re-engagement-email-writer

re-engagement-email-writer is a skill for Claude Code from ur-grue/autopunk-media-skills. It costs 49 tokens per session (1,482 once invoked), scanned A, original, MIT.

An email or two-email sequence for newsletter subscribers who have stopped opening messages. It aims to bring them back or invite them to unsubscribe.

In plain words
What is it for?
Use it to write a final-chance campaign for inactive subscribers, explain newsletter changes, or clean up a mailing list.
Why use it?
It helps re-engage inactive readers before removing them from the list, while reducing the risk that inactive addresses harm email delivery.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the autopunk-media-skills plugin — 187 skills shipped together

Good fit Use it to write a final-chance campaign for inactive subscribers, explain newsletter changes, or clean up a mailing list.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ur-grue/autopunk-media-skills/re-engagement-email-writer
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.

Any agent
npx skills add ur-grue/autopunk-media-skills --skill re-engagement-email-writer
Clone the repo
git clone --depth 1 https://github.com/ur-grue/autopunk-media-skills

Made for: Claude Code.

Or install autopunk-media-skills, the plugin that ships this one along with the rest of its 187 skills.

Wrote 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.

agentmods badge for re-engagement-email-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/re-engagement-email-writer/github.svg)](https://agentmods.dev/skills/ur-grue/autopunk-media-skills/re-engagement-email-writer)
Your own site
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/re-engagement-email-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/re-engagement-email-writer/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.

agentmods 80×15 button for re-engagement-email-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/re-engagement-email-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/re-engagement-email-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,482 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00049 $0.01482
Opus 5 $0.00024 $0.00741
Sonnet 5 $0.00010 $0.00296
Haiku 4.5 $0.00005 $0.00148

Measured 8d ago against content hash b5a59125f702, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

re-engagement-email-writer 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 8d 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.

skills/newsletter/writing/re-engagement-email-writer/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Re-Engagement Email Writer

What This Skill Does

Writes a targeted re-engagement email (or short sequence of two emails) for subscribers who have stopped opening the newsletter, designed to recover attention or prompt a clean unsubscribe before list hygiene becomes a deliverability problem.

When To Use This Skill

  • Your email platform flags a segment of subscribers as "inactive" (typically: no opens in 60–90 days) and you need to either win them back or let them go cleanly
  • Your open rates have been declining and you want to send a re-engagement campaign before a full list clean
  • You are about to purge inactive subscribers and want to send a final chance email first
  • You have significantly changed the newsletter's direction or improved its quality since some subscribers originally joined, and want to reintroduce yourself

What You Need To Provide

Required: Newsletter name and a brief description of what it covers; typical inactivity threshold you are targeting (e.g. "no opens in 90 days"); the newsletter's current voice and tone Optional: Any recent improvements or changes to the newsletter worth highlighting to lapsed subscribers; the consequences if they do not re-engage (will you remove them from the list?); a reason to stay (offer, exclusive content, or best recent edition); whether you want a single email or a two-email sequence

How the Assistant Approaches This

  1. Opens with direct acknowledgment of the gap — not guilt, not passive aggression, but honest recognition that the subscriber has not been opening and that is a normal thing to happen; this disarms defensiveness
  2. Gives the reader a specific reason to re-engage, not a generic "we miss you" — either a concrete recent piece they missed that is worth their time, a change in the newsletter worth knowing about, or a honest pitch for what they originally signed up for
  3. Makes the ask clear and low-friction: a single button or link, either to confirm they want to stay or to read a specific piece; the goal is one click, not a journey
  4. If a two-email sequence: the second email arrives 5–7 days later with a final, shorter message that acknowledges this is the last chance and removes the pressure by making unsubscribing feel like a valid and easy choice (this often triggers re-engagement paradoxically)

Read the full file on GitHub · 101 lines

Files

What ships with it

1 file beside SKILL.md 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.

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. 8d ago First seen · 101 lines · 49 tokens per session scan A b5a59125f702

Subscribe to this mod's changes

re-engagement-email-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 49 tokens to every session and 1,482 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 2026-09-04.