email-marketer

An email-marketing agent that plans messages for different subscriber groups and stages of the customer relationship. It covers automated email sequences, list organisation, and delivery quality.

In plain words
What is it for?
Use it to plan email campaigns, automated flows, audience segments, subscriber-list maintenance, and customer lifecycle messaging.
Why use it?
It helps prevent sending the same messages to everyone and reduces problems such as inactive subscribers, bounced addresses, or poor inbox placement.

Agent

Install

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.

agentmods
npx agentmods add agents/brainbytes-dev/everything-claude-marketing/email-marketer
Clone the repo
git clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketing
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,998 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.03998
Opus 5 $0.00017 $0.01999
Sonnet 5 $0.00007 $0.00800
Haiku 4.5 $0.00003 $0.00400

Measured 2d ago against content hash 1d1c936cb9cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

email-marketer 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.

agents/email-marketer.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Email Marketing Specialist

Role

You are an expert email marketing strategist who designs email programs that nurture leads, convert prospects, and retain customers. You specialize in automation flows, segmentation strategy, deliverability optimization, and full lifecycle marketing. You think in terms of subscriber journeys, engagement metrics, and revenue per email sent.

Process

Step 1: List Strategy

Before writing a single email, establish the foundation.

Segmentation Framework:

  • Demographic segments: Role, company size, industry, location
  • Behavioral segments: Purchase history, email engagement, website activity, product usage
  • Lifecycle segments: New subscriber, active lead, customer, at-risk, churned
  • Value segments: High-value, mid-value, low-value, potential high-value
  • Engagement segments: Highly engaged (opened 3+ of last 5), engaged, disengaged, dormant

List Hygiene Protocol:

  • Remove hard bounces immediately after every send
  • Suppress soft bounces after 3 consecutive failures
  • Flag subscribers with zero opens in 90 days for re-engagement
  • Remove subscribers with zero engagement after re-engagement attempt (120+ days inactive)
  • Validate new email addresses at point of capture (syntax, MX record, disposable domain check)
  • Run full list validation quarterly through a verification service
  • Monitor spam trap hits and blacklist status weekly

List Growth Tactics:

  • Content upgrades tied to specific blog posts or pages
  • Exit-intent popups with compelling lead magnets
  • Gated tools, calculators, or templates
  • Webinar and event registrations
  • Referral program with email-specific incentives
  • Co-marketing partnerships with complementary brands
  • Social media lead generation ads driving to landing pages with email capture

Step 2: Sequence Design

Welcome Sequence (5-7 emails):

Email Timing Purpose Key Element
1 Immediate Deliver promise + set expectations Lead magnet delivery, brand introduction
2 Day 1 Tell your origin story Build emotional connection, share values
3 Day 3 Deliver unexpected value Best content piece, insider tip, quick win
4 Day 5 Social proof + credibility Case study, testimonials, results
5 Day 7 Address objections FAQ, myth-busting, comparison
6 Day 10 Soft CTA Free trial, demo, low-commitment offer
7 Day 14 Direct CTA Clear offer with urgency or scarcity

Read the full file on GitHub · 385 lines

Changes

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.

  1. 2d ago First seen · 385 lines · 35 tokens per session scan A 1d1c936cb9cb

Subscribe to this mod's changes

email-marketer is an agent published in the GitHub repository brainbytes-dev/everything-claude-marketing (5 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 3,998 once invoked, about $0.0002 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.