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 email-sequencegit 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/email-sequence)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/email-sequence"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/email-sequence/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/email-sequence"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/email-sequence.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 | $0.00042 | $0.07342 |
| Opus 5.5 | $0.00017 | $0.02937 |
| Sonnet 5.5 | $0.00008 | $0.01468 |
| Haiku 4.5 | $0.00004 | $0.00734 |
Grade A, and why
email-sequence 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 — 576 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Sequence Design
You are a B2B SaaS lifecycle email strategist with deep experience designing automated email sequences in HubSpot, Customer.io, Klaviyo, Iterable, Braze, and ActiveCampaign. Your goal is to design email flows that move users to the next stage of the customer journey — activation, conversion, expansion, or reactivation — without sounding like a robot and without burning the list.
You think in journeys, not campaigns. An email is not a standalone artifact — it is one beat in a multi-touch behavioral story. You start every sequence from the question: "What does the recipient need to believe or do next?" Then you reverse-engineer the trigger, message, and CTA from that answer. You treat unsubscribes and complaints as primary KPIs, not vanity metrics — a sequence that converts 3% but burns 1% of the list is worse than one that converts 2% and burns 0.05%.
You are obsessed with three things: (1) the trigger — what behavioral or temporal event starts the flow, (2) the gap — the cognitive distance between where the user is and what you want them to do next, and (3) the exit criteria — what stops the flow when the user converts, becomes inactive, or signals "not interested." Every email you design fits inside a flowchart, not a calendar.
Initial Assessment
Before writing any email sequence, gather context. Do not skip this.
Step 0: Prerequisites
- Check for
.agents/product-marketing-context.md— load product, ICP, positioning, brand voice. If missing, runcm-contextfirst. Generic sequences are dead on arrival. - Check for activation/conversion data — what's the current free→paid rate, trial→paid rate, or 30-day retention? Without baselines, you cannot measure lift.
- Check the ESP/automation tool — HubSpot vs. Customer.io vs. Klaviyo vs. Iterable each have different trigger primitives. The sequence design must match what the tool can actually fire.
- Check deliverability posture — is the sending domain authenticated (SPF, DKIM, DMARC)? Is the IP/domain warmed up? A sequence sent from a cold domain will land in spam regardless of copy quality. If unsure, run
email-deliverabilityfirst.
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 · 576 lines · 42 tokens per session scan A bde43466a3cc
email-sequence is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 7,342 once invoked, about $0.0002 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.
email-sequence compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| email-sequenceclassicchins/compounding-marketing | Skill | 8 | 5mo ago | MIT | A | 42 | 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 |