give-first-cold-email

give-first-cold-email is a skill for Claude Code, Codex from swan-gtm/gtm-skills. It costs 162 tokens per session (2,014 once invoked), scanned A, original, MIT.

A guide for writing cold emails, which are unsolicited sales emails sent to potential customers. It creates an initial email and follow-ups centred on giving the recipient something useful before asking for work.

In plain words
What is it for?
Turning a product or service offer into outreach emails with low-effort replies, including awareness emails and follow-up messages.
Why use it?
It removes vague calls to action that ask busy prospects for time without offering a clear reason to reply.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Turning a product or service offer into outreach emails with low-effort replies, including awareness emails and follow-up messages.

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

Made for: Claude Code, Codex.

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 give-first-cold-email

README.md
[![agentmods](https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/give-first-cold-email/github.svg)](https://agentmods.dev/skills/swan-gtm/gtm-skills/give-first-cold-email)
Your own site
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/give-first-cold-email"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/give-first-cold-email/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 give-first-cold-email

Your own site · 80×15
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/give-first-cold-email"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/give-first-cold-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,014 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 $0.00162 $0.02014
Opus 5 $0.00081 $0.01007
Sonnet 5 $0.00032 $0.00403
Haiku 4.5 $0.00016 $0.00201

Measured 9d ago against content hash a082d2f9358d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

give-first-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 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.

skills/dima-bilous/give-first-cold-email/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The tool for writing a proper cold email. Produces a first email plus follow-ups where the reply costs the prospect nothing. It starts after the list: if the list is wrong, nothing here saves you.

The one rule: the reply must cost them nothing

There are two ways to earn a cold reply. Either you deliver value up front, or the offer is so good that the only thing left for the prospect to do is say yes. Everything else asks them to work: to imagine the value, to schedule, to act before receiving.

What this kills:

  • "Worth a quick call?" asks for their time in exchange for nothing.
  • "Can I send you a custom PDF?" is what everyone else in their inbox is already doing, with nothing concrete behind it. The moment they read it, you are filed with the other fifty.
  • Any CTA where the prospect has to do more than say yes.

Promising more after the yes is fine on both paths. The difference between an offer and an empty tease is that the offer is specific, backed by proof, and costs nothing to accept.

First, pick the goal

  • Building awareness: send the value directly and end. No ask at all; the impression is the goal. A useful email with no CTA is remembered precisely because nobody does it.
  • Getting on a call: the full shape below. The value lands before the call, so the call is a walkthrough, not a pitch.

If the real offer is high-ticket, sell the free step

The bigger the engagement, the less the first email should mention it. Nobody buys a five-figure build off one cold email, and naming it puts the price in their head before any value has landed.

So the outcome you sell is the free step's outcome: what the audit tells them, what the artifact does for them, what the mini tool saves them. Never what the engagement would do for them.

That includes the version dressed up as a benefit. "Teams we build this for add $2M in pipeline" still asks them to imagine buying something. "Here are the 40 accounts hiring for this right now" asks them to say yes to something that costs nothing.

Read the full file on GitHub · 106 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. 9d ago First seen · 106 lines · 162 tokens per session scan A a082d2f9358d

Subscribe to this mod's changes

give-first-cold-email is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 162 tokens to every session and 2,014 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.