A 83 tokens
- Skill suede-product-marketing A 104 tokens
- Skill suede-programmatic-seo A 96 tokens
- Skill suede-paywalls A 82 tokens
- Skill suede-referrals A 99 tokens
- Skill suede-lead-magnets A 86 tokens
- Skill suede-revops A 109 tokens
- Skill suede-competitors A 87 tokens
- Skill suede-free-tools A 95 tokens
- Skill suede-marketing-loops A 84 tokens
- Skill suede-public-relations A 98 tokens
- Skill suede-onboarding A 99 tokens
- Skill suede-analytics C 83 tokens
- Skill suede-cold-email A 88 tokens
- Skill suede-sms A 107 tokens
What ships with it
2 files beside marketplace.json#suede-marketing 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.
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.
- yesterday Changed · +1 lines c485ebbce2a7
- 3d ago Changed · -4 lines c3f0463c96de
- 1mo ago Changed 7a43e45d96cf
- 1mo ago First seen · 51 lines scan A f4b3f441109d
suede-marketing is a plugin published in the GitHub repository JasonColapietro/suede-creator-skills (126 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
dsh-skills
dsh-skills — generalized development-specification skills (defensive patterns, code conventions, testing tiers, prose standards, decision records, review/process discipline), extracted from DeepSeek Harness conventions and shaped by the mattpocock/skills architecture.
claude-shiploop
Autonomous delivery skills for Claude Code — pitch an idea, get an MVP. CEO/PO/DEV/Reviewer agent team with contracts, gates, and evidence rules.
liquid-org
Run a task as an evolved multi-agent ORG. The compose-org skill makes the running Claude embody a proven team — one subagent per specialist talent — then grades and records the result so good teams get reused on similar future tasks. Backed by the liquid-org CLI (plan / compose / record).
agb-recht-pruefer
Gigantischer AGB-Rechtsprüfer und Klausel-Entwerfer für deutsches Recht: §§ 305 bis 310 BGB, UKlaG, B2C/B2B, Branchen-AGB, Redlining, Klauselrisiko und rechtssichere Entwurfsworkflows.
rad-a11y
WCAG 2.2 AA accessibility toolkit for Claude Code. Six skills covering semantic HTML, ARIA patterns, keyboard/focus, forms, automated testing setup, and a static-analysis review pass; one autonomous reviewer agent. Four pure-stdlib Python validators (scan-jsx-patterns, check-tailwind-contrast with real WCAG sRGB ma.
salesforce-isv
Reusable skills for Salesforce ISVs and consulting partners, from Kugamon.