cold-email-subject-lines

cold-email-subject-lines is a skill for Claude Code from cmj-hub/claude-cold-email. It costs 87 tokens per session (936 once invoked), scanned A, original, MIT.

A set of patterns for writing and reviewing cold-email subject lines, which are the short titles shown before an unsolicited business email is opened. It covers pain, curiosity, social-proof, and direct-request approaches.

In plain words
What is it for?
Use it to create or critique three to five subject lines for a cold email or target audience, with reply-rate notes based on a supplied swipe file.
Why use it?
It helps avoid vague, misleading, or spam-like subject lines while keeping them short and relevant. It also explains which writing approach each suggestion uses.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the cold-email plugin — 12 skills, 2 agents shipped together

Good fit Use it to create or critique three to five subject lines for a cold email or target audience, with reply-rate notes based on a supplied swipe file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cmj-hub/claude-cold-email/cold-email-subject-lines
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 cmj-hub/claude-cold-email --skill cold-email-subject-lines
Clone the repo
git clone --depth 1 https://github.com/cmj-hub/claude-cold-email

Made for: Claude Code.

Or install cold-email, the plugin that ships this one along with the rest of its 12 skills, 2 agents.

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 cold-email-subject-lines

README.md
[![agentmods](https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-subject-lines/github.svg)](https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-subject-lines)
Your own site
<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-subject-lines"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-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.

agentmods 80×15 button for cold-email-subject-lines

Your own site · 80×15
<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-subject-lines"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-subject-lines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 936 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.
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 $0.00087 $0.00936
Opus 5 $0.00044 $0.00468
Sonnet 5 $0.00017 $0.00187
Haiku 4.5 $0.00009 $0.00094

Measured 2d ago against content hash 97f154b96aa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cold-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 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.

skills/cold-email-subject-lines/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cold Email Subject Lines — 4-Framework Pattern Library

Loaded by cold-email when the user wants subject-line suggestions or critique.

Activation triggers

  • "Subject lines for..."
  • "Subject line ideas"
  • "Critique this subject"
  • "Better subject than..."
  • "What's a good subject for..."

The 4 framework families

Framework When to use Example
Pain Audience is problem-aware "Pipeline gap after the Q3 hire freeze?"
Curiosity Audience needs a hook before they'll open "What tried after their Series B"
Social proof Audience trusts other companies more than vendors "How hit 40% reply rate"
Direct Audience is short on time, you have a clear ask "15 min Thursday re: demand gen?"

The skill's job: given a draft cold email (or a target audience + EVP), suggest 3-5 subject lines spanning at least 2 frameworks.

Constraints (every subject)

  • ≤7 words (Gmail truncates around 30 chars mobile)
  • No ALL CAPS
  • No emojis (deliverability)
  • No Re: / Fwd: fakes (banned by bulk-sender rules)
  • No clickbait ("You won't believe...", "This one trick...")
  • No spam triggers — load references/spam-trigger-words.md for the list
  • Personalization (first name, company) where relevant — but not faked
  • Lowercase first letter often outperforms capitalized in B2B (test)

Workflow

1. Gather context

Input Why needed
audience (PSP description) Determines which framework family fits
evp Anchors social-proof and pain framings
intent (open / reply / book) Direct frameworks work better for booking
relationship (cold / re-engagement / referred) Different opening patterns

2. Generate 5 suggestions

Default: 1-2 per framework family (3-5 total). Order by predicted fit, not framework alphabetical.

| # | Framework | Subject | Notes |
|---|---|---|---|
| 1 | Pain | "Pipeline gap after the freeze?" | Anchors PSP directly; for problem-aware audience |
| 2 | Social proof | "How <peer> hit 40% reply rate" | Best if you have the case study |
| 3 | Curiosity | "<peer> tried this after Series B" | If audience is skeptical of direct claims |
| 4 | Direct | "15 min Thursday re: demand gen?" | If they're warm or you have signal-based timing |
| 5 | Pain | "Q3 demand gen plan question" | Conservative; fits exec inboxes |

Read the full file on GitHub · 104 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 Changed 97f154b96aa3
  2. 11d ago First seen · 104 lines · 87 tokens per session scan A f3f77640686a

Subscribe to this mod's changes

cold-email-subject-lines is a skill published in the GitHub repository cmj-hub/claude-cold-email (2 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 936 once invoked, about $0.0004 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.