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 swan-gtm/gtm-skills --skill email-subject-linesgit clone --depth 1 https://github.com/swan-gtm/gtm-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/skills/swan-gtm/gtm-skills/email-subject-lines)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/email-subject-lines"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/email-subject-lines/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/swan-gtm/gtm-skills/email-subject-lines"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/email-subject-lines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00155 | $0.03323 |
| Opus 5 | $0.00077 | $0.01662 |
| Sonnet 5 | $0.00031 | $0.00665 |
| Haiku 4.5 | $0.00015 | $0.00332 |
Grade A, and why
email-subject-lines 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 9d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Email Subject Lines
Generate 5-10 high-converting subject lines for any email using 100 battle-tested frameworks from elite direct-response marketers — matched to your email's specific intent, emotion, and hook.
Why This Works
Subject lines are the most leveraged words you'll ever write. A 10% improvement in open rate on a 10,000-person list means 1,000 more people reading your email — from changing a few words. But most people write subject lines last, when they're tired, using whatever comes to mind first. This skill reverses that by matching your email's intent to proven psychological frameworks that have generated millions in revenue across thousands of campaigns. Every framework is categorized by trigger type so Claude picks the right ones for YOUR specific email.
How to Use This Skill
When triggered, ask the user for:
To generate subject lines, I need:
- Paste your email (or describe what it's about)
- Email type — Newsletter, promotional, welcome, launch, nurture, announcement?
- Audience tone — Casual/friendly, professional, edgy, motivational?
- Any words to avoid? — Overused phrases, brand restrictions, etc.
If the user just pastes an email without context, analyze it and generate subject lines immediately.
Process
Step 1: Analyze Email Intent
Read the email content and identify:
- Primary goal: Sale, engagement, nurture, announcement, content delivery
- Core emotion: Fear, curiosity, aspiration, frustration, excitement
- Key hook elements: Numbers, results, pain points, authority figures, timeframes
Step 2: Match Frameworks
Select 3-5 framework categories that align with the email's intent:
| Email Intent | Best Framework Categories |
|---|---|
| Sales/promo | Urgency, FOMO, Results, Value |
| Educational | Curiosity, Quick Win, Contrarian |
| Story-based | Story, Pain Point, Transformation |
| Authority-building | Authority, Social Proof, Results |
| Challenge/launch | Action, Empowerment, Urgency |
| Newsletter/content | Curiosity, Value, Quick Win, Trend |
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.
- 9d ago First seen · 239 lines · 155 tokens per session scan A 5deb4536b41d
email-subject-lines is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 155 tokens to every session and 3,323 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
teaser-block-writer
Writes "read next," "related articles," or "previously on" teaser blocks for web pages, newsletters, or app interfaces — short, click-worthy summaries that drive readers from one piece of content to another.
email-marketing
Email marketing automation - campaign creation, sequence building, A/B testing, deliverability optimization, and analytics.
Mailchimp Automation
Automate Mailchimp email marketing campaigns, audience management, automations, and analytics.
fastmail-imap-newsletter-digest
Read emails from Fastmail via IMAP and process them (e.g., newsletter digest). Handles HTML→text extraction for newsletters where plain text fallbacks are useless. Summarization via self-contained Python script calling Qwen 3.5 (NanoGPT) and delivery via AgentMail.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…