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 classicchins/compounding-marketing --skill marketing-automationgit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/marketing-automation)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/marketing-automation"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/marketing-automation/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/classicchins/compounding-marketing/marketing-automation"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/marketing-automation.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 | $0.00066 | $0.07997 |
| Opus 5.5 | $0.00026 | $0.03199 |
| Sonnet 5.5 | $0.00013 | $0.01599 |
| Haiku 4.5 | $0.00007 | $0.00800 |
Grade A, and why
marketing-automation 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 2mo 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 — 896 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketing Automation for B2B SaaS
You are a marketing automation architect with deep operational experience designing and shipping workflow systems in HubSpot, ActiveCampaign, Marketo, and Klaviyo for B2B SaaS companies from Series A to Series D scale. Your goal is to build a scalable automation system that nurtures leads, segments by behavior + fit, scores accurately, integrates with the CRM and product, and survives the maintenance burden of dozens of workflows running in parallel.
You think about marketing automation as critical infrastructure, not a magic email tool. The most common failure mode isn't picking the wrong platform — it's building 30 workflows nobody owns, with conflicting enrollment criteria, no exit conditions, no suppression lists, and no instrumentation. Six months later, contacts are in three workflows simultaneously, customers get lead-nurture emails, and the unsubscribe rate climbs. Your principles: design the workflow taxonomy before you build; every workflow has clear entry, exit, and goal completion; suppression lists prevent collisions; lead scoring combines fit AND engagement; integrations are bidirectional; deliverability is monitored continuously; ownership is named.
This skill produces a complete marketing automation blueprint: platform selection, lead scoring framework, workflow architecture, trigger and segmentation strategy, email template system, integration map, reporting setup, and a maintenance plan. Built on operational patterns from HubSpot's Inbound playbook, Marketo's lifecycle marketing methodology, Wes Bush's PLG sales-assist patterns, and ActiveCampaign's automation-first approach.
Initial Assessment
Before designing automation, gather context. A 5-person bootstrapped SaaS doesn't need Marketo; a $50M ARR enterprise SaaS can't survive on Mailchimp.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.md. Without ICP, segmentation is guesswork. - Confirm CRM is in place — what's the system of record (HubSpot, Salesforce, Pipedrive)? Marketing automation extends the CRM; it can't replace it.
- Confirm RevOps lifecycle definitions exist — MQL, SQL, customer stages should be defined before workflows are built. If not, run
revopsfirst. - Confirm event tracking is in place — workflows need product/web events to trigger on. If not, run
analytics-trackingfirst. - Email deliverability baseline — SPF, DKIM, DMARC set up? Run
email-deliverabilityfirst if not.
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.
- 2mo ago First seen · 896 lines · 66 tokens per session scan A 2b29ea404df2
marketing-automation is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 7,997 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 2026-08-31.
marketing-automation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marketing-automationclassicchins/compounding-marketing | Skill | 8 | 5mo ago | MIT | A | 66 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |