cold-email

cold-email is a skill for Claude Code from humanizerai/agent-skills. It costs 36 tokens per session (495 once invoked), scanned A, original, MIT.

A guide for writing unsolicited sales emails using frameworks such as AIDA, PAS, and BAB. It asks for the recipient, goal, and personalization context, then sets rules for a short subject line, personalized opening, and one clear request.

In plain words
What is it for?
Use it to draft short outreach emails for meetings, introductions, feedback, or sales. It can tailor the message to a person’s role, company, industry, or a relevant detail.
Why use it?
It gives structure to cold emails, which are messages sent to people without an existing conversation. The rules reduce vague introductions, unnecessary detail, and emails with multiple competing requests.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to draft short outreach emails for meetings, introductions, feedback, or…

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

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/humanizerai/agent-skills/cold-email.svg)](https://agentmods.dev/skills/humanizerai/agent-skills/cold-email)
Your own site
<a href="https://agentmods.dev/skills/humanizerai/agent-skills/cold-email"><img src="https://agentmods.dev/badge/skills/humanizerai/agent-skills/cold-email.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 495 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 $0.00036 $0.00495
Opus 5 $0.00018 $0.00247
Sonnet 5 $0.00007 $0.00099
Haiku 4.5 $0.00004 $0.00049

Measured 7d ago against content hash 7a6431d1f528, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cold-email 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 7d 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/SKILL.md · 70 lines

What it actually says

Write Cold Email

Generate a cold email that gets responses using proven copywriting frameworks.

Input

Parse $ARGUMENTS for:

  • Target: Who they're emailing (role, company, industry)
  • Goal: What they want (meeting, intro, feedback, sale)
  • Context: Personalization hooks (mutual connection, recent news, specific pain point)

If arguments are incomplete, ask for the missing pieces.

Frameworks (Choose the best fit)

AIDA (Awareness → Interest → Desire → Action)

  • Hook with relevance
  • Build interest with value
  • Create desire with proof/benefit
  • Clear CTA

PAS (Problem → Agitate → Solution)

  • Identify their problem
  • Make it feel urgent
  • Position as the solution

BAB (Before → After → Bridge)

  • Their current state (problem)
  • Their ideal state (outcome)
  • How you bridge the gap

Hard Rules

  1. 50-125 words - Shorter emails get more replies
  2. Subject line: 3-5 words, lowercase, no clickbait
  3. First line: Personalized - reference something specific about them
  4. No fluff: Cut "I hope this email finds you well", "My name is...", "I wanted to reach out"
  5. One CTA: Single, specific ask (not "let me know if you're interested")
  6. Read time: Under 30 seconds
  7. Mobile-friendly: Short paragraphs, no walls of text

What Makes It Human

  • Sounds like a real person, not a template
  • Has a specific reason for emailing THIS person
  • Shows you did research
  • Doesn't oversell or use hype words
  • Has a clear "what's in it for them"

Output Format

Subject: [subject line]

[Email body]

[First name only]

Framework used: [which one and why] Personalization: [what angle you used] Word count: [number]

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. 7d ago First seen · 70 lines · 36 tokens per session scan A 7a6431d1f528

Subscribe to this mod's changes

cold-email is a skill published in the GitHub repository humanizerai/agent-skills (42 stars, last pushed 7mo ago), licensed MIT. It adds 36 tokens to every session and 495 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 2026-08-30.